docs▌
buiducnhat/agent-skills · updated Apr 8, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Create and maintain project documentation in docs/ with a consistent, lightweight structure.
Docs
Create and maintain project documentation in docs/ with a consistent, lightweight structure.
Outputs
Maintain these outputs:
docs/SUMMARY.md— documentation entry point (always regenerated)docs/architecture/— system design, infrastructure, component interactions, data flows, feature flows. Focus on how the system works, not file/code structure.docs/codebase/— file organization, directory structure, entry points, key modules and their responsibilities. Focus on where things live in the code.docs/code-standard/— coding conventions, naming rules, style guides, environment setup, custom rules and patterns the team follows. Focus on how to write code that fits in with the existing codebase, best practices, and team conventions, very important for maintaining consistency.docs/project-pdr/— product goals, use cases, business rules, constraints, and decision rationale. Nice to have many use case/requirements files
Also keep README.md aligned with current docs links and project summary.
Workflow
Step 1: Context Scan
Scan the project to understand what needs documenting:
- Read existing docs if any (
docs/SUMMARY.mdand topic folders) - Read
README.mdand key config files (package.json,tsconfig.json,Cargo.toml, etc.) - Scan source directories to understand project structure, entry points, and major components
- Check
git log --oneline -20for recent changes when updating existing docs
Focus on facts: features, architecture, stack, directory structure, and workflows. Do not invent requirements or assume business logic that is not evident from the code.
Step 2: Infer Behavior
- Infer whether the repository needs an initial documentation pass or an incremental update based on the current
docs/state. - If
docs/does not exist or is clearly incomplete, perform initialization behavior. - If
docs/already exists with the standard structure, perform update behavior. - State the inferred behavior briefly when relevant.
Step 3: Produce Documentation
Initialize docs when missing or incomplete
- Create
docs/and 4 topic folders:architecture/,codebase/,code-standard/,project-pdr/ - For each topic folder:
a. Scan codebase for relevant information
b. Generate content based on codebase scan
c. Create topic-specific files based on content found in the codebase. Name each file by its content (e.g.,
components.md,conventions.md). Do NOT use generic names (overview.md,index.md,main.md). Split into multiple files when content covers 2+ clearly distinct sub-topics. Minimum 1 file per folder. - Create
docs/SUMMARY.mdusing the format specified in Content Requirements - Update
README.mdwith link todocs/SUMMARY.md
Populate each file with concrete, project-specific content. Avoid placeholders and generic templates.
Update docs when they already exist
- Detect what changed: compare current code against existing docs. Use
git log --onelineand source file scanning to identify new/modified/removed components. - Preserve useful existing content and section structure.
- Update stale or inaccurate sections in-place — do not rewrite from scratch.
- Add newly discovered features, components, or conventions.
- Remove clearly obsolete statements.
- Add, modify, or remove detail files as needed based on content changes.
- Regenerate
docs/SUMMARY.mdto match current files — only list files that actually exist on disk. - Update
README.mdif documentation links changed.
Important: The goal is an incremental, surgical update — not a full rewrite.
Step 4: Sync README
Ensure README.md includes:
- Short project overview
- Quick start (if present in project)
- Documentation link pointing to
docs/SUMMARY.md
Step 5: Validate Quality
Before finishing, verify:
docs/SUMMARY.mdexists and lists every detail file that actually exists on disk (no phantom entries)- Each topic folder has at least 1 topic-specific file
- No generic file names (
overview.md,index.md,main.md) in topic folders README.mdlinks point todocs/SUMMARY.mdSUMMARY.mdis concise and contains file tables for all sections- Terminology is consistent across files
- No contradictions between docs and code
- Paths and component names are accurate
- Content is concise, specific, and actionable
Content Requirements
SUMMARY.md format
Contains project overview and file tables for each documentation section.
Strictly follow the template in references/summary-template.md.
Topic file rules
- Each file focuses on 1 specific sub-topic within its folder
- Named by content slug:
components.md,conventions.md,product-goals.md - Do NOT use generic names:
overview.md,index.md,main.md,general.md - Keep files focused and concise without enforcing line-count targets
Edge Cases
- Minimal/empty project: If the codebase has very little code, keep topic files short and factual. Do not pad content to reach arbitrary size targets. Mark sections as "TBD — to be documented as the project grows" when there is genuinely nothing to document yet. Even with 1 file per folder, name it by its content.
- Custom files in
docs/: Preserve any user-created files outside the 4 standard topic folders (e.g.,docs/API.md,docs/deployment.md). List them under "Other" inSUMMARY.md. Do not move or rename them. - Monorepo: If the project contains multiple packages/apps, document the overall structure in
architecture/components.mdand note each package's purpose. Each package does not need its own full docs set — keep it proportional.
Rules
- Keep documentation factual; do not invent requirements.
- Prefer concise updates over verbose prose.
- Keep docs aligned with current implementation.
- When uncertain, mark assumptions explicitly and request confirmation.
- Ask targeted questions when information cannot be reliably inferred (business goals, ambiguous module ownership, conflicting conventions, unclear architecture decisions).
How to use docs on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add docs
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches docs from GitHub repository buiducnhat/agent-skills and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate docs. Access the skill through slash commands (e.g., /docs) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
Task Automation & Efficiency
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Knowledge Enhancement
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Quality Improvement
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client with skill support
- ›Clear understanding of task or problem to solve
- ›Willingness to iterate and refine outputs
Time Estimate
15-45 minutes depending on use case complexity
Installation Steps
- 1.Install skill using provided installation command
- 2.Test with simple use case relevant to your work
- 3.Evaluate output quality and relevance
- 4.Iterate on prompts to improve results
- 5.Integrate into regular workflow if valuable
Common Pitfalls
- ⚠Expecting perfect results without iteration
- ⚠Not providing enough context in prompts
- ⚠Using skill for tasks outside its intended scope
- ⚠Accepting outputs without review and validation
Best Practices▌
✓ Do
- +Start with clear, specific prompts
- +Provide relevant context and constraints
- +Review and refine all outputs before using
- +Iterate to improve output quality
- +Document successful prompt patterns
✗ Don't
- −Don't use without understanding skill limitations
- −Don't skip validation of outputs
- −Don't share sensitive information in prompts
- −Don't expect skill to replace human judgment
💡 Pro Tips
- ★Be specific about desired format and style
- ★Ask for multiple options to choose from
- ★Request explanations to understand reasoning
- ★Combine AI efficiency with human expertise
When to Use This▌
✓ Use When
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid When
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
Learning Path▌
- 1Familiarize yourself with skill capabilities and limitations
- 2Start with low-risk, non-critical tasks
- 3Progress to more complex and valuable use cases
- 4Build expertise through regular use and experimentation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.7★★★★★33 reviews- ★★★★★Yuki Li· Dec 28, 2024
docs reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Kofi Rao· Dec 16, 2024
Useful defaults in docs — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Xiao Patel· Nov 19, 2024
docs has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Tariq Yang· Oct 10, 2024
docs fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Piyush G· Sep 25, 2024
docs fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Nia Malhotra· Sep 21, 2024
docs reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Arya Park· Sep 17, 2024
docs is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Shikha Mishra· Aug 16, 2024
docs has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Nia Liu· Aug 12, 2024
We added docs from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Arya Okafor· Aug 8, 2024
Solid pick for teams standardizing on skills: docs is focused, and the summary matches what you get after install.
showing 1-10 of 33