knowledge-refresh — Claude Code skill: what it does, how to install
knowledge-refresh — a Claude Code skill that checks project knowledge against code and data after a release. It proposes fixes for stale or inaccurate files.
MIT ★ 106 updated 2026-11-06
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills
/plugin install data-engineering@data-with-baraaWhat knowledge-refresh does
knowledge-refresh checks whether project knowledge matches the current code and data. After a release, it compares CLAUDE.md, standards, source pages, the glossary, documents, architecture, the core model, known issues, and incident records. Run it with an area to inspect or without an argument.
For each finding, the skill names the file, summarizes its current claim, states what is true, and proposes a change. It also flags unread documents and trims repeated material while linking to the file that keeps it. Changes are written only after approval from the data engineer, and only to knowledge files; runbooks and how-to guides belong to a separate docs skill.
What it helps with
- find stale paths in
CLAUDE.md - compare project standards with the code
- check source contracts against their files
- prepare knowledge-file updates after a release
Example prompts for the agent
- After the release, check which project notes are out of date.
- Compare the architecture and standards with the code in
models. - Review the incident log and propose updates to the knowledge files.
How to install knowledge-refresh
1Plugin marketplace
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills/plugin install data-engineering@data-with-baraaThis installs the whole data-engineering plugin with all its skills
2Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill knowledge-refresh -a claude-code3Manually: put the files in place
~/.claude/skills/knowledge-refresh/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/knowledge-refresh/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill knowledge-refresh -a codex2Manually: put the files in place
.agents/skills/knowledge-refresh/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill knowledge-refresh -a cursor2Manually: put the files in place
.cursor/skills/knowledge-refresh/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install DataWithBaraa/claude-code-data-engineering-skills skills/knowledge-refresh2Manually: put the files in place
.github/skills/knowledge-refresh/SKILL.md1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill knowledge-refresh -a gemini-cli2Platform CLI
gemini skills install https://github.com/DataWithBaraa/claude-code-data-engineering-skills --path skills/knowledge-refreshManually: put the files in place
.devin/skills/knowledge-refresh/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about knowledge-refresh
How do I install knowledge-refresh in Claude Code?
Add the marketplace with /plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills, then install the plugin with /plugin install data-engineering@data-with-baraa.
What does knowledge-refresh do?
After a release, it compares project knowledge and documents with the code and data, then lists proposed fixes for mismatches. It writes approved changes only after the data engineer agrees.
Can knowledge-refresh change files without approval?
No. It presents proposed changes first and writes to knowledge files only after approval.
Source text
SKILL.md · MIT
--- name: knowledge-refresh description: Use after a release, to compare the knowledge Claude Code reads, CLAUDE.md, the standards, the source pages and the incident log, with the code and the data, and propose what is stale, missing or wrong. argument-hint: "[area]" --- # Knowledge refresh The job: keep the knowledge that Claude Code reads true to the project: CLAUDE.md and the knowledge folder. It proposes, and after the data engineer's yes it writes the approved changes. The runbook and the how-to guides belong to the docs skill. Input: none, or the area to check. ## Steps 1. CLAUDE.md: every folder it names exists, every skill is listed, every path is right. 2. The standards against the code: naming, layers, code style. 3. The sources against the contracts and the files: one page per source, current. 4. The business: the glossary and the stakeholders against the documents. 5. The architecture and the core model against what is built. 6. The known issues and the incident log: what a run has proven since. The incident skill adds the entries, this skill checks them. 7. The decision log: what is decided, what is still open. 8. A document nobody has read yet: what it adds to the knowledge. 9. Keep it short: what repeats another file is cut and linked. 10. Report every finding as a proposal: the file, what it says, what is true. ## Output A list of proposals, one per finding: the file, what it says, what is true, and the change. After the yes, the approved changes in the knowledge files. ## Reads - the knowledge, the code, the data contracts, the documents, the run records ## Writes - nothing until the yes, then only the knowledge files the data engineer approved ## Never - Never applies a change without the yes.
© Data With Baraa · MIT · DataWithBaraa/claude-code-data-engineering-skills