agentleFS
Sign inStart free
MasRamaMasRama/peka/skills/audit/SKILL.md

audit

Skill1 starsChanged 29 days agoMITView on GitHub

Check PEKA's store for knowledge in the wrong place (procedures saved as memories, facts saved as skills, skills saved outside PEKA, project-specific items without a project tag), then fix what the user approves. Use for /peka:audit and /peka:audit adopt <skill>.

  • Reads credentials

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delight, teach-impeccable and 10 more.

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.
  • HK-hubSkill

    delight

    Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

    Also in 32 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • SkillPilotCHSkill

    level-up

    Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.

    Also in 12 projects that use this

  • ww-w-aiSkill

    pm-discovery

    PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.

    Also in 3 projects that use this

  • +7 more from HK-hub

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" adopt <skill> and report the result.

    line 18
  2. Very specific:

    Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" audit.

    line 26
  3. Very specific:

    Leave out skills in ~/.claude/skills that look like the user's own hand-made ones unless they ask.

    line 40
  4. Distinctive:

    Ask which fixes to apply. Then:

    line 42
  5. Very specific:

    Conversions and project tags: run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" learn --session "${CLAUDE_SESSION_ID}" --mode decide and …

    line 43
  6. Very specific:

    Adoptions: run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" adopt <skill> for each one approved.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 175 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Audit PEKA

Arguments: $ARGUMENTS

adopt <skill>

Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" adopt <skill> and report the result. Adopting moves a skill folder from ~/.claude/skills into PEKA and links it back, so it keeps working while gaining history and /peka:status. Adopted skills are pinned, so the curator never archives them; /peka:status unpin <skill> hands them over fully. Folders with a .git, node_modules, or .env are refused; pass that reason on.

Otherwise: full audit

  1. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" audit. If it says there is nothing to fix, tell the user and stop.
  2. The script finds candidates by shape; you judge them. For each candidate in the "procedures" and "plain facts" sections, open it with node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" show <name> and decide whether it is really in the wrong place. For each item in the "project tag" section, check that it really applies to that project only; a general preference that merely mentions a project stays global.
  3. Show the user one short list of proposed fixes, for example:
    • deploy-howto: memory → skill (it is a 5-step procedure)
    • api-port: skill → memory (it is a single fact)
    • deploy-staging in ~/.claude/skills: adopt into PEKA (looks learned, not hand-made)
    • abq-billing: tag with project abqary-new (it is about that project only) Leave out skills in ~/.claude/skills that look like the user's own hand-made ones unless they ask; adopting is their call.
  4. Ask which fixes to apply. Then:
    • Conversions and project tags: run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" learn --session "${CLAUDE_SESSION_ID}" --mode decide and launch peka:learner as it says, with a Request: that lists each approved fix precisely (for example "convert memory deploy-howto into a skill and retire the memory; set metadata.project: abqary-new on memory abq-billing").
    • Adoptions: run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" adopt <skill> for each one approved.
    • Skills flagged as able to run commands: show them to the user; change nothing unless asked.
  5. Finish with one line per change made.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free