agentleFS
Sign inStart free
CodeAlive-AICodeAlive-AI/ceo-ai-os/skills/anti-pattern-audit/SKILL.md

anti-pattern-audit

Skill9 starsChanged 6 months agoMITView on GitHub

Monthly self-deception audit — 25 anti-patterns from CEO Bible Section M

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read daily logs and weekly reviews for the past month

    line 13
  2. Distinctive:

    Read MEMORY.md — current state

    line 14
  3. Distinctive:

    Check each block of anti-patterns

    line 15
  4. Distinctive:

    Follow output preferences from USER.md (language, format, platform constraints).

    line 79
  5. Distinctive:

    Use concrete data: "this week 2 conversations out of 8-12 target"

    line 84
  6. Distinctive:

    Don't sugar-coat or soften

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Anti-Pattern Audit

Monthly self-deception check. Based on CEO Bible Section M.

Process

  1. Read daily logs and weekly reviews for the past month
  2. Read MEMORY.md — current state
  3. Check each block of anti-patterns
  4. Score: 0 (not observed), 1 (mild risk), 2 (active problem)
  5. Total score > 8 = serious conversation needed

Block 1: General Founder-CEO Mistakes

  1. Too many wedges at once — is there diluted signal?
  2. Confusing early revenue with repeatability — a few sales != PMF
  3. Letting early customers dictate roadmap — building a services company?
  4. Scaling GTM before retention/onboarding stable — water into leaky bucket?
  5. Treating fundraising as validation — investor interest != customer truth

Block 2: Ex-Engineer Founder Mistakes

  1. Hiding in product — what % of time does the founder spend in code vs with customers?
  2. "Product should speak for itself" — markets don't decode architecture
  3. Leading with features, not pain — buyers buy changed outcomes
  4. Building platform before earning wedge — breadth is tax on learning
  5. Delegating sales/positioning too early — losing best signal stream

Block 3: Metric Interpretation Mistakes

  1. Aggregate dashboards vs cohort/segment cuts
  2. Calling pilots "ARR"
  3. Signed contracts = retention proof when engagement dead
  4. Optimizing traffic before activation/TTFV
  5. Counting shipped experiments vs changed beliefs

Block 4: Growth Mistakes Before PMF

  1. Many channels before one message lands
  2. Paid acquisition to compensate poor positioning
  3. Outbound with no proof, no content, no trust
  4. B2C DAU as success when B2B conversion weak
  5. Hiring marketer to find PMF

Block 5: AI-Era Specific Mistakes

  1. Demo excitement != durable value
  2. Selling "AI" instead of measurable business result
  3. Ignoring trust/evals/data handling until procurement
  4. Pricing ignoring compute/HITL costs -> negative-margin growth
  5. AI summaries replacing direct founder contact -> synthetic certainty

Output Format

Anti-Pattern Audit — [Month YYYY]

Score: X/50

Critical (score 2):
- #N: [description] — [evidence from this month]

Watch (score 1):
- #N: [description] — [early signs]

Clean:
- [list of areas with no issues]

Recommendation:
[Top 3 actions to address critical patterns]

Follow output preferences from USER.md (language, format, platform constraints).

Rules

  • Be honest. If the founder is hiding in code — say it directly.
  • Use concrete data: "this week 2 conversations out of 8-12 target"
  • Don't sugar-coat or soften
  • Log the result to memory/YYYY-MM-DD.md

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