docs-seeker

Name: docs-seeker
Author: Rune-kit

80stars21forks

How to install docs-seeker?

rune-kit/rune/docs-seeker

$npx -y skills add Rune-kit/rune --skill docs-seeker

Installs into the current project.

Summary

Find documentation for APIs, libraries, and error messages. Looks up official docs, changelog entries, and migration guides.

Files · 1

View on GitHub

SKILL.md

1	# docs-seeker
2
3	## Purpose
4
5	Documentation lookup utility. Receives a library name, API reference, or error message, resolves the correct documentation, and returns API signatures, usage examples, and known issues. Stateless — no memory between calls.
6
7	## Calls (outbound)
8
9	None — pure L3 utility using `WebSearch`, `WebFetch`, and Context7 MCP tools directly.
10
11	## Called By (inbound)
12
13	- `debug` (L2): lookup API docs for unclear errors
14	- `fix` (L2): check correct API usage before applying changes
15	- `review` (L2): verify API usage is current and correct
16	- `adversary` (L2): verify framework/API assumptions in plan are correct
17
18	## Execution
19
20	### Input
21
22	```
23	target: string — library name, API endpoint, or error message
24	version: string — (optional) specific version to look up
25	query: string — specific question about the target (e.g., "how to configure retry")
26	```
27
28	### Step 1 — Identify Target
29
30	Parse the input to extract:
31	- Library or framework name (e.g., "react-query", "fastapi", "prisma")
32	- Version if specified
33	- The specific API, method, or error to look up
34
35	### Step 2 — Try Context7 MCP (fastest)
36
37	Attempt Context7 MCP lookup first (faster, higher quality):
38
39	1. Call `mcp__plugin_context7_context7__resolve-library-id` with the library name and query
40	2. Select the best matching library ID from results (prioritize: name match, source reputation, snippet count)
41	3. Call `mcp__plugin_context7_context7__query-docs` with the resolved library ID and the specific query
42	4. If Context7 returns a satisfactory answer with code examples, proceed to Step 5
43
44	### Step 3 — Try llms.txt Discovery
45
46	If Context7 MCP is unavailable or insufficient, try llms.txt (AI-optimized documentation):
47
48	For GitHub repos — pattern: `https://context7.com/{org}/{repo}/llms.txt`
49	```
50	github.com/vercel/next.js → context7.com/vercel/next.js/llms.txt
51	github.com/shadcn-ui/ui → context7.com/shadcn-ui/ui/llms.txt
52	```
53
54	For doc sites — pattern: `https://context7.com/websites/{normalized-domain}/llms.txt`
55	```
56	docs.imgix.com → context7.com/websites/imgix/llms.txt
57	ffmpeg.org/doxygen/8.0 → context7.com/websites/ffmpeg_doxygen_8_0/llms.txt
58	```
59
60	Topic-specific — append `?topic={query}` for focused results:
61	```
62	context7.com/shadcn-ui/ui/llms.txt?topic=date-picker
63	context7.com/vercel/next.js/llms.txt?topic=cache
64	```
65
66	Traditional llms.txt fallback: `WebSearch "[library] llms.txt"` → common paths: `docs.[lib].com/llms.txt`, `[lib].dev/llms.txt`
67
68	Use `WebFetch` on the resolved llms.txt URL. If it contains multiple section URLs (3+), launch parallel Explorer agents (one per section, max 5).
69
70	### Step 4 — Fallback to Web Search
71
72	If neither Context7 nor llms.txt available:
73
74	1. Use `WebSearch` with queries:
75	- "[library] [api/method] official documentation"
76	- "[library] [version] [query]"
77	- "[error message] [library] fix"
78	2. Identify official documentation URLs (docs.*, official GitHub, npm/pypi pages)
79	3. Call `WebFetch` on the top 1-3 official sources
80
81	Repository analysis fallback (when docs are sparse but code is available):
82	```bash
83	npx repomix --output /tmp/repomix-output.xml # in the cloned repo
84	```
85	Read the repomix output to extract API patterns, usage examples, and internal documentation.
86
87	### Step 5 — Extract Answer
88
89	From Context7, llms.txt, or fetched pages, extract:
90	- Exact API signature with parameter types and return type
91	- Minimal working code example
92	- Version-specific notes (deprecated in X, changed in Y)
93	- Known issues or common pitfalls mentioned in docs
94
95	### Step 6 — Report
96
97	Return structured documentation in the output format below.
98
99	## Constraints
100
101	- Prefer Context7 MCP → llms.txt → WebSearch (in that priority order)
102	- Only fall back to web if Context7 and llms.txt both lack coverage
103	- Use `?topic=` parameter on llms.txt URLs for targeted results
104	- Always include source URL so callers can verify
105	- If the API is deprecated, say so explicitly and link to the replacement
106	- For parallel fetching: 1-3 URLs = single agent, 4-10 = 3-5 Explorer agents, 11+ = 5-7 agents
107
108	## Output Format
109
110	```
111	## Documentation: [Library/API]
112	- Version: [detected or "latest"]
113	- Source: [official docs URL or "Context7"]
114
115	### API Reference
116	- Signature: `functionName(param1: Type, param2: Type): ReturnType`
117	- Parameters:
118	- `param1` — description
119	- `param2` — description
120	- Returns: description
121
122	### Usage Example
123	```[lang]
124	[minimal working code snippet from official docs]
125	```
126
127	### Known Issues / Deprecations
128	- [relevant warning, deprecation notice, or common mistake]
129	```
130
131	## Sharp Edges
132
133	Known failure modes for this skill. Check these before declaring done.
134
135	\| Failure Mode \| Severity

People who liked this also viewed

6 picks

Type

azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026472k1.3k
just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026245k37
firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 202694k531
firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 202676k531
firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 202674k531
firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 202674k531

docs-seeker

80stars21forks

View on GitHub

How to install docs-seeker?

rune-kit/rune/docs-seeker

$npx -y skills add Rune-kit/rune --skill docs-seeker

Installs into the current project.

Summary

Find documentation for APIs, libraries, and error messages. Looks up official docs, changelog entries, and migration guides.

Files · 1

View on GitHub

SKILL.md

1	# docs-seeker
2
3	## Purpose
4
5	Documentation lookup utility. Receives a library name, API reference, or error message, resolves the correct documentation, and returns API signatures, usage examples, and known issues. Stateless — no memory between calls.
6
7	## Calls (outbound)
8
9	None — pure L3 utility using `WebSearch`, `WebFetch`, and Context7 MCP tools directly.
10
11	## Called By (inbound)
12
13	- `debug` (L2): lookup API docs for unclear errors
14	- `fix` (L2): check correct API usage before applying changes
15	- `review` (L2): verify API usage is current and correct
16	- `adversary` (L2): verify framework/API assumptions in plan are correct
17
18	## Execution
19
20	### Input
21
22	```
23	target: string — library name, API endpoint, or error message
24	version: string — (optional) specific version to look up
25	query: string — specific question about the target (e.g., "how to configure retry")
26	```
27
28	### Step 1 — Identify Target
29
30	Parse the input to extract:
31	- Library or framework name (e.g., "react-query", "fastapi", "prisma")
32	- Version if specified
33	- The specific API, method, or error to look up
34
35	### Step 2 — Try Context7 MCP (fastest)
36
37	Attempt Context7 MCP lookup first (faster, higher quality):
38
39	1. Call `mcp__plugin_context7_context7__resolve-library-id` with the library name and query
40	2. Select the best matching library ID from results (prioritize: name match, source reputation, snippet count)
41	3. Call `mcp__plugin_context7_context7__query-docs` with the resolved library ID and the specific query
42	4. If Context7 returns a satisfactory answer with code examples, proceed to Step 5
43
44	### Step 3 — Try llms.txt Discovery
45
46	If Context7 MCP is unavailable or insufficient, try llms.txt (AI-optimized documentation):
47
48	For GitHub repos — pattern: `https://context7.com/{org}/{repo}/llms.txt`
49	```
50	github.com/vercel/next.js → context7.com/vercel/next.js/llms.txt
51	github.com/shadcn-ui/ui → context7.com/shadcn-ui/ui/llms.txt
52	```
53
54	For doc sites — pattern: `https://context7.com/websites/{normalized-domain}/llms.txt`
55	```
56	docs.imgix.com → context7.com/websites/imgix/llms.txt
57	ffmpeg.org/doxygen/8.0 → context7.com/websites/ffmpeg_doxygen_8_0/llms.txt
58	```
59
60	Topic-specific — append `?topic={query}` for focused results:
61	```
62	context7.com/shadcn-ui/ui/llms.txt?topic=date-picker
63	context7.com/vercel/next.js/llms.txt?topic=cache
64	```
65
66	Traditional llms.txt fallback: `WebSearch "[library] llms.txt"` → common paths: `docs.[lib].com/llms.txt`, `[lib].dev/llms.txt`
67
68	Use `WebFetch` on the resolved llms.txt URL. If it contains multiple section URLs (3+), launch parallel Explorer agents (one per section, max 5).
69
70	### Step 4 — Fallback to Web Search
71
72	If neither Context7 nor llms.txt available:
73
74	1. Use `WebSearch` with queries:
75	- "[library] [api/method] official documentation"
76	- "[library] [version] [query]"
77	- "[error message] [library] fix"
78	2. Identify official documentation URLs (docs.*, official GitHub, npm/pypi pages)
79	3. Call `WebFetch` on the top 1-3 official sources
80
81	Repository analysis fallback (when docs are sparse but code is available):
82	```bash
83	npx repomix --output /tmp/repomix-output.xml # in the cloned repo
84	```
85	Read the repomix output to extract API patterns, usage examples, and internal documentation.
86
87	### Step 5 — Extract Answer
88
89	From Context7, llms.txt, or fetched pages, extract:
90	- Exact API signature with parameter types and return type
91	- Minimal working code example
92	- Version-specific notes (deprecated in X, changed in Y)
93	- Known issues or common pitfalls mentioned in docs
94
95	### Step 6 — Report
96
97	Return structured documentation in the output format below.
98
99	## Constraints
100
101	- Prefer Context7 MCP → llms.txt → WebSearch (in that priority order)
102	- Only fall back to web if Context7 and llms.txt both lack coverage
103	- Use `?topic=` parameter on llms.txt URLs for targeted results
104	- Always include source URL so callers can verify
105	- If the API is deprecated, say so explicitly and link to the replacement
106	- For parallel fetching: 1-3 URLs = single agent, 4-10 = 3-5 Explorer agents, 11+ = 5-7 agents
107
108	## Output Format
109
110	```
111	## Documentation: [Library/API]
112	- Version: [detected or "latest"]
113	- Source: [official docs URL or "Context7"]
114
115	### API Reference
116	- Signature: `functionName(param1: Type, param2: Type): ReturnType`
117	- Parameters:
118	- `param1` — description
119	- `param2` — description
120	- Returns: description
121
122	### Usage Example
123	```[lang]
124	[minimal working code snippet from official docs]
125	```
126
127	### Known Issues / Deprecations
128	- [relevant warning, deprecation notice, or common mistake]
129	```
130
131	## Sharp Edges
132
133	Known failure modes for this skill. Check these before declaring done.
134
135	\| Failure Mode \| Severity

People who liked this also viewed

6 picks

Type