Skip to content

aiskillstore/marketplace / skills/2389-research/binary-re-synthesis

binary-re-synthesis

Verified

Use when ready to document findings, generate a report, or summarize binary analysis results. Compiles analysis findings into structured reports - correlates facts from triage/static/dynamic phases, validates hypotheses, generates documentation with evidence chains. Keywords - "summarize findings", "generate report", "document analysis", "what did we find", "write up results", "export findings"

FileKindSize
SKILL.mdskill md9.6 KB
skill-report.jsonconfig26.8 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-09T01:43:28.941Z",
    "slug": "2389-research-binary-re-synthesis",
    "source_url": "https://github.com/2389-research/claude-plugins/tree/main/binary-re/skills/synthesis",
    "source_ref": "main",
    "model": "claude",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "1aad2334bf0c8b47621156dd7e33cfbfac7e822bed8dcefdfffa95d1ee5decf2",
    "tree_hash": "60047e682e2dd81a8e518fcd672e41e1ee5abf6ee714609a85179982bed9ec0f",
    "provenance": {
      "model_requested": "claude-sonnet-4.6",
      "model_effective": "claude:claude-sonnet-4.6",
      "fallback_chain": [
        {
          "agent": "claude",
          "model": "claude-sonnet-4.6",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "binary-re-synthesis",
    "description": "Compiles binary reverse engineering findings into evidence-based reports with validated hypotheses, capability maps, and recommendations.",
    "summary": "Turn binary analysis evidence into structured, traceable reverse engineering reports.",
    "icon": "📦",
    "version": "1.0.0",
    "author": "2389-research",
    "license": "MIT",
    "tags": [
      "binary-analysis",
      "reverse-engineering",
      "reporting",
      "malware-analysis",
      "security-research"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ],
    "category": "security"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All static findings were adjudicated as false positives. The skill is a markdown-based reporting guide for binary reverse engineering and does not contain executable commands, live network activity, weak cryptography, log deletion, or prompt injection evidence.",
    "remediation": [
      {
        "issue": "Static scanners may misread fenced report examples as executable commands.",
        "suggestion": "Label example blocks as text or markdown where possible, and avoid language markers that imply runnable shell or Ruby code.",
        "severity": "low"
      },
      {
        "issue": "Example indicators include an internal IP address and log path that can look like active behavior.",
        "suggestion": "Clarify that network destinations, file paths, and security findings are illustrative evidence from analyzed binaries.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 25,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 64
          },
          {
            "file": "SKILL.md",
            "line_start": 64,
            "line_end": 70
          },
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 87
          },
          {
            "file": "SKILL.md",
            "line_start": 87,
            "line_end": 93
          },
          {
            "file": "SKILL.md",
            "line_start": 93,
            "line_end": 112
          },
          {
            "file": "SKILL.md",
            "line_start": 112,
            "line_end": 116
          },
          {
            "file": "SKILL.md",
            "line_start": 116,
            "line_end": 220
          },
          {
            "file": "SKILL.md",
            "line_start": 220,
            "line_end": 248
          },
          {
            "file": "SKILL.md",
            "line_start": 248,
            "line_end": 280
          },
          {
            "file": "SKILL.md",
            "line_start": 280,
            "line_end": 284
          },
          {
            "file": "SKILL.md",
            "line_start": 284,
            "line_end": 323
          },
          {
            "file": "SKILL.md",
            "line_start": 323,
            "line_end": 329
          },
          {
            "file": "SKILL.md",
            "line_start": 329,
            "line_end": 345
          },
          {
            "file": "SKILL.md",
            "line_start": 345,
            "line_end": 355
          },
          {
            "file": "SKILL.md",
            "line_start": 355,
            "line_end": 365
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 58
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 25,
        "line_end": 39,
        "snippet": "```"
      },
      {
        "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": 56,
        "snippet": "```"
      },
      {
        "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": 64,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 64,
        "line_end": 70,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 87,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 87,
        "line_end": 93,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 93,
        "line_end": 112,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 112,
        "line_end": 116,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 116,
        "line_end": 220,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:220:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 220,
        "line_end": 248,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:248:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 248,
        "line_end": 280,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:280:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 280,
        "line_end": 284,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:284:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 284,
        "line_end": 323,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:323:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 323,
        "line_end": 329,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:329:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 329,
        "line_end": 345,
        "snippet": "```json"
      },
      {
        "id": "external_commands:SKILL.md:345:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 345,
        "line_end": 355,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:355:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 355,
        "line_end": 365,
        "snippet": "```json"
      },
      {
        "id": "network:SKILL.md:58:hardcoded-ip-address",
        "category": "network",
        "severity": "medium",
        "pattern": "Hardcoded IP address",
        "file": "SKILL.md",
        "line_start": 58,
        "line_end": 58,
        "snippet": "Dynamic finding: connect() to 192.168.1.100:8443 observed"
      },
      {
        "id": "blocker:SKILL.md:85:weak-cryptographic-algorithm",
        "category": "blocker",
        "severity": "high",
        "pattern": "Weak cryptographic algorithm",
        "file": "SKILL.md",
        "line_start": 85,
        "line_end": 85,
        "snippet": "- [ ] Symmetric encryption (no AES/DES imports)"
      },
      {
        "id": "blocker:SKILL.md:304:log-file-deletion",
        "category": "blocker",
        "severity": "critical",
        "pattern": "Log file deletion",
        "file": "SKILL.md",
        "line_start": 304,
        "line_end": 304,
        "snippet": "- Logging: writes to /var/log/thermostat.log"
      },
      {
        "id": "blocker:SKILL.md:3:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 3,
        "line_end": 3,
        "snippet": "description: Use when ready to document findings, generate a report, or summarize binary analysis re"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:220:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:248:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:280:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:284:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:323:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:329:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:345:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "external_commands:SKILL.md:355:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "This finding points to markdown code fences and report templates in SKILL.md, not Ruby backtick execution or executable shell code. The skill provides documentation examples for analysts and does not instruct the agent to run these blocks as commands."
      },
      {
        "id": "network:SKILL.md:58:hardcoded-ip-address",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The hardcoded IP appears inside an example correlation statement for a dynamic analysis report. It documents observed sample behavior and does not make a network connection."
      },
      {
        "id": "blocker:SKILL.md:85:weak-cryptographic-algorithm",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The line is a checklist item saying no AES, DES, SHA, or MD5 imports were found in an analyzed binary. It does not recommend weak cryptography or implement any cryptographic algorithm."
      },
      {
        "id": "blocker:SKILL.md:304:log-file-deletion",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The line describes a sample binary writing to a log file. It does not delete logs, clear audit trails, or instruct the agent to remove evidence."
      },
      {
        "id": "blocker:SKILL.md:3:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The description states the skill summarizes binary analysis results. That is normal defensive reverse engineering documentation, not host reconnaissance or data collection."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 374,
    "audit_model": "claude",
    "audited_at": "2026-07-09T01:43:28.941Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Document Binary Analysis Findings",
    "value_statement": "Binary analysis often produces scattered facts that are hard to share. This skill helps Claude, Codex, and Claude Code turn evidence into clear reports with confidence levels and next steps.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "binary reverse engineering",
      "binary analysis report",
      "malware analysis documentation",
      "evidence synthesis",
      "capability mapping",
      "hypothesis validation",
      "security research workflow"
    ],
    "actual_capabilities": [
      "Reviews facts from triage, static analysis, and dynamic analysis phases.",
      "Classifies hypotheses as confirmed, refuted, uncertain, or unvalidated.",
      "Maps observed binary capabilities across network, file system, and cryptography areas.",
      "Generates structured markdown reports with evidence logs and recommendations.",
      "Creates final knowledge journal entries for completed binary analysis sessions.",
      "Formats findings for human readers, databases, or threat intelligence workflows."
    ],
    "limitations": [
      "Requires prior analysis facts; it does not perform triage, disassembly, or dynamic testing by itself.",
      "Report quality depends on the accuracy and completeness of supplied evidence.",
      "Cannot prove behavior that was not observed or supported by prior findings.",
      "Threat intelligence formats still need analyst review before external sharing."
    ],
    "use_cases": [
      {
        "title": "Prepare a handoff report",
        "description": "Summarize reverse engineering results for another analyst or incident response team.",
        "target_user": "Security analyst"
      },
      {
        "title": "Validate malware hypotheses",
        "description": "Compare evidence from static and dynamic analysis before declaring binary behavior.",
        "target_user": "Malware researcher"
      },
      {
        "title": "Archive completed research",
        "description": "Create a durable record of conclusions, evidence, unknowns, and recommended follow-up work.",
        "target_user": "Research lead"
      }
    ],
    "prompt_templates": [
      {
        "title": "Summarize my findings",
        "scenario": "Beginner report creation after collecting notes.",
        "prompt": "Use the binary-re-synthesis skill to summarize my current binary analysis notes into an executive summary, confirmed capabilities, and open questions."
      },
      {
        "title": "Validate hypotheses against evidence",
        "scenario": "Intermediate review before writing conclusions.",
        "prompt": "Use the binary-re-synthesis skill to review each hypothesis, mark it confirmed, refuted, uncertain, or unvalidated, and cite the supporting evidence."
      },
      {
        "title": "Create a stakeholder report",
        "scenario": "Advanced reporting for incident response or management.",
        "prompt": "Use the binary-re-synthesis skill to produce a stakeholder-ready report with artifact details, behavioral summary, evidence log, risk findings, and recommendations."
      },
      {
        "title": "Prepare threat intelligence output",
        "scenario": "Advanced synthesis for shareable intelligence.",
        "prompt": "Use the binary-re-synthesis skill to convert confirmed malicious behavior into threat intelligence language, including capabilities, confidence, evidence, and remaining unknowns."
      }
    ],
    "output_examples": [
      {
        "input": "Notes include a network function, TLS imports, a telemetry string, and one observed outbound connection.",
        "output": "A concise report states that the binary is likely a telemetry client, explains the confidence level, lists supporting evidence, and recommends payload review."
      },
      {
        "input": "The analyst has three hypotheses, with mixed evidence for persistence and strong evidence for configuration parsing.",
        "output": "A hypothesis table separates confirmed, refuted, and uncertain claims, then lists the exact evidence needed to close remaining gaps."
      },
      {
        "input": "A completed malware analysis needs archival documentation for future investigations.",
        "output": "A final journal entry records the artifact identity, confirmed capabilities, security findings, unresolved questions, and evidence index."
      }
    ],
    "best_practices": [
      "Run this skill after collecting evidence from triage, static analysis, and dynamic analysis.",
      "Keep every conclusion tied to a specific observation, function, string, trace, or tool result.",
      "Separate confirmed behavior from speculation and unresolved questions."
    ],
    "anti_patterns": [
      "Do not use the skill to invent findings when evidence is missing.",
      "Do not present potential capabilities as confirmed behavior.",
      "Do not share threat intelligence output externally without human review."
    ],
    "faq": [
      {
        "question": "Does this skill analyze binaries directly?",
        "answer": "No. It synthesizes evidence that was already collected by triage, static analysis, and dynamic analysis work."
      },
      {
        "question": "Can it produce reports for malware analysis?",
        "answer": "Yes. It can organize malware analysis findings, evidence, confidence levels, and recommended follow-up actions."
      },
      {
        "question": "What inputs work best?",
        "answer": "Provide artifact metadata, hypotheses, function notes, strings, dynamic observations, tool outputs, and unresolved questions."
      },
      {
        "question": "Does it support non-malicious firmware or application binaries?",
        "answer": "Yes. The templates cover general binary capabilities, file access, network behavior, configuration parsing, and reporting."
      },
      {
        "question": "How does it handle uncertainty?",
        "answer": "It labels hypotheses as confirmed, refuted, uncertain, or unvalidated, and asks for more evidence where needed."
      },
      {
        "question": "Can it create machine-readable summaries?",
        "answer": "Yes. The skill describes structured output options for tools, databases, and threat intelligence workflows."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 374
    }
  ]
}
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall