aiskillstore/marketplace / skills/2025emma/claude-skills
claude-skills
VerifiedClaude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.
| File | Kind | Size |
|---|---|---|
| AGENTS.md | markdown | 1.9 KB |
| SKILL.md | skill md | 7.9 KB |
| assets/template-complete.md | markdown | 2.4 KB |
| assets/template-minimal.md | markdown | 926 B |
| references/README.md | markdown | 7.5 KB |
| references/anti-patterns.md | markdown | 3.0 KB |
| references/index.md | markdown | 1.3 KB |
| references/quality-checklist.md | markdown | 1.9 KB |
| references/skill-spec.md | markdown | 3.4 KB |
| scripts/create-skill.sh | script | 4.1 KB |
| scripts/validate-skill.sh | script | 5.4 KB |
| skill-report.json | config | 35.2 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-18T09:21:35.791Z",
"slug": "2025emma-claude-skills",
"source_url": "https://github.com/2025Emma/vibe-coding-cn/tree/main/i18n/en/skills/claude-skills",
"source_ref": "main",
"model": "claude",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "f660d6a166c5231e5ec6bedb8797752ddcdb0ffe14137773ebe6ec92bdc3f6de",
"tree_hash": "c503699dabb6b7ab70eecb14a09a6577359d1b93adc432a9a9cdb69f4132c8f2",
"provenance": {
"model_effective": "claude",
"fallback_chain": [
{
"agent": "codex",
"outcome": "failed",
"error": "2026-07-18T09:21:35.930514Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-18T09:21:35.951000Z ERROR codex_models_manageβ¦"
},
{
"agent": "claude",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "Claude Skills Meta-Skill",
"description": "Build and improve reusable AI Skills from domain documentation, code, specifications, and examples.",
"summary": "Scaffold, structure, and validate reusable Skills with clear triggers and quality gates.",
"icon": "π¦",
"author": "2025Emma",
"license": "MIT",
"tags": [
"skill-authoring",
"documentation",
"validation",
"scaffolding",
"ai-workflows"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"filesystem"
],
"category": "documentation"
},
"security_audit": {
"risk_level": "low",
"is_blocked": false,
"safe_to_publish": false,
"analysis_status": "ok",
"summary": "The detected command substitutions are quoted shell utilities used by local scaffolding and validation scripts. Path references resolve bundled assets or local documentation, and manual review of SKILL.md found a benign translated-content prefix rather than harmful instructions. No evidence of network activity, credential collection, data exfiltration, or prompt injection was found.",
"remediation": [
{
"issue": "SKILL.md has text before its YAML frontmatter, so the bundled validator rejects it.",
"suggestion": "Move the translated-content label below the closing frontmatter delimiter or remove it so YAML frontmatter begins on line one.",
"severity": "low"
},
{
"issue": "The scaffolder accepts an arbitrary output directory and supports --force.",
"suggestion": "Document that users should choose a trusted output directory and review the target path before using --force.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "AGENTS.md",
"line_start": 17,
"line_end": 18
},
{
"file": "AGENTS.md",
"line_start": 23,
"line_end": 24
},
{
"file": "scripts/create-skill.sh",
"line_start": 120,
"line_end": 120
},
{
"file": "scripts/create-skill.sh",
"line_start": 121,
"line_end": 121
},
{
"file": "scripts/create-skill.sh",
"line_start": 122,
"line_end": 122
},
{
"file": "scripts/create-skill.sh",
"line_start": 123,
"line_end": 123
},
{
"file": "scripts/create-skill.sh",
"line_start": 128,
"line_end": 128
},
{
"file": "scripts/create-skill.sh",
"line_start": 83,
"line_end": 83
},
{
"file": "scripts/validate-skill.sh",
"line_start": 68,
"line_end": 68
},
{
"file": "scripts/validate-skill.sh",
"line_start": 73,
"line_end": 77
},
{
"file": "scripts/validate-skill.sh",
"line_start": 101,
"line_end": 103
},
{
"file": "scripts/validate-skill.sh",
"line_start": 112,
"line_end": 114
},
{
"file": "scripts/validate-skill.sh",
"line_start": 136,
"line_end": 136
},
{
"file": "scripts/validate-skill.sh",
"line_start": 172,
"line_end": 172
},
{
"file": "scripts/validate-skill.sh",
"line_start": 174,
"line_end": 174
},
{
"file": "scripts/validate-skill.sh",
"line_start": 175,
"line_end": 175
},
{
"file": "scripts/validate-skill.sh",
"line_start": 177,
"line_end": 177
},
{
"file": "scripts/validate-skill.sh",
"line_start": 179,
"line_end": 179
},
{
"file": "scripts/validate-skill.sh",
"line_start": 190,
"line_end": 190
},
{
"file": "scripts/validate-skill.sh",
"line_start": 192,
"line_end": 192
},
{
"file": "scripts/validate-skill.sh",
"line_start": 193,
"line_end": 193
},
{
"file": "scripts/validate-skill.sh",
"line_start": 195,
"line_end": 195
},
{
"file": "scripts/validate-skill.sh",
"line_start": 198,
"line_end": 200
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "references/index.md",
"line_start": 8,
"line_end": 8
},
{
"file": "scripts/create-skill.sh",
"line_start": 84,
"line_end": 84
},
{
"file": "scripts/validate-skill.sh",
"line_start": 136,
"line_end": 136
}
]
}
],
"static_findings": [
{
"id": "external_commands:AGENTS.md:17:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "AGENTS.md",
"line_start": 17,
"line_end": 18,
"snippet": "| `-- validate-skill.sh"
},
{
"id": "external_commands:AGENTS.md:23:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "AGENTS.md",
"line_start": 23,
"line_end": 24,
"snippet": "`-- skill-spec.md"
},
{
"id": "blocker:assets/template-complete.md:9:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "assets/template-complete.md",
"line_start": 9,
"line_end": 9,
"snippet": "Production-grade skill for [domain]: extract rules, patterns, and reproducible examples from source "
},
{
"id": "filesystem:references/index.md:8:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/index.md",
"line_start": 8,
"line_end": 8,
"snippet": "- [`../SKILL.md`](../SKILL.md): the meta-skill entrypoint (workflow, quality gate, tooling)"
},
{
"id": "blocker:references/README.md:83:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/README.md",
"line_start": 83,
"line_end": 83,
"snippet": "These example skills are all already available to paid plans in Claude.ai."
},
{
"id": "external_commands:scripts/create-skill.sh:120:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/create-skill.sh",
"line_start": 120,
"line_end": 120,
"snippet": "- Getting started: \\`getting_started.md\\`"
},
{
"id": "external_commands:scripts/create-skill.sh:121:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/create-skill.sh",
"line_start": 121,
"line_end": 121,
"snippet": "- API/CLI/config: \\`api.md\\` (if applicable)"
},
{
"id": "external_commands:scripts/create-skill.sh:122:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/create-skill.sh",
"line_start": 122,
"line_end": 122,
"snippet": "- Examples: \\`examples.md\\`"
},
{
"id": "external_commands:scripts/create-skill.sh:123:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/create-skill.sh",
"line_start": 123,
"line_end": 123,
"snippet": "- Troubleshooting: \\`troubleshooting.md\\`"
},
{
"id": "external_commands:scripts/create-skill.sh:128:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/create-skill.sh",
"line_start": 128,
"line_end": 128,
"snippet": "- Keep \\`SKILL.md\\` Quick Reference short and directly usable"
},
{
"id": "external_commands:scripts/create-skill.sh:83:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/create-skill.sh",
"line_start": 83,
"line_end": 83,
"snippet": "script_dir=\"$(cd -- \"$(dirname -- \"${BASH_SOURCE[0]}\")\" && pwd)\""
},
{
"id": "filesystem:scripts/create-skill.sh:84:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "scripts/create-skill.sh",
"line_start": 84,
"line_end": 84,
"snippet": "assets_dir=\"${script_dir}/../assets\""
},
{
"id": "external_commands:scripts/validate-skill.sh:68:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 68,
"line_end": 68,
"snippet": "base_name=\"$(basename -- \"${skill_dir%/}\")\""
},
{
"id": "external_commands:scripts/validate-skill.sh:73:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 73,
"line_end": 77,
"snippet": "if frontmatter=\"$("
},
{
"id": "external_commands:scripts/validate-skill.sh:101:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 101,
"line_end": 103,
"snippet": "name=\"$("
},
{
"id": "external_commands:scripts/validate-skill.sh:112:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 112,
"line_end": 114,
"snippet": "description=\"$("
},
{
"id": "external_commands:scripts/validate-skill.sh:136:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 136,
"line_end": 136,
"snippet": "filtered_md=\"$(mktemp)\""
},
{
"id": "external_commands:scripts/validate-skill.sh:172:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 172,
"line_end": 172,
"snippet": "quick_start=\"$(awk 'match($0, /^##[[:space:]]+Quick Reference([[:space:]]*)$/){print NR; exit}' \"$fi"
},
{
"id": "external_commands:scripts/validate-skill.sh:174:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 174,
"line_end": 174,
"snippet": "quick_end=\"$(awk -v s=\"$quick_start\" 'NR>s && match($0, /^##[[:space:]]+/){print NR; exit}' \"$filter"
},
{
"id": "external_commands:scripts/validate-skill.sh:175:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 175,
"line_end": 175,
"snippet": "total_lines=\"$(wc -l < \"$filtered_md\" | tr -d ' ')\""
},
{
"id": "external_commands:scripts/validate-skill.sh:177:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 177,
"line_end": 177,
"snippet": "quick_end=\"$((total_lines + 1))\""
},
{
"id": "external_commands:scripts/validate-skill.sh:179:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 179,
"line_end": 179,
"snippet": "quick_len=\"$((quick_end - quick_start - 1))\""
},
{
"id": "external_commands:scripts/validate-skill.sh:190:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 190,
"line_end": 190,
"snippet": "examples_start=\"$(awk 'match($0, /^##[[:space:]]+Examples([[:space:]]*)$/){print NR; exit}' \"$filter"
},
{
"id": "external_commands:scripts/validate-skill.sh:192:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 192,
"line_end": 192,
"snippet": "examples_end=\"$(awk -v s=\"$examples_start\" 'NR>s && match($0, /^##[[:space:]]+/){print NR; exit}' \"$"
},
{
"id": "external_commands:scripts/validate-skill.sh:193:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 193,
"line_end": 193,
"snippet": "total_lines=\"$(wc -l < \"$filtered_md\" | tr -d ' ')\""
},
{
"id": "external_commands:scripts/validate-skill.sh:195:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 195,
"line_end": 195,
"snippet": "examples_end=\"$((total_lines + 1))\""
},
{
"id": "external_commands:scripts/validate-skill.sh:198:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/validate-skill.sh",
"line_start": 198,
"line_end": 200,
"snippet": "example_count=\"$("
},
{
"id": "filesystem:scripts/validate-skill.sh:136:temp-file-creation",
"category": "filesystem",
"severity": "low",
"pattern": "Temp file creation",
"file": "scripts/validate-skill.sh",
"line_start": 136,
"line_end": 136,
"snippet": "filtered_md=\"$(mktemp)\""
},
{
"id": "blocker:scripts/validate-skill.sh:127:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/validate-skill.sh",
"line_start": 127,
"line_end": 127,
"snippet": "die \"Invalid name: '$name' (expected ^[a-z][a-z0-9-]*$)\""
},
{
"id": "metadata:SKILL.md:1:unscanned-file-invalid-frontmatter-manual-review",
"category": "metadata",
"severity": "low",
"pattern": "Unscanned file (invalid_frontmatter) β manual review required",
"file": "SKILL.md",
"line_start": 1,
"line_end": 1,
"snippet": "[unscanned: invalid_frontmatter]"
}
],
"finding_verdicts": [
{
"id": "external_commands:AGENTS.md:17:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks are Markdown formatting in a directory tree, not executable shell syntax. No command is invoked."
},
{
"id": "external_commands:AGENTS.md:23:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks are Markdown formatting for a filename in documentation, not shell execution."
},
{
"id": "blocker:assets/template-complete.md:9:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The template asks an author to extract domain rules from supplied source material. It does not inspect the host or collect system information."
},
{
"id": "filesystem:references/index.md:8:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The relative link navigates from a reference document to the bundled SKILL.md entrypoint. It is documentation, not a runtime filesystem operation."
},
{
"id": "blocker:references/README.md:83:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is informational text about plan availability. It performs no system reconnaissance."
},
{
"id": "external_commands:scripts/create-skill.sh:120:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks occur inside heredoc output as Markdown formatting for filenames. They are not evaluated by the shell."
},
{
"id": "external_commands:scripts/create-skill.sh:121:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks occur inside heredoc output as Markdown formatting for filenames. They are not evaluated by the shell."
},
{
"id": "external_commands:scripts/create-skill.sh:122:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks occur inside heredoc output as Markdown formatting for filenames. They are not evaluated by the shell."
},
{
"id": "external_commands:scripts/create-skill.sh:123:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks occur inside heredoc output as Markdown formatting for filenames. They are not evaluated by the shell."
},
{
"id": "external_commands:scripts/create-skill.sh:128:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks occur inside heredoc output as Markdown formatting for filenames. They are not evaluated by the shell."
},
{
"id": "external_commands:scripts/create-skill.sh:83:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The command substitution derives the script directory using quoted Bash variables and standard utilities. It does not execute user-provided commands."
},
{
"id": "filesystem:scripts/create-skill.sh:84:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The parent-directory reference resolves the script's bundled assets directory after deriving its own location. It is expected local resource lookup."
},
{
"id": "external_commands:scripts/validate-skill.sh:68:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "basename is called with a quoted local directory argument to obtain a directory name. This is normal validation logic."
},
{
"id": "external_commands:scripts/validate-skill.sh:73:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The command substitution runs a fixed awk program against the selected local SKILL.md file to parse frontmatter. No shell code from the file is executed."
},
{
"id": "external_commands:scripts/validate-skill.sh:101:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The command substitution uses a fixed awk parser on already-read frontmatter. It extracts text and does not execute it."
},
{
"id": "external_commands:scripts/validate-skill.sh:112:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The command substitution uses a fixed awk parser on already-read frontmatter. It extracts text and does not execute it."
},
{
"id": "external_commands:scripts/validate-skill.sh:136:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "mktemp is invoked without attacker-controlled template arguments to create a temporary validation file. The result is quoted in later uses."
},
{
"id": "external_commands:scripts/validate-skill.sh:172:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "A fixed awk expression locates a Markdown heading in a local temporary file. It does not execute document content."
},
{
"id": "external_commands:scripts/validate-skill.sh:174:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "A fixed awk expression calculates the next heading boundary using quoted local input. It is not command injection."
},
{
"id": "external_commands:scripts/validate-skill.sh:175:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "wc and tr calculate a local line count with the temporary filename quoted. This is ordinary validation logic."
},
{
"id": "external_commands:scripts/validate-skill.sh:177:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is Bash arithmetic expansion, not command execution, and uses a locally calculated line count."
},
{
"id": "external_commands:scripts/validate-skill.sh:179:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is Bash arithmetic expansion, not command execution, and operates on validator-derived values."
},
{
"id": "external_commands:scripts/validate-skill.sh:190:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "A fixed awk expression locates an Examples heading in a local temporary file. It does not execute document content."
},
{
"id": "external_commands:scripts/validate-skill.sh:192:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "A fixed awk expression finds a Markdown section boundary using quoted local input. It is not command injection."
},
{
"id": "external_commands:scripts/validate-skill.sh:193:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "wc and tr calculate a local line count with the temporary filename quoted. This is ordinary validation logic."
},
{
"id": "external_commands:scripts/validate-skill.sh:195:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is Bash arithmetic expansion, not command execution, and uses validator-derived values."
},
{
"id": "external_commands:scripts/validate-skill.sh:198:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "A fixed awk program counts Markdown example headings in a local temporary file. It does not run file contents as commands."
},
{
"id": "filesystem:scripts/validate-skill.sh:136:temp-file-creation",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "mktemp creates a private temporary file for stripped Markdown during validation, and the EXIT trap removes it."
},
{
"id": "blocker:scripts/validate-skill.sh:127:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The message reports a failed local name-format check. It neither collects nor exposes system information."
},
{
"id": "metadata:SKILL.md:1:unscanned-file-invalid-frontmatter-manual-review",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Manual review found a translated-content label before otherwise ordinary YAML frontmatter. This causes a validation defect but contains no malicious behavior."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [
{
"title": "Unscanned file (invalid_frontmatter) β manual review required",
"description": "[unscanned: invalid_frontmatter]",
"locations": [
{
"file": "SKILL.md",
"line_start": 1,
"line_end": 1
}
],
"review_kind": "security",
"source_category": "metadata",
"source_severity": "low",
"confidence": 1,
"confidence_reasoning": "Force-confirmed metadata/low static finding; AI false-positive verdict rejected."
}
],
"dangerous_patterns": [],
"files_scanned": 10,
"total_lines": 1011,
"audit_model": "claude",
"audited_at": "2026-07-18T09:21:35.791Z",
"agent_auto_install_policy": "confirmation_required",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Create and Improve Reusable AI Skills",
"value_statement": "Building a reliable Skill from scattered material is difficult and inconsistent. This meta-skill provides a repeatable structure, templates, and local checks for clear, maintainable Skills.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"AI Skills",
"skill authoring",
"SKILL.md",
"skill validation",
"documentation templates",
"prompt engineering",
"skill scaffolding"
],
"actual_capabilities": [
"Creates minimal or full Skill directory skeletons with SKILL.md, references, assets, and scripts folders.",
"Defines decidable activation triggers, boundaries, and required inputs for a Skill.",
"Moves long-form evidence into navigable reference documents.",
"Provides templates for reusable Skill documentation and examples.",
"Validates frontmatter, recommended sections, Quick Reference length, and example count.",
"Supports strict validation for the recommended directory and section layout."
],
"limitations": [
"Does not verify facts that are absent from the supplied source material.",
"Uses heuristic validation and may require adapted headings for nonstandard Skill layouts.",
"Does not replace domain expertise or review of generated content.",
"Creates local files and does not publish Skills to a marketplace."
],
"use_cases": [
{
"title": "Convert domain material into a Skill",
"description": "Turn documentation, specifications, and working examples into a structured reusable Skill.",
"target_user": "Technical writers and domain experts"
},
{
"title": "Refactor an existing Skill",
"description": "Separate long explanations from quick patterns and clarify activation boundaries.",
"target_user": "AI workflow maintainers"
},
{
"title": "Apply a release quality gate",
"description": "Check frontmatter, core sections, references, and examples before sharing a Skill.",
"target_user": "Platform engineers and reviewers"
}
],
"prompt_templates": [
{
"title": "Create a first Skill",
"scenario": "Beginner",
"prompt": "Create a reusable Skill from these notes. Include a clear name, activation triggers, boundaries, Quick Reference, three examples, and a reference index."
},
{
"title": "Organize supplied documentation",
"scenario": "Intermediate",
"prompt": "Use this documentation and these examples to design a Skill. Keep quick actions in SKILL.md and place detailed evidence in references/."
},
{
"title": "Improve an existing Skill",
"scenario": "Advanced",
"prompt": "Review this existing SKILL.md. Identify unclear triggers, missing boundaries, and documentation that should move to references. Return an improved structure and revision plan."
},
{
"title": "Run a strict quality review",
"scenario": "Advanced",
"prompt": "Evaluate this Skill against the recommended structure. Check frontmatter, triggers, boundaries, Quick Reference size, examples, and reference navigation. List concrete fixes by priority."
}
],
"output_examples": [
{
"input": "Create a Skill from an API guide and two code samples.",
"output": [
"A proposed Skill directory layout.",
"A SKILL.md outline with activation triggers and boundaries.",
"A reference plan for API details and troubleshooting."
]
},
{
"input": "Review a long Skill that activates inconsistently.",
"output": [
"A list of ambiguous triggers and missing constraints.",
"A shorter Quick Reference plan.",
"Suggested reference documents and validation checks."
]
}
],
"best_practices": [
"Use source material with verified examples before authoring a Skill.",
"State concrete trigger keywords and explicit boundaries in the frontmatter and body.",
"Run strict validation after restructuring a Skill and before distribution."
],
"anti_patterns": [
"Do not copy large documentation blocks into the Quick Reference.",
"Do not claim external facts without source evidence or a verification path.",
"Do not use vague descriptions such as \"helps with\" for activation rules."
],
"faq": [
{
"question": "What does this Skill create?",
"answer": "It helps create or improve a Skill with SKILL.md, references, templates, and optional validation scripts."
},
{
"question": "Who should use this Skill?",
"answer": "Use it when you maintain AI workflows or want to package domain knowledge into a reusable Skill."
},
{
"question": "Can it create a minimal Skill?",
"answer": "Yes. The included scaffolder supports minimal and full directory layouts."
},
{
"question": "What does strict validation check?",
"answer": "It checks frontmatter, the directory name, recommended sections, references, Quick Reference size, and example count."
},
{
"question": "Does it verify domain facts?",
"answer": "No. You must provide reliable source material, and uncertain claims need a verification path."
},
{
"question": "Does it publish a Skill?",
"answer": "No. It creates and validates local Skill content only."
}
]
},
"file_structure": [
{
"name": "AGENTS.md",
"type": "file",
"path": "AGENTS.md",
"lines": 43
},
{
"name": "assets",
"type": "dir",
"path": "assets",
"children": [
{
"name": "template-complete.md",
"type": "file",
"path": "assets/template-complete.md",
"lines": 90
},
{
"name": "template-minimal.md",
"type": "file",
"path": "assets/template-minimal.md",
"lines": 52
}
]
},
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "anti-patterns.md",
"type": "file",
"path": "references/anti-patterns.md",
"lines": 112
},
{
"name": "index.md",
"type": "file",
"path": "references/index.md",
"lines": 28
},
{
"name": "quality-checklist.md",
"type": "file",
"path": "references/quality-checklist.md",
"lines": 51
},
{
"name": "README.md",
"type": "file",
"path": "references/README.md",
"lines": 125
},
{
"name": "skill-spec.md",
"type": "file",
"path": "references/skill-spec.md",
"lines": 113
}
]
},
{
"name": "scripts",
"type": "dir",
"path": "scripts",
"children": [
{
"name": "create-skill.sh",
"type": "file",
"path": "scripts/create-skill.sh",
"lines": 183
},
{
"name": "validate-skill.sh",
"type": "file",
"path": "scripts/validate-skill.sh",
"lines": 214
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 245
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product β 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 β 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 β a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK β model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER β read BEFORE opening the target file; don't skip because it "looks like a one-liner" β 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) β 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 β don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |