Automated summary
This skill tells the agent how to locate relevant information inside a project's docs/ folder, starting with docs/README.md and docs/STATUS.md and then routing to the right runbook or reference file.
Strengths
- Provides an explicit routing table mapping needs (crawlers, deployment, classification, droplet) to specific documentation files
- Requires reading STATUS.md as the source of truth before answering, which prevents guessing from stale assumptions
- Covers operational runbooks as well as strategy, architecture references, and in-progress working notes
- Explicitly instructs the agent to admit when no docs file has the answer instead of fabricating one
Limitations
- Tightly coupled to one specific docs/ tree (runbooks/, strategy/, references/, working/, archive/), so it is not directly reusable on another project
- Describes only how to read documentation, not how to write or maintain it
- Output quality depends entirely on how current STATUS.md and the referenced files actually are
Use it whenever an agent needs operational or strategic project context before acting, or when the user asks to check the docs or look something up.
Avoid it for general questions unrelated to the project, or when the answer must come from reading the source code rather than the documentation.
Security analysis
SafeThe skill only instructs reading documentation files within a docs/ directory and summarizing information. It declares no tools, does not execute commands, access the network, or modify files. There is no destructive, exfiltrating, or obfuscated behavior.
No concerns found
How this analysis is madeExamples
Check the docs and tell me the current corpus size, per-crawler doc counts, and whether production is in sync.I need to sync the latest data to production and deploy — look up the docs for the exact steps.What do we know about building a new crawler? Check the docs before we start.name: docs description: Find project information in the docs/ folder. Use when you need context about the project state, how to run crawlers, deployment steps, research plans, or any operational detail. Also use when the user says "check the docs", "look it up", "what do we know about X", or when you realize you're missing context to complete a task.
Project Documentation Lookup
Project documentation lives in docs/. Find what you need using this strategy.
Step 1: Orient
Read these two files first:
docs/README.md— folder structure and quick linksdocs/STATUS.md— live project state: corpus size, per-crawler doc counts, droplet status, production sync state, classification progress
Read STATUS.md even if you think you know the answer — it's the source of truth.
Step 2: Find the right file
| You need to... | Read |
|----------------|------|
| Run a crawler, debug a crawl, understand a crawler's technique | docs/runbooks/crawling.md |
| Build a new crawler from scratch | docs/runbooks/new-crawler-guide.md |
| Sync data to production or deploy | docs/runbooks/sync-and-deploy.md |
| Classify documents with DeepSeek | docs/runbooks/classification.md |
| Set up or manage the droplet | docs/runbooks/droplet.md |
| Know what to work on next (crawler expansion) | docs/strategy/crawl-expansion.md |
| Understand the research vision, audience, competitive landscape | docs/strategy/research-vision.md |
| Plan web app features | docs/strategy/website-features.md |
| Understand the system architecture or database schema | docs/references/architecture.md |
| Understand gkmlpt (Guangdong platform) | docs/references/gkmlpt-survey.md |
| Understand how APIs and web scraping work | docs/references/apis-and-scraping.md |
| Understand the AI policy governance chain (central to local) | docs/references/ai-policy-vertical.md |
| Find in-progress research or notes | docs/working/ (list files) |
| Find completed plans or historical session logs | docs/archive/ |
Step 3: Report
Summarize the key information found. If no docs file has the answer, say so.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/project-documentation-lookup-mryiqir1' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/project-documentation-lookup-mryiqir1/download' --output '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md.part' && mv '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md.part' '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md' && test -s '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/docs' && cp -R '.skill-downloads/project-documentation-lookup-mryiqir1' '.claude/skills/docs'Cursor
test -f '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md' && test -s '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/docs' && cp -R '.skill-downloads/project-documentation-lookup-mryiqir1' '.cursor/skills/docs'Codex
test -f '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md' && test -s '.skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/docs' && cp -R '.skill-downloads/project-documentation-lookup-mryiqir1' '.agents/skills/docs'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/project-documentation-lookup-mryiqir1'openskills read 'project-documentation-lookup-mryiqir1'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/project-documentation-lookup-mryiqir1/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.