agentleFS
stellar-experimentalstellar-experimental/stellar-raven/.agents/skills/retrieval-system-audit/SKILL.md

retrieval-system-audit

Skill17 starsChanged 2 days agoApache-2.0View on GitHub

Audit and improve stellar-raven-codemode retrieval across every exposed service operation and skill. Use for comprehensive endpoint, response-shape, catalog-description, search-ranking, execute-grounding, evaluation-coverage, golden-truth, or cross-source weighting reviews that require live probes and measured A/B evidence.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep data, soft-empty, and error responses distinct.

    line 26
  2. Distinctive:

    Keep secrets and service traffic outside model-authored code.

    line 27
  3. Distinctive:

    Never call a paid or side-effecting operation during inventory work.

    line 28
  4. Distinctive:

    Never tune production behavior for one question.

    line 29
  5. Distinctive:

    Prefer deletion, simpler descriptions, and existing interfaces to new code.

    line 30
  6. Very specific:

    Trace retrieval decisions: Follow search from catalog generation through scoring, tiering, quotas, descriptions, profiles, and recovery …

    line 48
  7. Distinctive:

    Implement the smallest proven change: Keep measurement changes separate from product changes, with disjoint write ownership.

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Retrieval system audit

Measure the retrieval system before changing it. Ship only general improvements that survive real endpoint calls and reviewed golden questions.

Scope first

A full audit is the largest task in this repo. Before you start, write in the round ledger the question the audit answers, the surfaces and steps below that it needs, and the expected time and cost. Run only those steps. Probes and offline instruments are free and run here against the local dev server; every paid run follows the run-evals spend rule. Stop when the question is answered.

Companion skills: run-evals for every evaluation and spend decision, golden-truth before any golden change, improvements-pipeline for verified upstream defects, and live-drift-resolution first when the committed catalog differs from the live surfaces. Read PLAN.md, ARCHITECTURE.md, eval/EVALS.md, and eval/qa/README.md for the parts in scope.

Fixed boundaries

  • The manifest is the exposed surface. Keep exact operation and skill IDs.
  • Keep data, soft-empty, and error responses distinct.
  • Keep secrets and service traffic outside model-authored code.
  • Never call a paid or side-effecting operation during inventory work.
  • Never tune production behavior for one question.
  • Prefer deletion, simpler descriptions, and existing interfaces to new code.
  • Raw paid results stay local and gitignored.
  • The coordinator holds Git, spending, deployment, and external filing authority.

Steps

  1. Pin. Work in a dedicated worktree with a round ledger. Record the revision and the manifest, runner, and corpus digests. Run the free baseline from AGENTS.md and confirm that regeneration leaves the tree clean.
  2. Build one surface ledger. For each operation and skill in scope, compare the committed manifest, generated spec, adapters, live catalog, and fresh-client MCP descriptions. Use the fields in references/evidence-contract.md. Separate deployed drift from a client that cached an older MCP schema.
  3. Probe live response contracts. Design the probe matrix first and mark every probe read-only, paid, side-effecting, secret-bearing, or unsafe. Call each safe read-only operation with a representative input, then add bounded soft-empty and invalid-input probes by response class. Compare returned keys and nested shapes with the model-visible schema. Keep hashes and compact projections, not raw bodies.
  4. Trace retrieval decisions. Follow search from catalog generation through scoring, tiering, quotas, descriptions, profiles, and recovery guidance. Follow execute through adapters, envelopes, truncation, artifacts, and evidence packing. For each suspected defect, name the first failed boundary: discovery, schema, retrieval, execution, upstream data, synthesis, judge, or golden truth. When the evidence is absent upstream, file a finding and make no runtime change.
  5. Audit evaluation coverage. Map each operation and skill to its routing, holdout, discovery, plan, QA, live, temporal, and agentic coverage. Separate direct case labels from operations that agents called. Review every consequential verdict change against the transcript and golden. Claim no gain below the documented noise floor, and compare different memberships only on common cases.
  6. Pre-register each experiment. One hypothesis per candidate: mechanism, target cases, symmetric controls, one mechanism metric, expected time and cost, hard cap, stop rule, and acceptance threshold. Size the controls to the decision, and state and justify their coverage before any outcome is read. Use identical case IDs, runner code, judge tuple, and arm order across arms. Collect answers before judging when the runner supports it.
  7. Implement the smallest proven change. Keep measurement changes separate from product changes, with disjoint write ownership. Use generation scripts. Remove rejected experimental code and dormant flags. Advance a candidate only after two unrelated targets show the intended mechanism. Stop after a verified control, security, exposure, or exact-match regression.
  8. Close. Goldens change only through golden-truth; service defects go to improvements/, never behind a local answer patch. A reviewer who did not author the change reviews it, and every finding is reconciled. Run the tests, smoke tests, build, routing gate, relevant evals, improvements lint, and secret scan that the change touches. Record artifacts, costs, failures, and rejected hypotheses. Stop only the lanes you started.

Evidence rule

An aggregate score never overrides a blocking regression. A shipped change needs reviewed correctness, causal evidence, stable retrieval, complete accounting, and no security or exposure regression. Cost counts as run-evals states: a much cheaper path that is only slightly less correct can be the better product.

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.