agentleFS
Sign inStart free
ianshankianshank/Agents/skills/corpus-guardian/SKILL.md

corpus-guardian

Skill1 starsChanged 59 days agoApache-2.0View on GitHub

Manage, verify, and synchronize the four frozen synthetic evaluation corpora (RCA, Requirements, TestGen, Answer Quality). Use whenever verifying corpus freshness, regenerating frozen synthetic fixtures, or asserting negative control invariants.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Negative Control Carve-Out: Every synthetic corpus must contain intentional negative control items with expected failure verdicts.

    line 17
  2. Very specific:

    All 4 corpora pass --check verification without diff or drift.

    line 35
  3. Distinctive:

    All generators run idempotently with zero unintended git status mutations.

    line 36

≈ “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

Corpus Guardian — Synthetic Evaluation Corpora Management

Unified management and invariant enforcement for the four frozen synthetic evaluation corpora:

  1. RCA Corpus (corpora/rca/v1/ via scripts/gen_rca_corpus.py)
  2. Requirements Corpus (corpora/requirements/v1/ via scripts/gen_requirements_corpus.py)
  3. TestGen Corpus (corpora/testgen/v1/ via scripts/gen_testgen_corpus.py)
  4. Answer Quality Corpus (corpora/answer_quality/v1/ via scripts/gen_answer_quality_corpus.py)

Invariants

  • Negative Control Carve-Out: Every synthetic corpus must contain intentional negative control items with expected failure verdicts.
  • Deterministic Generation: Generators must produce byte-identical output across repeated runs on all platforms (CRLF/LF normalized).
  • Frozen Baseline: Corpora are never hand-edited. Any changes must occur in generator libraries (scripts/_*_corpus_lib.py).

Usage

Verify Freshness Across All Corpora

python skills/corpus-guardian/scripts/corpus_guard.py --check

Regenerate All Synthetic Corpora

python skills/corpus-guardian/scripts/corpus_guard.py --generate

Definition of Done

  • All 4 corpora pass --check verification without diff or drift.
  • All generators run idempotently with zero unintended git status mutations.
  • Fast tier and Tier A mechanical verification pass.

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