skill-fetch

Name: skill-fetch
Author: girofu

51installs3forks

How to install skill-fetch?

girofu/skill-fetch/skill-fetch

$npx -y skills add girofu/skill-fetch --skill skill-fetch

Installs into the current project.

Summary

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 m

Files · 1

View on GitHub

SKILL.md

1	# Skill Fetch
2
3	Search, score, and install agent skills from multiple registries in parallel.
4
5	## When to Use
6
7	- A skill-eval hook outputs "MISSING EXTERNAL SKILL"
8	- The current task requires domain expertise not available locally
9	- The user asks to "fetch skill", "search for a skill", or "install a skill"
10
11	## Critical Rules
12
13	1. Never use `skillsmp_get_skill_content` to preview before deciding — search descriptions are sufficient. Only use as a fallback if installation fails.
14	2. Stop on first results, continue only on zero (max 5 rounds) — any round with ≥1 result proceeds to analysis.
15	3. Only the user can decide to skip — the LLM must never skip installation on its own.
16	4. Always use plain-text interaction — do not use AskUserQuestion. Output analysis and wait for the user to reply with a number or command.
17	5. Show up to 5 results per page — with full analysis (content, pros, cons, repo URL) so the user can make an informed decision.
18
19	## Platform Compatibility
20
21	This skill works across 6+ AI coding agents (Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Amp). Tool names adapt automatically. See `references/platform-adapters.md` for the full mapping table.
22
23	## Procedure
24
25	### Step 0: SkillsMP MCP Self-Check (Claude Code only)
26
27	Before searching, verify that the SkillsMP MCP server is available:
28
29	1. First, try loading deferred tools: Run `ToolSearch("skillsmp")` to load any deferred SkillsMP MCP tools. In Claude Code, MCP tools are often deferred (not loaded until requested) and have namespaced names like `mcp__skillsmp__skillsmp_search`. The `ToolSearch` call resolves these.
30	2. After ToolSearch, check if any `skillsmp_` or `mcp__skillsmp__` tool is now available
31	3. If available → proceed to Step 1
32	4. If still not available → run: `claude mcp add --scope user skillsmp -- npx -y skillsmp-mcp-server`
33	5. Inform the user: "SkillsMP MCP server has been registered. It will be available after restarting the session. Continuing search with the remaining 7 sources for now."
34	6. Proceed to Step 1 (SkillsMP sources will be skipped this session, but available in future sessions)
35
36	> Tool name note: SkillsMP tools may appear with MCP namespace prefix: `mcp__skillsmp__skillsmp_search` instead of `skillsmp_search`. Both forms work — use whichever is available.
37
38	> Non-Claude Code agents: Skip this step. SkillsMP tools are Claude Code-specific.
39
40	### Step 0.5: Load API Keys (MANDATORY — execute before Step 2)
41
42	Sources 8-9 require API keys. Read the config file to determine availability:
43
44	1. Read `~/.claude/skills/.fetch-config.json` NOW — do not assume keys are absent without reading the file
45	2. Expected format:
46	```json
47	{
48	"SKILLHUB_API_KEY": "sk-sh-...",
49	"SKILLS_DIRECTORY_API_KEY": "sk_live_..."
50	}
51	```
52	3. Record the result — set two flags for use in Step 2b:
53	- `HAS_SKILLHUB_KEY`: true/false
54	- `HAS_SKILLS_DIR_KEY`: true/false
55	4. If config file does not exist → both flags = false, inform user they can create the file
56	5. If config file exists but a specific key is missing → that flag = false
57
58	> ⚠️ COMMON FAILURE MODE: LLM skips reading the config file and assumes "no key". This causes Sources 8-9 to be incorrectly skipped even when keys ARE configured. Always read the file first.
59
60	### Step 1: Determine Search Keywords and Source
61
62	URL mode: If `$ARGUMENTS` is a URL (starts with `https://github.com/...` or any `https://`), skip directly to Step 3 installation flow.
63
64	Search mode:
65	- Has `$ARGUMENTS`: Use directly as search terms
66	- No search terms (auto-triggered): Prefer `Suggested search terms` from hook output, otherwise extract 2-3 queries from task context
67
68	### Step 2: Parallel Search — ALL 9 Sources (mandatory)
69
70	⚠️ MANDATORY: You MUST fire ALL 9 sources. Do NOT proceed to scoring until all 9 sources have returned or failed.
71
72	⚠️ COMMON FAILURE MODE: LLM fires sources 1-2 (SkillsMP), gets results, then skips sources 3-9. This is WRONG. SkillsMP results alone are insufficient — GitHub, ClawhHub, skills.sh, and PolySkill contain different skills not indexed by SkillsMP.
73
74	⚠️ EXECUTION ORDER: You MUST complete BOTH Step 2a AND Step 2b before proceeding to Step 2.5. Step 2a alone is NOT sufficient.
75
76	#### Step 2a: Fire SkillsMP sources (1-2)
77
78	\| # \| Source \| Tool Call \| Fallback \|
79	\|---\|--------\|-----------\|----------\|
80	\| 1 \| SkillsMP AI \| `skillsmp_ai_search` × 3 query v

People who liked this also viewed

6 picks

Type

skill-fetch

51installs3forks

View on GitHub

How to install skill-fetch?

girofu/skill-fetch/skill-fetch

$npx -y skills add girofu/skill-fetch --skill skill-fetch

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Skill Fetch
2
3	Search, score, and install agent skills from multiple registries in parallel.
4
5	## When to Use
6
7	- A skill-eval hook outputs "MISSING EXTERNAL SKILL"
8	- The current task requires domain expertise not available locally
9	- The user asks to "fetch skill", "search for a skill", or "install a skill"
10
11	## Critical Rules
12
13	1. Never use `skillsmp_get_skill_content` to preview before deciding — search descriptions are sufficient. Only use as a fallback if installation fails.
14	2. Stop on first results, continue only on zero (max 5 rounds) — any round with ≥1 result proceeds to analysis.
15	3. Only the user can decide to skip — the LLM must never skip installation on its own.
16	4. Always use plain-text interaction — do not use AskUserQuestion. Output analysis and wait for the user to reply with a number or command.
17	5. Show up to 5 results per page — with full analysis (content, pros, cons, repo URL) so the user can make an informed decision.
18
19	## Platform Compatibility
20
21	This skill works across 6+ AI coding agents (Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Amp). Tool names adapt automatically. See `references/platform-adapters.md` for the full mapping table.
22
23	## Procedure
24
25	### Step 0: SkillsMP MCP Self-Check (Claude Code only)
26
27	Before searching, verify that the SkillsMP MCP server is available:
28
29	1. First, try loading deferred tools: Run `ToolSearch("skillsmp")` to load any deferred SkillsMP MCP tools. In Claude Code, MCP tools are often deferred (not loaded until requested) and have namespaced names like `mcp__skillsmp__skillsmp_search`. The `ToolSearch` call resolves these.
30	2. After ToolSearch, check if any `skillsmp_` or `mcp__skillsmp__` tool is now available
31	3. If available → proceed to Step 1
32	4. If still not available → run: `claude mcp add --scope user skillsmp -- npx -y skillsmp-mcp-server`
33	5. Inform the user: "SkillsMP MCP server has been registered. It will be available after restarting the session. Continuing search with the remaining 7 sources for now."
34	6. Proceed to Step 1 (SkillsMP sources will be skipped this session, but available in future sessions)
35
36	> Tool name note: SkillsMP tools may appear with MCP namespace prefix: `mcp__skillsmp__skillsmp_search` instead of `skillsmp_search`. Both forms work — use whichever is available.
37
38	> Non-Claude Code agents: Skip this step. SkillsMP tools are Claude Code-specific.
39
40	### Step 0.5: Load API Keys (MANDATORY — execute before Step 2)
41
42	Sources 8-9 require API keys. Read the config file to determine availability:
43
44	1. Read `~/.claude/skills/.fetch-config.json` NOW — do not assume keys are absent without reading the file
45	2. Expected format:
46	```json
47	{
48	"SKILLHUB_API_KEY": "sk-sh-...",
49	"SKILLS_DIRECTORY_API_KEY": "sk_live_..."
50	}
51	```
52	3. Record the result — set two flags for use in Step 2b:
53	- `HAS_SKILLHUB_KEY`: true/false
54	- `HAS_SKILLS_DIR_KEY`: true/false
55	4. If config file does not exist → both flags = false, inform user they can create the file
56	5. If config file exists but a specific key is missing → that flag = false
57
58	> ⚠️ COMMON FAILURE MODE: LLM skips reading the config file and assumes "no key". This causes Sources 8-9 to be incorrectly skipped even when keys ARE configured. Always read the file first.
59
60	### Step 1: Determine Search Keywords and Source
61
62	URL mode: If `$ARGUMENTS` is a URL (starts with `https://github.com/...` or any `https://`), skip directly to Step 3 installation flow.
63
64	Search mode:
65	- Has `$ARGUMENTS`: Use directly as search terms
66	- No search terms (auto-triggered): Prefer `Suggested search terms` from hook output, otherwise extract 2-3 queries from task context
67
68	### Step 2: Parallel Search — ALL 9 Sources (mandatory)
69
70	⚠️ MANDATORY: You MUST fire ALL 9 sources. Do NOT proceed to scoring until all 9 sources have returned or failed.
71
72	⚠️ COMMON FAILURE MODE: LLM fires sources 1-2 (SkillsMP), gets results, then skips sources 3-9. This is WRONG. SkillsMP results alone are insufficient — GitHub, ClawhHub, skills.sh, and PolySkill contain different skills not indexed by SkillsMP.
73
74	⚠️ EXECUTION ORDER: You MUST complete BOTH Step 2a AND Step 2b before proceeding to Step 2.5. Step 2a alone is NOT sufficient.
75
76	#### Step 2a: Fire SkillsMP sources (1-2)
77
78	\| # \| Source \| Tool Call \| Fallback \|
79	\|---\|--------\|-----------\|----------\|
80	\| 1 \| SkillsMP AI \| `skillsmp_ai_search` × 3 query v

People who liked this also viewed

6 picks

Type