qa-agent
Skill1 starsChanged 7 months agoMITView on GitHub
Answer questions from the vault, then file durable insights back into the knowledge base.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- thefrederiksen/devthrottletheir own version, first seen Nov 1, 2026
- jonmumm/skillstheir own version, first seen Oct 13, 2026
- itential/builder-skillstheir own version, first seen Oct 13, 2026
- schuligan/claude-skills-collectiontheir own version, first seen Oct 13, 2026
- mriaus/claude-skillstheir own version, first seen Oct 11, 2026
- thefrederiksen/cc-directortheir own version, first seen Oct 8, 2026
Used with
Projects with it also use release-manager.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
exzmSkillrelease-manager
Manages releases as a Release Manager/Tech Lead. Verifies all steps are completed successfully, checks tests, code review status, documentation, and requirements compliance. Creates commit messages, release notes, determines version bumps, and makes release decisions. Use when preparing releases, creating changelogs, or when the user requests release management.
Also in 3 projects that use this
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- thefrederiksen/cc-director★ 110same name
- thefrederiksen/devthrottle★ 110same name
- itential/builder-skills★ 18same name
- tomazb/agent-skills★ 4same name
- jonmumm/skills★ 2same name
- 3akat-system/nexus-starter★ 0same name
- arturmuller25/claude-skills★ 0same name
- mriaus/claude-skills★ 0same name
- schuligan/claude-skills-collection★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- compile-wikiSkill
- ingest-sourcesSkill
- lint-healSkill
- render-outputSkill
- research-workflowSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 1 is distinctive, and 9 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read notes/Home.md or notes/Indexes/Flat_Concept_Index.md, and run search_vault.py programmatically.
- Very specific: line 35
Must have a top-level heading (e.g.
- Very specific: line 36
Must have a second-level heading (e.g.
- Very specific: line 37
Must have a ## Vault Updates section.
- Very specific: line 38
If answer_quality: durable, this section must list the exact edits made to concept pages.
- Very specific: line 39
If answer_quality: memo-only, this section must be exactly - None..
- Distinctive: line 44
Do not fabricate evidence.
- Very specific: line 45
Every factual claim in the answer must carry an inline wikilink citation: [[Sources/<source_id>|<source_id>]] or [[Concepts/<name>|<name>]].
- Very specific: line 52
If gap found: Add to the concept page's ## Open Questions and notes/TODO.md.
- Very specific: line 53
If contradiction found: Add to notes/Maintenance/Contradictions.md.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Q&A Agent
Goal
Produce useful answers without letting knowledge disappear into chat.
Workflow
- Read
notes/Home.mdornotes/Indexes/Flat_Concept_Index.md, and runsearch_vault.pyprogrammatically. - Classify the query using
notes/Runbooks/Query_Planner.md(one of:lookup,synthesis,contradiction,freshness,code,audit,research). - Execute the required retrieval layers in the order specified for that query class.
- Find the most relevant concept pages and source summaries (capped at reading at most 10 concept pages total).
- Answer from the vault.
- Save the answer memo in
notes/Answers/YYYYMMDDTHHMMSS-topic.mdusing the schema below. - File durable improvements back into concept pages, open questions, contradictions, or TODOs.
Answer Memo Schema
Frontmatter:
title(Human-readable topic title)type: answerasked_at(ISO-8601 date)answer_quality(must be exactlydurableif updating the vault, ormemo-onlyif not)scope(must be exactlysharedfor durable answers, orprivatefor memo-only answers)query_class(must be one of:lookup,synthesis,contradiction,freshness,code,audit,research)sources_consulted(YAML list of everysource_idopened during the session)retrieval_path(YAML list of dictionaries specifying each retrieval step taken; each step must have keys:method,layer,query,results_count)fetch_required(boolean, indicating whether external web fetching was performed/required)tags(must includekb/answer)
Structure:
- Must have a top-level heading (e.g.
# Question/# Answer). - Must have a second-level heading (e.g.
## Summary,## Analysis). - Must have a
## Vault Updatessection.- If
answer_quality: durable, this section must list the exact edits made to concept pages. - If
answer_quality: memo-only, this section must be exactly- None..
- If
Rules
- Prefer vault-grounded answers.
- State uncertainty clearly (e.g., "according to [[Sources/...]]" vs "this is unclear").
- Do not fabricate evidence.
- Every factual claim in the answer must carry an inline wikilink citation:
[[Sources/<source_id>|<source_id>]]or[[Concepts/<name>|<name>]]. If no source supports a claim, mark it(unverified). - For a consequential answer, gate the evidence by stakes: run
consequence-gate --tier <recommendation|decision|autonomous>(optionally--concept <stem>). Do not let blocked, quarantined, or unsupported claims back a high-consequence answer; flag the shortfall in the memo instead.
Write-Back Requirement
The Q&A skill is not complete until at least one write-back path is executed:
- Always: Save the answer memo under
notes/Answers/and ensure quality/scope/updates match. - If new claim found: Append to the relevant concept page's
## Key Claimsand ensure the concept has ≥ 90% direct citation coverage or demote it. - If gap found: Add to the concept page's
## Open Questionsandnotes/TODO.md. - If contradiction found: Add to
notes/Maintenance/Contradictions.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

