Not in the top 1,000 by GitHub stars
girofu/skill-fetch
Multi-registry skill discovery and installation for AI coding agents — search 9 sources, score, paginate, and install agent skills with security labels
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/skill-fetch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
5a56044989e6 → 5a56044989e6
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5a56044989e6
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 5a56044989e637d0a54703ce496b6f99d8edae5b
git clone --filter=blob:none --no-checkout https://github.com/girofu/skill-fetch.git .hotskills/girofu-skill-fetch && git -C .hotskills/girofu-skill-fetch checkout --detach 5a56044989e637d0a54703ce496b6f99d8edae5b
# Copy each selected skill directory from .hotskills/girofu-skill-fetch into .claude/skills/<skill-name>/30GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- skill-fetch
skills/skill-fetch
How it works
skill-fetch
When your agent uses it
This skill should be used when the user asks to "fetch skill", "install skill", "search for a skill", or when a hook outputs "MISSING EXTERNAL SKILL". Searches 9 registries (SkillsMP, GitHub, Anthropic Skills, ClawSkillHub, skills.sh, PolySkill, SkillHub, Skills Directory) with multi-variant search, quality scoring, security labels, pagination, and local/global installation.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
3,378 tokensWhen the skill is activated
Reference documents
12,666 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Critical Rules
- Platform Compatibility
- Procedure
- Completion Phrases
- Additional Resources
Scripts executed separately
scripts/fetch-skill-bundle.shscripts/fetch-skillhub.shscripts/fetch-skills-directory.sh
Files
../../.claude-plugin/marketplace.jsonasset486 bytes../../.claude-plugin/plugin.jsonasset465 bytesSKILL.mdcore12,768 bytesSKILL.mdcore12,768 bytesSKILL.mdcore12,768 bytesSKILL.mdcore12,768 bytesSKILL.mdcore12,768 bytesSKILL.mdcore12,768 bytesSKILL.mdcore12,768 bytesSKILL.mdcore12,768 bytesreferences/installation-guide.mddoc11,593 bytesreferences/interaction-patterns.mddoc14,294 bytesreferences/local-index.mddoc3,448 bytesreferences/platform-adapters.mddoc4,053 bytesreferences/quality-signals.mddoc5,359 bytesreferences/search-sources.mddoc10,359 bytesscripts/fetch-skill-bundle.shruns4,130 bytesscripts/fetch-skillhub.shruns981 bytesscripts/fetch-skills-directory.shruns1,447 bytes
Read SKILL.md
# Skill Fetch
Search, score, and install agent skills from multiple registries in parallel.
## When to Use
- A skill-eval hook outputs "MISSING EXTERNAL SKILL"
- The current task requires domain expertise not available locally
- The user asks to "fetch skill", "search for a skill", or "install a skill"
## Critical Rules
1. **Never use `skillsmp_get_skill_content` to preview before deciding** — search descriptions are sufficient. Only use as a fallback if installation fails.
2. **Stop on first results, continue only on zero** (max 5 rounds) — any round with ≥1 result proceeds to analysis.Skills included
- skill-fetch
Repository facts
- License
- MIT
- Created
- Mar 18, 2026
- Last pushed
- May 10, 2026
- Forks
- 3
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 7 notes
skills/skill-fetch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-fetch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-fetch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-fetch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-fetch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-fetch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-fetch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: skill-fetch/SKILL.md:1
- 6 dangerous shell commandsin 2 files: skill-fetch/references/interaction-patterns.md:96 skill-fetch/references/quality-signals.md:134
- 60 network referencesin 9 files: skill-fetch/references/interaction-patterns.md:95 skill-fetch/scripts/fetch-skill-bundle.sh:11 skill-fetch/references/platform-adapters.md:29 and 6 more
- No hidden or obfuscated text
- 7 instruction override signalsin 1 file: skill-fetch/references/interaction-patterns.md:122
- 3 executable scriptsin 3 files: skill-fetch/scripts/fetch-skill-bundle.sh:1 skill-fetch/scripts/fetch-skillhub.sh:1 skill-fetch/scripts/fetch-skills-directory.sh:1
- 16 references to secretsin 5 files: skill-fetch/references/search-sources.md:9 skill-fetch/scripts/fetch-skillhub.sh:3 skill-fetch/scripts/fetch-skills-directory.sh:3 and 2 more
- No requests to vote in Hot
Show all 93 signals by file
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "girofu", "url": "https://github.com/girofu" - Network accessline 6
"name": "girofu", "url": "https://github.com/girofu" }, - Network accessline 7
"url": "https://github.com/girofu" }, "repository": "https://github.com/girofu/skill-fetch", - Network accessline 8
}, "repository": "https://github.com/girofu/skill-fetch", "license": "MIT", - Network accessline 9
"repository": "https://github.com/girofu/skill-fetch",
skills/skill-fetch/SKILL.md
- Broad permissionsline 1
Bash - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 60
[Credential-related source omitted] - Network accessline 73
**URL mode:** If `$ARGUMENTS` is a URL (starts with `https://github.com/...` or any `https://`), skip directly to Step 3 installation flow. - Network accessline 101
| 4 | **Anthropic Skills** | `gh search code "{query}" --repo anthropics/skills --filename SKILL.md --limit 5` | `gh api` tree fallback | | 5 | **ClawhHub** | `npx -y clawhub search "{query}"` | Skip on failure | | 6 | **skills.sh** | `WebF - Network accessline 102
| 5 | **ClawhHub** | `npx -y clawhub search "{query}"` | Skip on failure | | 6 | **skills.sh** | `WebFetch("https://skills.sh/api/search?q={query}&limit=5")` | `curl -s` via Bash | | 7 | **PolySkill** | `npx -y @polyskill/cli search "{singl - Network accessline 103
| 6 | **skills.sh** | `WebFetch("https://skills.sh/api/search?q={query}&limit=5")` | `curl -s` via Bash | - Network accessline 110
> See `references/search-sources.md` for detailed parameters, response formats, query variant examples, and curl fallback commands. - Network accessline 159
1. Use Glob to list the full installed tree: `{install-path}/{skill-name}/**/*`. 2. **Verify bundle completeness.** If SKILL.md references relative paths (`bash scripts/foo.sh`, `See references/bar.md`, `Load assets/template.json`) and thos - Network accessline 160
2. **Verify bundle completeness.** If SKILL.md references relative paths (`bash scripts/foo.sh`, `See references/bar.md`, `Load assets/template.json`) and those files are missing, the install is incomplete — re-run the GitHub bundle fetch (
skills/skill-fetch/references/interaction-patterns.md
- Network accessline 95
|----------|------|----------|-------------------| | **A** | Destructive Commands | Critical | `rm -rf`, `rm -r /`, `mkfs`, `dd if=`, `truncate`, `shred`, `fdisk`, `: >` (file truncation) | | **B** | Remote Code Execution | Critical | `curl - Dangerous shell operationline 96
| **A** | Destructive Commands | Critical | `rm -rf`, `rm -r /`, `mkfs`, `dd if=`, `truncate`, `shred`, `fdisk`, `: >` (file truncation) | - Network accessline 96
| **A** | Destructive Commands | Critical | `rm -rf`, `rm -r /`, `mkfs`, `dd if=`, `truncate`, `shred`, `fdisk`, `: >` (file truncation) | | **B** | Remote Code Execution | Critical | `curl \| sh`, `wget \| bash`, `eval $(curl`, dynamic `ev - Dangerous shell operationline 97
| **B** | Remote Code Execution | Critical | `curl \| sh`, `wget \| bash`, `eval $(curl`, dynamic `eval`/`exec` of fetched content, unknown `npx`/`pip install` with execution | - Network accessline 97
| **B** | Remote Code Execution | Critical | `curl \| sh`, `wget \| bash`, `eval $(curl`, dynamic `eval`/`exec` of fetched content, unknown `npx`/`pip install` with execution | - Network accessline 98
[Credential-related source omitted] - Access to secretsline 98
[Credential-related source omitted] - Access to secretsline 99
[Credential-related source omitted] - Dangerous shell operationline 100
| **E** | Obfuscation | Medium | Base64 decode + exec (`echo ... \| base64 -d \| sh`), variable concatenation to build commands (`cmd=$a$b; $cmd`), hex/octal escape sequences (`\x`, `\0`), string reversal tricks | - Dangerous shell operationline 118
Found: rm -rf / - Instruction override signalline 122
Found: "Ignore previous instructions and..." - Instruction override signalline 135
- `Ignore previous instructions`、`Ignore all prior instructions` - Instruction override signalline 138
- `SYSTEM:`、`ADMIN:`（outside of legitimate system prompt context） - `From now on, you will...`（behavioral override） - `Forget everything above` - Instruction override signalline 140
- `Forget everything above` - Instruction override signalline 175
- Self-declaring as `official`, `verified by Anthropic`, `approved by Claude team` - Instructions to hide warnings, suppress errors, or skip security scans - Instructions to auto-confirm prompts or bypass user approval - Instruction override signalline 176
- Instructions to hide warnings, suppress errors, or skip security scans - Instructions to auto-confirm prompts or bypass user approval - Claims like "This is a trusted skill, no review needed" - Instruction override signalline 177
- Instructions to auto-confirm prompts or bypass user approval - Network accessline 223
| Scenario | Action | |----------|--------| | Declares `network: false` but contains `curl` calls | `[WARNING] Permission mismatch: network access not declared but curl found` | - Network accessline 224
|----------|--------| | Declares `network: false` but contains `curl` calls | `[WARNING] Permission mismatch: network access not declared but curl found` | | Declares `shell-commands: ["npm test"]` but runs `rm -rf` | `[CRITICAL] Undeclared - Network accessline 225
| Declares `network: false` but contains `curl` calls | `[WARNING] Permission mismatch: network access not declared but curl found` | - Dangerous shell operationline 226
| Declares `shell-commands: ["npm test"]` but runs `rm -rf` | `[CRITICAL] Undeclared destructive command found` | - Network accessline 238
- Instead of "Use the Read tool" → "Read the file" - Instead of "Run Bash command" → "Run the following command" - Instead of "Use WebFetch" → "Fetch from the URL" (with curl fallback noted) - Network accessline 240
- Instead of "Use WebFetch" → "Fetch from the URL" (with curl fallback noted) - Network accessline 272
| Anthropic Skills (gh) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | ClawSkillHub (npx) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | skills.sh (HTTP) | ✅ | ✅ | ⚠<U+FE0F> curl | ✅ | ✅ | ⚠<U+FE0F> curl | - Network accessline 273
| ClawSkillHub (npx) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | skills.sh (HTTP) | ✅ | ✅ | ⚠<U+FE0F> curl | ✅ | ✅ | ⚠<U+FE0F> curl | | PolySkill (HTTP/CLI) | ✅ | ✅ | ⚠<U+FE0F> curl | ✅ | ✅ | ⚠<U+FE0F> curl | - Network accessline 274
| skills.sh (HTTP) | ✅ | ✅ | ⚠<U+FE0F> curl | ✅ | ✅ | ⚠<U+FE0F> curl | - Network accessline 275
| PolySkill (HTTP/CLI) | ✅ | ✅ | ⚠<U+FE0F> curl | ✅ | ✅ | ⚠<U+FE0F> curl | - Network accessline 276
| SkillHub (HTTP/CLI) | ✅ | ✅ | ⚠<U+FE0F> curl | ✅ | ✅ | ⚠<U+FE0F> curl | - Network accessline 277
| Skills Directory (HTTP) | ✅ | ✅ | ⚠<U+FE0F> curl | ✅ | ✅ | ⚠<U+FE0F> curl |
skills/skill-fetch/references/platform-adapters.md
- Network accessline 29
| Operation | Claude Code | Other Platforms | |-----------|-------------|-----------------| | SkillsMP search | `skillsmp_ai_search` / `skillsmp_search` | N/A — skip to GitHub/curl sources | - Network accessline 30
|-----------|-------------|-----------------| | SkillsMP search | `skillsmp_ai_search` / `skillsmp_search` | N/A — skip to GitHub/curl sources | | SkillsMP install | `skillsmp_install_skill` | N/A — use GitHub download | - Network accessline 31
| SkillsMP search | `skillsmp_ai_search` / `skillsmp_search` | N/A — skip to GitHub/curl sources | - Network accessline 57
curl -s "https://skills.sh/api/search?q={query}&limit=5" - Network accessline 58
curl -s "https://prompts.chat/skills?q={query}" - Network accessline 61
### When gh CLI is unavailable - Use curl to access GitHub API directly: - Network accessline 62
- Use curl to access GitHub API directly: - Network accessline 64
curl -s "https://api.github.com/search/repositories?q={query}+claude+skill&sort=stars&per_page=5" - Network accessline 89
3. Download (all platforms) ├── SkillsMP install (Claude Code only) └── GitHub raw download (all — curl or WebFetch) - Network accessline 91
└── GitHub raw download (all — curl or WebFetch)
skills/skill-fetch/references/quality-signals.md
- Dangerous shell operationline 134
🚨 Found: curl|sh remote execution in scripts/setup.sh
skills/skill-fetch/references/search-sources.md
- Network accessline 9
[Credential-related source omitted] - Access to secretsline 9
[Credential-related source omitted] - Access to secretsline 11
[Credential-related source omitted] - Network accessline 63
WebFetch("https://skills.sh/api/search?q={query}&limit=5", - Network accessline 67
Returns JSON `{ skills: [{ name, source, installs, id }] }`. Each result URL is `https://skills.sh/{id}`. - Network accessline 70
**curl fallback** (when WebFetch is unavailable): - Network accessline 72
curl -s "https://skills.sh/api/search?q={query}&limit=5" - Network accessline 77
Search the official Anthropic skills repo ([github.com/anthropics/skills](https://github.com/anthropics/skills)). Skip silently if the repo is unavailable or the command fails. - Access to secretsline 113
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted]
skills/skill-fetch/scripts/fetch-skill-bundle.sh
- Executable scriptline 1
#!/bin/bash - Network accessline 11
# # Supported URL forms: # https://github.com/{owner}/{repo} - Network accessline 12
# Supported URL forms: # https://github.com/{owner}/{repo} # https://github.com/{owner}/{repo}/blob/{ref}/{path} - Network accessline 13
# https://github.com/{owner}/{repo} - Network accessline 14
# https://github.com/{owner}/{repo}/blob/{ref}/{path} - Network accessline 15
# https://github.com/{owner}/{repo}/tree/{ref}/{path} - Network accessline 16
# https://raw.githubusercontent.com/{owner}/{repo}/{ref}/{path} - Network accessline 37
if ! command -v gh >/dev/null 2>&1; then echo '{"error":"gh CLI not found","hint":"Install GitHub CLI: https://cli.github.com"}' >&2 - Network accessline 38
echo '{"error":"gh CLI not found","hint":"Install GitHub CLI: https://cli.github.com"}' >&2 - Network accessline 52
if [[ "$URL" =~ ^https://github\.com/([^/]+)/([^/]+)(/(blob|tree)/([^/]+)(/(.*))?)?/?$ ]]; then - Network accessline 55
REF="${BASH_REMATCH[5]:-}" RAWPATH="${BASH_REMATCH[7]:-}" elif [[ "$URL" =~ ^https://raw\.githubusercontent\.com/([^/]+)/([^/]+)/([^/]+)(/(.*))?/?$ ]]; then - Network accessline 56
RAWPATH="${BASH_REMATCH[7]:-}" elif [[ "$URL" =~ ^https://raw\.githubusercontent\.com/([^/]+)/([^/]+)/([^/]+)(/(.*))?/?$ ]]; then OWNER="${BASH_REMATCH[1]}" - Network accessline 57
elif [[ "$URL" =~ ^https://raw\.githubusercontent\.com/([^/]+)/([^/]+)/([^/]+)(/(.*))?/?$ ]]; then
skills/skill-fetch/scripts/fetch-skillhub.sh
- Executable scriptline 1
#!/bin/bash - Access to secretsline 3
[Credential-related source omitted] - Access to secretsline 8
[Credential-related source omitted] - Access to secretsline 12
[Credential-related source omitted] - Access to secretsline 14
[Credential-related source omitted] - Network accessline 18
RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "https://www.skillhub.club/api/v1/skills/search" \
skills/skill-fetch/scripts/fetch-skills-directory.sh
- Executable scriptline 1
#!/bin/bash - Access to secretsline 3
[Credential-related source omitted] - Access to secretsline 8
[Credential-related source omitted] - Access to secretsline 12
[Credential-related source omitted] - Access to secretsline 14
[Credential-related source omitted] - Network accessline 28
RESPONSE=$(curl -s -w "\n%{http_code}" "https://www.skillsdirectory.com/api/v1/skills?q=${ENCODED_QUERY}&limit=5&securityGrade=A" \
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 2 facts
- Contacts www.skillhub.club, which SKILL.md, the README and the plugin manifest do not mentionskill-fetch/scripts/fetch-skillhub.sh:18High confidence
- Contacts www.skillsdirectory.com, which SKILL.md, the README and the plugin manifest do not mentionskill-fetch/scripts/fetch-skills-directory.sh:28High confidence
Signal confidence: 85 facts
- Broad permissions in the frontmatter of the SKILL.mdskill-fetch/SKILL.md:1High confidence
- Access to secrets in code of the SKILL.mdskill-fetch/SKILL.md:59High confidence
- Access to secrets in code of the SKILL.mdskill-fetch/SKILL.md:60High confidence
- Network access in prose of the SKILL.mdskill-fetch/SKILL.md:73Low confidence
- Network access in prose of the SKILL.mdskill-fetch/SKILL.md:101Low confidence
- Network access in prose of the SKILL.mdskill-fetch/SKILL.md:102Low confidence
- Network access in prose of the SKILL.mdskill-fetch/SKILL.md:103Low confidence
- Network access in prose of the SKILL.mdskill-fetch/SKILL.md:110Low confidence
- Network access in prose of the SKILL.mdskill-fetch/SKILL.md:159Low confidence
- Network access in prose of the SKILL.mdskill-fetch/SKILL.md:160Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:95Low confidence
- Dangerous shell operation in prose of documentationskill-fetch/references/interaction-patterns.md:96Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:96Low confidence
- Dangerous shell operation in prose of documentationskill-fetch/references/interaction-patterns.md:97Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:97Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:98Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueskill-fetch/references/interaction-patterns.md:98Low confidence
- Access to secrets in prose of documentation: reads a credential storeskill-fetch/references/interaction-patterns.md:99Low confidence
- Dangerous shell operation in prose of documentationskill-fetch/references/interaction-patterns.md:100Low confidence
- Dangerous shell operation in code of documentationskill-fetch/references/interaction-patterns.md:118Low confidence
- Instruction override signal in code of documentationskill-fetch/references/interaction-patterns.md:122Low confidence
- Instruction override signal in prose of documentationskill-fetch/references/interaction-patterns.md:135Low confidence
- Instruction override signal in prose of documentationskill-fetch/references/interaction-patterns.md:138Low confidence
- Instruction override signal in prose of documentationskill-fetch/references/interaction-patterns.md:140Low confidence
- Instruction override signal in prose of documentationskill-fetch/references/interaction-patterns.md:175Low confidence
- Instruction override signal in prose of documentationskill-fetch/references/interaction-patterns.md:176Low confidence
- Instruction override signal in prose of documentationskill-fetch/references/interaction-patterns.md:177Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:223Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:224Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:225Low confidence
- Dangerous shell operation in prose of documentationskill-fetch/references/interaction-patterns.md:226Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:238Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:240Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:272Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:273Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:274Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:275Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:276Low confidence
- Network access in prose of documentationskill-fetch/references/interaction-patterns.md:277Low confidence
- Network access in prose of documentationskill-fetch/references/platform-adapters.md:29Low confidence
- Network access in prose of documentationskill-fetch/references/platform-adapters.md:30Low confidence
- Network access in prose of documentationskill-fetch/references/platform-adapters.md:31Low confidence
- Network access in code of documentationskill-fetch/references/platform-adapters.md:57Low confidence
- Network access in code of documentationskill-fetch/references/platform-adapters.md:58Low confidence
- Network access in prose of documentationskill-fetch/references/platform-adapters.md:61Low confidence
- Network access in prose of documentationskill-fetch/references/platform-adapters.md:62Low confidence
- Network access in code of documentationskill-fetch/references/platform-adapters.md:64Low confidence
- Network access in code of documentationskill-fetch/references/platform-adapters.md:89Low confidence
- Network access in code of documentationskill-fetch/references/platform-adapters.md:91Low confidence
- Dangerous shell operation in code of documentationskill-fetch/references/quality-signals.md:134Low confidence
and 35 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/skill-fetch/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/skill-fetch/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/skill-fetch/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/skill-fetch/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/skill-fetch/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
