Skip to content

aiskillstore/marketplace / skills/0xrdan/learn-on

learn-on

Verified

Enable continuous learning mode for automatic insight extraction

FileKindSize
SKILL.mdskill md1.6 KB
skill-report.jsonconfig13.5 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T14:06:44.801Z",
    "slug": "0xrdan-learn-on",
    "source_url": "https://github.com/0xrdan/claude-router/tree/main/.claude-plugin/skills/learn-on",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "d995869eed0afccd04fe78de1d28b992d6800c51632b19cab2c9490e5f647d4b",
    "tree_hash": "ed2a0e30385e01a6023459eabb4f3b27cf2aff46105a237c11c8045bcaf7bf5f",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "learn-on",
    "description": "Enable continuous learning mode so session insights are captured automatically.",
    "summary": "Turns on automatic learning capture for long AI sessions.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "0xrdan",
    "license": "MIT",
    "category": "productivity",
    "tags": [
      "continuous-learning",
      "knowledge-base",
      "session-insights",
      "workflow-automation"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All eight static findings are false positives caused by Markdown code formatting and slash-command references in SKILL.md. No prompt injection, data exfiltration intent, or executable command behavior was found in the reviewed file.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 18
          },
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 22
          },
          {
            "file": "SKILL.md",
            "line_start": 24,
            "line_end": 30
          },
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 31
          },
          {
            "file": "SKILL.md",
            "line_start": 31,
            "line_end": 36
          },
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 51
          },
          {
            "file": "SKILL.md",
            "line_start": 51,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 58
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "This is useful for long sessions where you want to capture insights as you go without remembering to"
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 22,
        "line_end": 22,
        "snippet": "1. Read `knowledge/state.json`"
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 24,
        "line_end": 30,
        "snippet": "```json"
      },
      {
        "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": 31,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 31,
        "line_end": 36,
        "snippet": "3. Write updated state back to `knowledge/state.json`"
      },
      {
        "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": 51,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 51,
        "line_end": 57,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 58,
        "snippet": "- You can still run `/learn` manually while continuous mode is active"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 18 references the /learn slash command in prose. It does not contain shell execution, Ruby backticks, or user-controlled command construction."
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 22 uses Markdown inline code for the knowledge/state.json path. It describes a file to read and does not invoke an external command."
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 24 starts a fenced JSON example. The backticks are Markdown syntax and there is no executable shell or Ruby code."
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 30 closes a fenced JSON example. This is Markdown formatting only and has no command execution behavior."
      },
      {
        "id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 31 uses Markdown inline code for the knowledge/state.json path. It instructs a state-file update, not an external command execution."
      },
      {
        "id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 36 opens a fenced output-format block. The backticks are documentation formatting and do not execute code."
      },
      {
        "id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 51 closes a fenced output-format block. This is not a shell command or Ruby backtick expression."
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 57 references the /learn slash command in a note. It is user-facing documentation and does not execute an external process."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 59,
    "audit_model": "codex",
    "audited_at": "2026-07-04T14:06:44.801Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Enable Continuous Learning for Session Insights",
    "value_statement": "Long AI sessions can lose useful decisions and patterns. This skill turns on automatic insight capture into a local knowledge base.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "continuous learning",
      "knowledge base",
      "session insights",
      "automatic extraction",
      "learning mode",
      "AI workflow",
      "router automation"
    ],
    "actual_capabilities": [
      "Guides the assistant to read knowledge/state.json before changing learning state.",
      "Sets learning_mode to true and stores the current activation timestamp.",
      "Resets the query counter used for automatic extraction thresholds.",
      "Documents automatic extraction after 10 queries or 30 minutes of activity.",
      "Shows users where extracted patterns, quirks, and decisions will be saved."
    ],
    "limitations": [
      "Requires a router or workflow that reads knowledge/state.json.",
      "Does not extract insights by itself when the router is absent.",
      "Learning mode is documented as session scoped and resets on new sessions.",
      "Depends on related commands for manual extraction, status, and disabling."
    ],
    "use_cases": [
      {
        "title": "Capture Long Debugging Sessions",
        "description": "Enable automatic learning while investigating repeated bugs and implementation decisions.",
        "target_user": "Software developers"
      },
      {
        "title": "Maintain Project Working Memory",
        "description": "Record patterns and preferences during extended collaboration with an AI assistant.",
        "target_user": "Technical leads"
      },
      {
        "title": "Build Workflow Notes",
        "description": "Keep operational quirks and decisions available for future sessions.",
        "target_user": "AI workflow operators"
      }
    ],
    "prompt_templates": [
      {
        "title": "Turn On Learning",
        "prompt": "Enable continuous learning for this session and confirm when it is active.",
        "scenario": "Beginner setup"
      },
      {
        "title": "Start Capture Before Work",
        "prompt": "Turn on continuous learning before we start this debugging session. Track useful patterns and decisions for later review.",
        "scenario": "Routine project work"
      },
      {
        "title": "Prepare for Extended Collaboration",
        "prompt": "Enable continuous learning and reset the query counter. Confirm the extraction thresholds and destination files.",
        "scenario": "Long collaborative session"
      },
      {
        "title": "Coordinate Learning Workflow",
        "prompt": "Enable continuous learning, verify the state file update, and explain how manual extraction and disabling should be handled.",
        "scenario": "Advanced workflow control"
      }
    ],
    "output_examples": [
      {
        "input": "Enable continuous learning for this session.",
        "output": "Continuous learning is enabled. Automatic extraction will run after the configured query or time threshold."
      },
      {
        "input": "Turn on learning before we continue the architecture review.",
        "output": "Learning mode is active. Future patterns, quirks, and decisions will be saved to the knowledge files."
      },
      {
        "input": "Start automatic insight capture and tell me how to stop it later.",
        "output": "Continuous learning is enabled. Use the matching off command to disable it, or run manual learning when needed."
      }
    ],
    "best_practices": [
      "Enable the skill before long sessions where decisions may accumulate.",
      "Review saved learning files after important milestones.",
      "Use manual extraction when a major insight should be captured immediately."
    ],
    "anti_patterns": [
      "Do not expect learning capture without the router state workflow.",
      "Do not leave learning mode on when session notes should stay temporary.",
      "Do not use this as a replacement for deliberate documentation reviews."
    ],
    "faq": [
      {
        "question": "What does this skill enable?",
        "answer": "It enables continuous learning mode for automatic insight extraction during a session."
      },
      {
        "question": "Where does it store learning state?",
        "answer": "The instructions use knowledge/state.json to store learning mode, timestamp, and query count."
      },
      {
        "question": "When does extraction run?",
        "answer": "The documented threshold is every 10 queries or every 30 minutes of activity."
      },
      {
        "question": "Does this skill perform extraction itself?",
        "answer": "No. It enables the state that a compatible router uses to trigger extraction."
      },
      {
        "question": "Can users still run manual learning?",
        "answer": "Yes. The skill notes that manual learning can still run while continuous mode is active."
      },
      {
        "question": "Is this suitable for Claude Code and Codex?",
        "answer": "Yes. The report marks support for Claude, Claude Code, and Codex workflows."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 59
    }
  ]
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall