agentleFS
ARCASSystemsARCASSystems/FounderOS/skills/audit/SKILL.md

audit

Skill7 starsChanged 19 days agoMITView on GitHub

Audit the OS in one composite report. Say "audit the OS", "check OS health", "full audit", or "is the OS healthy" (or run /founder-os:audit). Runs readiness, lint, wiki graph state, brain staleness, and voice completeness together. Read-only.

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

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 3

    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:

    If core/identity.md does not exist, stop with: Founder OS not set up here.

    line 18
  2. Distinctive:

    Run all five checks. Sequential by default.

    line 22
  3. Very specific:

    readiness-check: - read skills/readiness-check/SKILL.md and apply.

    line 30
  4. Very specific:

    lint: - read skills/lint/SKILL.md and apply.

    line 31
  5. Very specific:

    wiki-build state: - read brain/relations.yaml and report counts of curated edges and auto-generated wikilinks.

    line 32
  6. Very specific:

    Voice completeness: - check whether core/voice-profile.yml and core/brand-profile.yml exist and have been filled past their template …

    line 34
  7. Distinctive:

    If the user says no, read the existing graph and mark wiki freshness as not refreshed.

    line 42
  8. Distinctive:

    Read-only unless the user approves wiki-build.

    line 84

“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

Runs on: reasoning - reads your files and reasons; any capable agent can run this.

This skill returns one Founder OS health report. It composes five checks that can also run on their own.

Pre-Flight

If core/identity.md does not exist, stop with: Founder OS not set up here. Run /founder-os:setup first.

Checks

Run all five checks. Sequential by default; parallel only if explicitly available.

Parallel path (preferred when the Agent tool is exposed in this Claude Code build): dispatch five sub-agents in a single message, one per check, each with a focused prompt that names the check and the expected output shape. Then merge the five results into the composite block.

Sequential path (fallback - applies if the Agent tool is not available, if a sub-agent fails, or if you are unsure): read skills/<check>/SKILL.md for each of the five checks below and apply its logic inline against the live OS. Mark the report parallel: unavailable.

For checks 4 and 5 there is no separate skill file - apply the rules below inline regardless of path.

  1. readiness-check - read skills/readiness-check/SKILL.md and apply. Returns score and next 3 moves.
  2. lint - read skills/lint/SKILL.md and apply. Returns broken links, orphans, stale content, provenance gaps, possible contradictions.
  3. wiki-build state - read brain/relations.yaml and report counts of curated edges and auto-generated wikilinks. Do NOT run wiki-build itself unless the user has approved the write at the gate above. If brain/relations.yaml does not exist, return wiki: not initialised - run /founder-os:wiki-build to create it.
  4. Brain staleness - count entries past Decay after, flags older than Week 3, and rants in brain/rants/ older than 30 days where processed: false.
  5. Voice completeness - check whether core/voice-profile.yml and core/brand-profile.yml exist and have been filled past their template defaults.

Wiki Write Gate

Audit is read-only by default. wiki-build writes to brain/relations.yaml, so ask before running it:

Audit can refresh the wiki graph before scoring. This writes only to brain/relations.yaml. Run wiki-build first? yes / no

If the user says no, read the existing graph and mark wiki freshness as not refreshed.

Composite Output

Render only the composite report. Do not paste raw sub-check outputs.

FOUNDER OS HEALTH - <YYYY-MM-DD>
---
Readiness: <score>/100 - <one-line headline>
Wiki: <links count>, <orphans count>, <broken refs count>
Brain: <decay-due count>, <Week 3+ flags>, <stale rants>
Voice: <state>
Parallel: available | unavailable
---
Top 3 actions to lift health:
1. <action>
2. <action>
3. <action>

Brain Staleness Rules

  • Decay after: date in the past counts as decay-due.
  • Any flag marked Week 3, Week 3+, or older than 21 days counts as Week 3+.
  • Any file in brain/rants/ older than 30 days with processed: false counts as stale.

Voice Completeness Rules

Voice is incomplete if:

  • core/voice-profile.yml is missing.
  • It still contains placeholder brackets or template examples.
  • It has fewer than 2 writing samples referenced.

Brand is incomplete if:

  • core/brand-profile.yml is missing.
  • Colors, fonts, logo, or document style are still blank placeholders.

Rules

  • Read-only unless the user approves wiki-build.
  • The composite report is the only output.
<!-- private-tag: not applicable: audit reads and reports; any brain/ reference is to files being read, not user-speech writes -->

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.