audit-project-context
Audit, verify, update, or clean docs, prompts, skills, agents, instructions, README files, and other markdown/MD files against the current project codebase.
Skill by werlang
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/werlang-audit-project-context
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/audit-project-context
What's inside
- Skill name
audit-project-context- Description
- Audit, verify, update, or clean docs, prompts, skills, agents, instructions, README files, and other markdown/MD files against the current project codebase. Use when documentation or agent context may be stale, inaccurate, inconsistent, or aspirational and must be aligned with the real implementation.
- License
- MIT
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- audit-checklist.md · references/
- output-template.md · references/
SKILL.md (first lines)
# Audit Project Context Use this skill to audit the current project's documentation and agent customization files against the actual implementation, then rewrite inaccurate sections so the context stays trustworthy. ## Covers - `.github/**` - `.agents/**` - `.claude/**` - `README.md`, `AGENTS.md`, `CLAUDE.md` - `docs/**/*.md`, `tasks/**/*.md` - prompt, instruction, agent, skill, reference, and other markdown files related to project context ## Workflow 1. Read the in-scope docs and customization files first to understand the current documented state. 2. Research the actual implementation: runtime, services, routes, entities/models, config, env vars, scripts, infrastructure, tests, and deployment expectations. 3. Compare docs to code and record discrepancies with [the audit checklist](./references/audit-checklist.md). 4. Update inaccurate, stale, or incomplete files. Remove aspirational claims that are not enforced by code or tooling. 5. Sweep for terminology drift, broken links, missing files, and contradictory claims across docs. 6. Return the result using [the output template](./references/output-template.md). ## Rules - Code and configuration are the source of truth. - Do not preserve "should", "must", or "we have" language unless the repository actually enforces it. - Keep accurate structure when useful, but rewrite incorrect technical details. - If a doc references tooling, agents, or files that do not exist, fix or remove the reference. ## Required Checks - Routes, commands, env vars, ports, and file paths are real. - Skill descriptions and examples match actual workflows. - Prompts and agents point to files and conventions that exist. - README/setup steps are executable for the current project. - Cross-file terminology is consistent for the same concepts. ## Output Return: - files updated - key discrepancies fixed, removed, or added - remaining implementation issues discovered during the audit - confidence notes for terminology and consistency sweeps
From werlang/user-skills, MIT.
More from werlang/user-skills
- 0.570score
clean-code-and-oop
werlang
Authoritative engineering standards for writing Clean Code, Object-Oriented Programming (OOP) architectures, SOLID design principles, and safe refactoring.
SkillAFreshness: AClaude Code +9 - 0.570score
code-review
werlang
Review changes since a fixed point (commit, branch, tag, or merge-base) along a risk-calibrated gradient (Trunk vs Leaf code) across Standards, Spec, and…
SkillAFreshness: AClaude Code +9 - 0.570score
css-standards
werlang
Enforce reusable, brand-aware CSS architecture for public web apps by owning shared tokens in a common stylesheet, importing page entrypoints first, keeping…
SkillAFreshness: AClaude Code +9 - 0.570score
entity-models
werlang
Model API entities as classes inside model/, including base model inheritance, relation helpers, model-to-model composition, and route-to-model instance flows.
SkillAFreshness: AClaude Code +9 - 0.570score
git-change-workflow
werlang
Choose and apply a Git branching, worktree, and commit workflow for implementation, refactor, bug-fix, documentation, and configuration work.
SkillAFreshness: AClaude Code +9 - 0.570score
api-building
werlang
Build or refactor reusable Node.js APIs using Express, express.Router, ESM imports, named exports, entity classes in model/, helpers for non-endpoint logic…
SkillAFreshness: AClaude Code +9 - 0.544score
frontend-design
werlang
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.
SkillAFreshness: AClaude Code +9 - 0.529score
document-touched-code
werlang
Document touched code with JSDoc, method comments, and focused section comments as the default behavior whenever implementing a new feature, refactoring…
SkillBFreshness: BClaude Code +9 - 0.474score
documentation-maintenance
werlang
Keep project documentation, agent guidance, comments, and validation instructions synchronized with the real implementation.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 10, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/werlang/user-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from werlang
- 0.570score
clean-code-and-oop
werlang
Authoritative engineering standards for writing Clean Code, Object-Oriented Programming (OOP) architectures, SOLID design principles, and safe refactoring.
SkillAFreshness: AClaude Code +9 - 0.570score
code-review
werlang
Review changes since a fixed point (commit, branch, tag, or merge-base) along a risk-calibrated gradient (Trunk vs Leaf code) across Standards, Spec, and…
SkillAFreshness: AClaude Code +9 - 0.570score
css-standards
werlang
Enforce reusable, brand-aware CSS architecture for public web apps by owning shared tokens in a common stylesheet, importing page entrypoints first, keeping…
SkillAFreshness: AClaude Code +9 - 0.570score
entity-models
werlang
Model API entities as classes inside model/, including base model inheritance, relation helpers, model-to-model composition, and route-to-model instance flows.
SkillAFreshness: AClaude Code +9 - 0.570score
git-change-workflow
werlang
Choose and apply a Git branching, worktree, and commit workflow for implementation, refactor, bug-fix, documentation, and configuration work.
SkillAFreshness: AClaude Code +9 - 0.570score
api-building
werlang
Build or refactor reusable Node.js APIs using Express, express.Router, ESM imports, named exports, entity classes in model/, helpers for non-endpoint logic…
SkillAFreshness: AClaude Code +9
Cite this page
audit-project-context skill. Agent Mart. https://agentmart.dev/skills/werlang-audit-project-context (last updated 2026-10-24)