agentleFS
Sign inStart free
AgriciDanielAgriciDaniel/anti-slop/anti-slop-brain/SKILL.md

anti-slop-brain

Skill51 starsChanged 4 months agoApache-2.0View on GitHub

Scaffold and operate Anti-Slop Brain, a source-cited Obsidian brain for detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection. Use when the user says "anti-slop-brain", "Anti-Slop Brain", "create a detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection brain", "import sources", "synthesize plan", "render report", or wants a persistent vault-backed operating system for detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never store credentials in the vault.

    line 51
  2. Distinctive:

    Never make domain-specific claims without dated trustworthy sources.

    line 52
  3. Very specific:

    Keep hot, index, overview, and log current.

    line 53
  4. Distinctive:

    No authorship verdict, ever.

    line 69
  5. Distinctive:

    No hard failure on a stylistic marker alone.

    line 70
  6. Distinctive:

    No claim about detector accuracy, marker frequency, or prevalence without a current cited source

    line 71
  7. Distinctive:

    No credentials, tokens, or private operator content in repo artifacts

    line 72
  8. Distinctive:

    No model self-grading as a release gate.

    line 73
  9. Very specific:

    Do not call this brain market-ready unless scripts/audit_brain.py --require market-ready passes.

    line 75

≈ “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-Slop Brain

Operate the deployed vault first. Treat CODEX.md, wiki/hot.md, and wiki/index.md as vault-root-relative paths, where the vault root is the directory passed to --vault or opened in Obsidian. In this repo, the template vault root is assets/template-brain/ and the demo vault root is examples/sample-vault/.

Secretary: use agents/anti-slop-secretary.md for grounded answers, claim review, and vault maintenance. That secretary reads the brain first, cites a vault note and an official URL, and stays advisory and read-only.

Commands

/anti-slop-brain new <client-slug> --owner <name>
/anti-slop-brain ingest --vault <path> --file <source>
/anti-slop-brain synthesize --vault <path>
/anti-slop-brain report --vault <path>
/anti-slop-brain visuals --vault <path>
/anti-slop-brain lint --vault <path>
/anti-slop-brain next --vault <path>

Source checkout equivalent:

anti-slop-brain new <client-slug> --owner <name>
anti-slop-brain ingest --vault <path> --file <source>
anti-slop-brain synthesize --vault <path>
anti-slop-brain report --vault <path> --html-only

Required Operating Rules

  1. Read <vault>/CODEX.md.
  2. Read <vault>/wiki/hot.md.
  3. Read <vault>/wiki/index.md.
  4. Preserve .raw/ as immutable source material.
  5. Never store credentials in the vault.
  6. Never make domain-specific claims without dated trustworthy sources.
  7. Keep hot, index, overview, and log current.
  8. Record research evidence in references/source-ledger.json.
  9. Record domain adapter completion in references/adapter-manifest.json.

Script Mapping

  • new -> python scripts/scaffold_vault.py
  • ingest -> python scripts/ingest_source.py
  • synthesize -> python scripts/synthesize_brain.py
  • report -> python scripts/render_brain_report.py
  • visuals -> python scripts/generate_vault_visuals.py
  • lint -> python scripts/lint_vault.py
  • next -> python scripts/guide_next_action.py

Quality Gates

  • No authorship verdict, ever; this brain reports defects, not origin
  • No hard failure on a stylistic marker alone; markers route to structural tests
  • No claim about detector accuracy, marker frequency, or prevalence without a current cited source
  • No credentials, tokens, or private operator content in repo artifacts
  • No model self-grading as a release gate; deterministic scanners re-run after every repair

Do not call this brain market-ready unless scripts/audit_brain.py --require market-ready passes. A scaffold is not a finished brain.

Research Refresh

30 days for model-specific marker cohorts and detector claims; 90 days for corpus studies and regulation; before every release for any numeric claim

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