Skip to content

aiskillstore/marketplace / skills/0xbigboss/tilt

Use when checking deployment health, investigating errors, reading logs, or working with Tiltfiles. Queries Tilt resource status, logs, and manages dev environments.

FileKindSize
CLI_REFERENCE.mdmarkdown6.0 KB
SKILL.mdskill md4.9 KB
TILTFILE_API.mdmarkdown8.1 KB
skill-report.jsonconfig39.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-06T14:05:09.708Z",
    "slug": "0xbigboss-tilt",
    "source_url": "https://github.com/0xBigBoss/claude-code/tree/main/.claude/skills/tilt",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "8ccb87311af420f39139cde7852e94ad69f387d8ab57fed1b051ce53ec6763a4",
    "tree_hash": "dc0e3e375e98f6025ba90d533dbf574f4f2566f5ac1ae08400a778b343ad7e9f",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "tilt",
    "description": "Check Tilt deployment health, inspect logs, handle Docker Compose health gaps, and improve Tiltfiles for local development workflows.",
    "summary": "Guide AI agents through Tilt health checks, logs, lifecycle commands, and Tiltfile authoring.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "0xBigBoss",
    "license": "MIT",
    "tags": [
      "tilt",
      "devops",
      "kubernetes",
      "docker-compose",
      "logs"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network",
      "filesystem"
    ],
    "category": "devops"
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "Several Markdown backtick detections are false positives, but command examples intentionally guide agents to run local Tilt, Docker, git, jq, and zmx commands. The main concern is state-changing Tilt lifecycle operations, especially trigger, up, and down, which should require explicit user approval. I found no prompt injection or hidden data-exfiltration intent in SKILL.md, CLI_REFERENCE.md, or TILTFILE_API.md.",
    "remediation": [
      {
        "issue": "State-changing Tilt lifecycle commands",
        "suggestion": "Require explicit user confirmation before running tilt trigger, tilt up, tilt down, or commands that change cluster resources.",
        "severity": "medium"
      },
      {
        "issue": "Shell examples use local project names and zmx sessions",
        "suggestion": "Keep variable expansions quoted and avoid eval or untrusted command construction when adapting the examples.",
        "severity": "low"
      },
      {
        "issue": "Command examples can look like automatic actions",
        "suggestion": "Document which commands are read-only and which commands modify local resources.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 12,
            "line_end": 20
          },
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 26
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 28
          },
          {
            "file": "SKILL.md",
            "line_start": 28,
            "line_end": 28
          },
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 30
          },
          {
            "file": "SKILL.md",
            "line_start": 34,
            "line_end": 36
          },
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 43
          },
          {
            "file": "SKILL.md",
            "line_start": 43,
            "line_end": 52
          },
          {
            "file": "SKILL.md",
            "line_start": 52,
            "line_end": 55
          },
          {
            "file": "SKILL.md",
            "line_start": 55,
            "line_end": 55
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 65
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 69
          },
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 77
          },
          {
            "file": "SKILL.md",
            "line_start": 77,
            "line_end": 77
          },
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 89
          },
          {
            "file": "SKILL.md",
            "line_start": 89,
            "line_end": 93
          },
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 80
          },
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 89
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 104,
            "line_end": 104
          },
          {
            "file": "TILTFILE_API.md",
            "line_start": 253,
            "line_end": 253
          },
          {
            "file": "TILTFILE_API.md",
            "line_start": 342,
            "line_end": 342
          },
          {
            "file": "TILTFILE_API.md",
            "line_start": 343,
            "line_end": 343
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 80
          },
          {
            "file": "SKILL.md",
            "line_start": 83,
            "line_end": 83
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 12,
        "line_end": 20,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 20,
        "line_end": 26,
        "snippet": "#    An `Up (unhealthy)` compose container keeps runtimeStatus=ok/update=ok, so"
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 28,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 28,
        "line_end": 28,
        "snippet": "If a resource is `in_progress` when you check, **re-poll** before declaring it healthy — it can tran"
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 30,
        "line_end": 30,
        "snippet": "**Docker-compose resources are a blind spot.** Their `runtimeStatus`/`updateStatus` reflect only bui"
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 34,
        "line_end": 36,
        "snippet": "When Tilt runs on a non-default port, add `--port`:"
      },
      {
        "id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 36,
        "line_end": 39,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 39,
        "line_end": 43,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 43,
        "line_end": 52,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 52,
        "line_end": 55,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 55,
        "line_end": 55,
        "snippet": "- RuntimeStatus: `ok`, `error`, `pending`, `none`, `not_applicable`"
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 56,
        "snippet": "- UpdateStatus: `ok`, `error`, `pending`, `in_progress`, `none`, `not_applicable`"
      },
      {
        "id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 60,
        "line_end": 65,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 65,
        "line_end": 69,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 69,
        "line_end": 73,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 73,
        "line_end": 77,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 77,
        "line_end": 77,
        "snippet": "Follow `zmx` skill patterns — check for existing sessions, derive name from git root, use `zmx run` "
      },
      {
        "id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 79,
        "line_end": 89,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 89,
        "line_end": 93,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:80:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 80,
        "snippet": "PROJECT=$(basename \"$(git rev-parse --show-toplevel 2>/dev/null)\" || basename \"$PWD\")"
      },
      {
        "id": "external_commands:SKILL.md:79:template-literal-with-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Template literal with command substitution",
        "file": "SKILL.md",
        "line_start": 79,
        "line_end": 89,
        "snippet": "```bash"
      },
      {
        "id": "network:SKILL.md:104:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 104,
        "line_end": 104,
        "snippet": "- https://docs.tilt.dev/"
      },
      {
        "id": "filesystem:SKILL.md:80:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 80,
        "snippet": "PROJECT=$(basename \"$(git rev-parse --show-toplevel 2>/dev/null)\" || basename \"$PWD\")"
      },
      {
        "id": "filesystem:SKILL.md:83:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "SKILL.md",
        "line_start": 83,
        "line_end": 83,
        "snippet": "if zmx list --short 2>/dev/null | grep -q \"^${SESSION}$\"; then"
      },
      {
        "id": "network:TILTFILE_API.md:253:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "TILTFILE_API.md",
        "line_start": 253,
        "line_end": 253,
        "snippet": "url='https://github.com/org/tilt-extensions',"
      },
      {
        "id": "network:TILTFILE_API.md:342:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "TILTFILE_API.md",
        "line_start": 342,
        "line_end": 342,
        "snippet": "link('http://localhost:8080', 'API'),"
      },
      {
        "id": "network:TILTFILE_API.md:343:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "TILTFILE_API.md",
        "line_start": 343,
        "line_end": 343,
        "snippet": "link('http://localhost:8080/docs', 'Swagger'),"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "The fenced shell block instructs the agent to run tilt and jq against the local Tilt environment. These are legitimate read-only diagnostics, but they are still external command execution over local deployment state."
      },
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "severity": "medium",
        "reason": "This range includes a tilt and jq query for Docker Compose health and a status summary. It is expected operational tooling, but it executes local commands and may expose deployment details."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The detected text is a Markdown code fence and nearby explanatory prose. It is not Ruby backtick execution or an executable instruction by itself."
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The backticks on this line mark field names and status values in documentation. There is no shell or Ruby execution primitive on this line."
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.67,
        "severity": "medium",
        "reason": "The prose tells the agent to drop to docker inspect when Tilt status is insufficient. This is a legitimate diagnostic step, but it reads local container health data through an external command."
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This range only introduces non-default port usage and opens a Markdown bash block. The detected backticks are formatting, not runtime command execution."
      },
      {
        "id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.7,
        "severity": "medium",
        "reason": "The fenced block contains tilt get and tilt logs commands with a custom port. They are legitimate diagnostics, but they execute local CLI commands and can reveal local service data."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The detection falls on a Markdown fence boundary and a section heading. There is no executable command syntax in this range."
      },
      {
        "id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.74,
        "severity": "medium",
        "reason": "The resource status section instructs running tilt get and tilt wait commands. This is normal Tilt use, but it queries and waits on local deployment resources through external commands."
      },
      {
        "id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "This range is the end of a Markdown code fence and a status values heading. It does not contain Ruby backtick execution."
      },
      {
        "id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit documented RuntimeStatus enum values. They are formatting and cannot execute commands."
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit documented UpdateStatus enum values. They are formatting and cannot execute commands."
      },
      {
        "id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.73,
        "severity": "medium",
        "reason": "The logs section instructs running tilt logs commands, including JSON output. This is expected troubleshooting behavior, but logs may contain sensitive application or deployment information."
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.92,
        "reason": "The detection covers a Markdown fence boundary and the next section heading. It does not contain an executable external command."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.86,
        "severity": "medium",
        "reason": "The lifecycle block instructs running tilt trigger, tilt up, and tilt down. These commands change local development resources and should require explicit user approval."
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "This range closes a Markdown code block and introduces the next section. The actual lifecycle commands are covered by the prior finding."
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.62,
        "severity": "medium",
        "reason": "The line directs the agent to use zmx run for Tilt sessions. It is an intentional external command workflow, although the exact command appears in the following block."
      },
      {
        "id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.82,
        "severity": "medium",
        "reason": "The fenced shell block derives a project name, checks zmx sessions, and can start tilt up. This is real external command execution that can start local services."
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.92,
        "reason": "The range closes the shell block and gives safety guidance about when not to restart Tilt. It does not add executable backtick behavior."
      },
      {
        "id": "external_commands:SKILL.md:80:shell-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.68,
        "severity": "medium",
        "reason": "The shell example uses command substitution to call git and derive a project name from the working tree. It is quoted and not an injection pattern, but it still executes local commands."
      },
      {
        "id": "external_commands:SKILL.md:79:template-literal-with-command-substitution",
        "verdict": "confirmed",
        "confidence": 0.78,
        "severity": "medium",
        "reason": "The fenced shell template contains command substitution and zmx commands intended to be run by the agent. It is operationally useful, but it starts local processes when executed."
      },
      {
        "id": "network:SKILL.md:104:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The URL is a public Tilt documentation reference. It is not code that performs a network request or sends data."
      },
      {
        "id": "filesystem:SKILL.md:80:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The device path is stderr redirection to /dev/null in a shell example. This suppresses errors and does not read or write sensitive filesystem content."
      },
      {
        "id": "filesystem:SKILL.md:83:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The device path is stderr redirection to /dev/null for a zmx list check. It is not meaningful filesystem access beyond suppressing command errors."
      },
      {
        "id": "network:TILTFILE_API.md:253:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The URL appears in a Tiltfile API example for a custom extension repository. It is documentation, not an automatic network call or exfiltration endpoint."
      },
      {
        "id": "network:TILTFILE_API.md:342:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The localhost URL is a UI link example for a local API. It does not cause outbound network traffic or expose data by itself."
      },
      {
        "id": "network:TILTFILE_API.md:343:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The localhost URL is a UI link example for local documentation. It is not an external request or data exfiltration path."
      }
    ],
    "semantic_findings": [
      {
        "title": "State-Changing Tilt Commands Need Consent",
        "description": "The skill presents tilt trigger, tilt up, and tilt down as lifecycle commands. These commands can modify or remove local development resources, so agents should request explicit approval before running them.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 73
          }
        ],
        "confidence": 0.86,
        "confidence_reasoning": "The cited lines directly list lifecycle commands, including tilt down, which the CLI reference says removes resources created by tilt up. The risk is operational rather than malicious."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 12,
            "line_end": 20
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "The fenced shell block instructs the agent to run tilt and jq against the local Tilt environment. These are legitimate read-only diagnostics, but they are still external command execution over local deployment state."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "#    An `Up (unhealthy)` compose container keeps runtimeStatus=ok/update=ok, so",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 26
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This range includes a tilt and jq query for Docker Compose health and a status summary. It is expected operational tooling, but it executes local commands and may expose deployment details."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "**Docker-compose resources are a blind spot.** Their `runtimeStatus`/`updateStatus` reflect only bui",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 30
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.67,
        "confidence_reasoning": "The prose tells the agent to drop to docker inspect when Tilt status is insufficient. This is a legitimate diagnostic step, but it reads local container health data through an external command."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 39
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.7,
        "confidence_reasoning": "The fenced block contains tilt get and tilt logs commands with a custom port. They are legitimate diagnostics, but they execute local CLI commands and can reveal local service data."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 43,
            "line_end": 52
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.74,
        "confidence_reasoning": "The resource status section instructs running tilt get and tilt wait commands. This is normal Tilt use, but it queries and waits on local deployment resources through external commands."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 65
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.73,
        "confidence_reasoning": "The logs section instructs running tilt logs commands, including JSON output. This is expected troubleshooting behavior, but logs may contain sensitive application or deployment information."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 73
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.86,
        "confidence_reasoning": "The lifecycle block instructs running tilt trigger, tilt up, and tilt down. These commands change local development resources and should require explicit user approval."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "Follow `zmx` skill patterns — check for existing sessions, derive name from git root, use `zmx run` ",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 77,
            "line_end": 77
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.62,
        "confidence_reasoning": "The line directs the agent to use zmx run for Tilt sessions. It is an intentional external command workflow, although the exact command appears in the following block."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 89
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The fenced shell block derives a project name, checks zmx sessions, and can start tilt up. This is real external command execution that can start local services."
      },
      {
        "title": "Shell command substitution",
        "description": "PROJECT=$(basename \"$(git rev-parse --show-toplevel 2>/dev/null)\" || basename \"$PWD\")",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 80
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.68,
        "confidence_reasoning": "The shell example uses command substitution to call git and derive a project name from the working tree. It is quoted and not an injection pattern, but it still executes local commands."
      },
      {
        "title": "Template literal with command substitution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 89
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "The fenced shell template contains command substitution and zmx commands intended to be run by the agent. It is operationally useful, but it starts local processes when executed."
      },
      {
        "title": "State-Changing Tilt Commands Need Consent",
        "description": "The skill presents tilt trigger, tilt up, and tilt down as lifecycle commands. These commands can modify or remove local development resources, so agents should request explicit approval before running them.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 73
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.86,
        "confidence_reasoning": "The cited lines directly list lifecycle commands, including tilt down, which the CLI reference says removes resources created by tilt up. The risk is operational rather than malicious."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 3,
    "total_lines": 754,
    "audit_model": "codex",
    "audited_at": "2026-07-06T14:05:09.708Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Diagnose Tilt Dev Environments",
    "value_statement": "Local Tilt environments can hide failing resources, stale logs, and Docker Compose health problems. This skill guides Claude, Codex, and Claude Code through status checks, logs, and Tiltfile fixes.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "Tilt",
      "Tiltfile",
      "dev environment",
      "Kubernetes local development",
      "Docker Compose health",
      "resource status",
      "deployment logs"
    ],
    "actual_capabilities": [
      "Query Tilt UIResource status and summarize runtime and update health.",
      "Surface build errors before pending or in-progress resources.",
      "Identify Docker Compose healthcheck failures missed by basic Tilt status fields.",
      "Read and filter Tilt logs by resource, time range, tail count, and JSON output.",
      "Guide Tiltfile authoring for resources, live update, configuration, extensions, and UI links.",
      "Start or reuse a zmx session for tilt up using the project name."
    ],
    "limitations": [
      "Requires local Tilt and project tools to be installed.",
      "Commands inspect the current workstation and active development cluster.",
      "Examples do not replace production deployment policy review.",
      "Tiltfile examples need project-specific validation before use."
    ],
    "use_cases": [
      {
        "title": "Check Local Deployment Health",
        "target_user": "Application developer",
        "description": "Find failing Tilt resources, pending updates, and Docker Compose healthcheck problems after a code change."
      },
      {
        "title": "Triage Build And Runtime Errors",
        "target_user": "DevOps engineer",
        "description": "Use status queries and recent logs to identify why a local service did not reach a ready state."
      },
      {
        "title": "Improve Tiltfile Workflows",
        "target_user": "Platform engineer",
        "description": "Review Tiltfile resource definitions, live update ordering, dependency links, and UI labels."
      }
    ],
    "prompt_templates": [
      {
        "title": "Run A Health Check",
        "scenario": "Beginner check for a local Tilt environment.",
        "prompt": "Check this Tilt environment for errors first. Summarize failing resources, pending resources, and Docker Compose health issues. Ask before running commands that change state."
      },
      {
        "title": "Investigate One Resource",
        "scenario": "Focused troubleshooting for a specific resource.",
        "prompt": "Investigate the <resource> Tilt resource. Use status and recent logs. Explain the likely cause and the next verification step."
      },
      {
        "title": "Review A Tiltfile",
        "scenario": "Improve a Tiltfile without changing unrelated behavior.",
        "prompt": "Review my Tiltfile for dependency order, live update steps, trigger modes, and resource labels. Suggest minimal changes with clear reasons."
      },
      {
        "title": "Build A Troubleshooting Flow",
        "scenario": "Advanced investigation on a custom Tilt port.",
        "prompt": "Create a troubleshooting flow for intermittent Tilt failures on port <port>. Include status polling, log filters, Docker Compose health checks, and valid restart cases."
      }
    ],
    "output_examples": [
      {
        "input": "Check Tilt health for the current project.",
        "output": [
          "No runtime errors found. One resource is still in progress, so recheck before declaring success.",
          "One Docker Compose service reports an unhealthy healthcheck. Inspect the probe output next."
        ]
      },
      {
        "input": "Investigate why the api resource is not ready.",
        "output": [
          "The latest build failed before deployment completed.",
          "Recent logs point to a missing dependency during startup.",
          "Verify the dependency and trigger a rebuild after approval."
        ]
      },
      {
        "input": "Review this Tiltfile for faster local updates.",
        "output": [
          "Move rebuild triggers before sync steps in the live update list.",
          "Add labels to group backend and frontend resources.",
          "Keep manual trigger mode for expensive builds."
        ]
      }
    ],
    "best_practices": [
      "Check error states before broad pending status lists.",
      "Re-poll resources that are in progress before reporting success.",
      "Use structured Tilt output when you need reliable status decisions."
    ],
    "anti_patterns": [
      "Declaring a deployment healthy while resources are still pending or in progress.",
      "Restarting Tilt for normal code or Tiltfile changes.",
      "Ignoring Docker Compose healthStatus because runtimeStatus is ok."
    ],
    "faq": [
      {
        "question": "Does this skill run Tilt automatically?",
        "answer": "It provides command guidance. The assistant should ask before commands that change local resources."
      },
      {
        "question": "Can it work with non-default Tilt ports?",
        "answer": "Yes. It includes guidance for passing a custom port to Tilt commands."
      },
      {
        "question": "What tools are expected?",
        "answer": "Tilt is required. jq, rg, docker, kubectl, and zmx are useful for some workflows."
      },
      {
        "question": "Can it help edit Tiltfiles?",
        "answer": "Yes. It can guide edits for resources, live update, dependencies, configuration, and UI links."
      },
      {
        "question": "Does it cover Docker Compose?",
        "answer": "Yes. It highlights Docker Compose healthcheck signals that basic Tilt status can miss."
      },
      {
        "question": "Is it intended for production clusters?",
        "answer": "No. It is focused on local development. Review context and permissions before using shared clusters."
      }
    ]
  },
  "file_structure": [
    {
      "name": "CLI_REFERENCE.md",
      "type": "file",
      "path": "CLI_REFERENCE.md",
      "lines": 284
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 105
    },
    {
      "name": "TILTFILE_API.md",
      "type": "file",
      "path": "TILTFILE_API.md",
      "lines": 365
    }
  ]
}
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall