Context Audit
Audit project context management (CLAUDE.md, rules, knowledge) for progressive disclosure compliance. Checks that all knowledge files are reachable from rules, detects stale references, orphaned files, and CLAUDE.md index leakage. Triggers: 'audit context', 'check context', 'context hygiene', 'context audit', '检查 context', '审计上下文', 'knowledge 覆盖检查'. NOT for: code review, rule content correctness, or knowledge content quality.
Install
/plugin marketplace add jiahao-shao1/sjh-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add jiahao-shao1/sjh-skills --skill context-auditgit clone --depth 1 https://github.com/jiahao-shao1/sjh-skills.git /tmp/sjh-skills
mkdir -p ~/.claude/skills
cp -r /tmp/sjh-skills/skills/context-audit ~/.claude/skills/context-auditPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Context Audit
Audits the project's three-layer context management system (CLAUDE.md / rules / knowledge) against the **progressive disclosure** architecture:
```
CLAUDE.md (always loaded) — describes architecture, no detailed index
└─ Rules (.claude/rules/) (always loaded) — inline `> 详见` refs to knowledge
└─ Knowledge (docs/knowledge/) — on-demand deep experience
```
## When to Use
- After adding new knowledge files — verify they're indexed from a rule
- After refactoring rules — verify no references broke
- Periodic hygiene check — catch drift over time
- After onboarding a new domain — verify the new rule covers its knowledge files
## Execution
### Phase 1: Discovery
Scan the project to find all context files:
```bash
# Knowledge files
find docs/knowledge/ -name "*.md" -type f 2>/dev/null | sort
# Rule files
find .claude/rules/ -name "*.md" -type f 2>/dev/null | sort
# CLAUDE.md
ls CLAUDE.md 2>/dev/null
```
If `docs/knowledge/` or `.claude/rules/` doesn't exist, report and skip the corresponding checks.
### Phase 2: Cross-Reference Audit
For each knowledge file found in Phase 1:
1. **Grep rule files first** for references to that knowledge file (match `docs/knowledge/<filename>` or bare `<filename>`)
2. **If not found in rules, grep knowledge index files** (`docs/knowledge/*-index.md` or files whose name ends with `-index.md`). An index file that is itself rule-referenced transitively covers the leaves it lists.Details
- Skill name
context-audit- Repository
- jiahao-shao1/sjh-skills
- Path
skills/context-audit/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Context Audit skill do?
Audit project context management (CLAUDE.md, rules, knowledge) for progressive disclosure compliance. Checks that all knowledge files are reachable from rules, detects stale references, orphaned files, and CLAUDE.md index leakage. Triggers: 'audit context', 'check context', 'context hygiene', 'context audit', '检查 context', '审计上下文', 'knowledge 覆盖检查'. NOT for: code review, rule content correctness, or knowledge content quality.
How do I install the Context Audit skill?
Claude Code plugin: /plugin marketplace add jiahao-shao1/sjh-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Context Audit popular?
It lives in jiahao-shao1/sjh-skills, which has 44 GitHub stars and 1 forks.
Related skills
Bibtex Fetch
44jiahao-shao1/sjh-skills
Fetch BibTeX entries from arXiv / Semantic Scholar. Triggers: 'fetch bibtex', 'cite this paper', 'arXiv bibtex', '拉 bibtex', '获取引用', '引用这篇论文'. Not for citation format conversion (APA/MLA) or literature review.
Daily Summary
44jiahao-shao1/sjh-skills
Produce daily/yesterday work summary (日报) by aggregating Claude Code sessions, Git commits, and Notion task data — git log alone cannot do this. Args: today (default), yesterday, 24h, YYYY-MM-DD. Triggers: 'daily summary', 'what did I do today', 'yesterday summary', '日报', '今天干了什么', '工作总结', '某天做了什么'. Not for weekly reports or summarizing files.
Experiment Registry
44jiahao-shao1/sjh-skills
Manage ML experiment lifecycle via structured YAML registry — register, record results, compare runs, track status. Triggers: 'register experiment', 'compare experiments', 'experiment results', 'exp init', 'exp list', '注册实验', '对比实验', '查实验', '哪个实验最好', '记录结果'. Not for training monitoring, checkpoints, or launching jobs.
Davinci Resolve Color Grade Webcam
35ChaiWithJai/davinci-resolve-claude-skills
Use when a user wants webcam, interview, or talking-head footage to look broadcast-quality — corrects exposure, white balance, skin tones, and overall color. Triggering symptoms include phrases like "my webcam footage looks dull", "skin tones look orange/green", "wash out background", "make the face pop", "match shots from two cameras", or any DaVinci Resolve color page question for talking-head content.
Adapter Capability Probe
43rohitg00/agentbrain
Use when a command, adapter, or runtime smoke depends on proving an agent runtime's capabilities before trusting command routing, writes, shell access, or validation claims.
Davinci Resolve Cut Screen Recording
35ChaiWithJai/davinci-resolve-claude-skills
Use when a user has a long screen recording, tutorial, conference talk, or demo recording and needs to cut it down to a tight watchable version — removes dead air, mistakes, "ums", and silences. Triggering symptoms include phrases like "raw recording is too long", "edit out the bad takes", "fix the ums", "remove silences", "rough cut my demo", or any DaVinci Resolve cutting question for long-form content.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.