Skip to content
cccskills
FreePublished on GitHub

gaia-steward-observe

Observe the repository with every registered Gaia Steward detector and report what each one actually saw, without changing anything. Use for "/gaia-steward-full --observe", "what is Steward seeing", "scan the repo for maintenance debt", or as the first phase of a full Steward run. Distinguishes actively observed, unknown/unavailable and not-evaluated detectors; never treats an unexecuted probe as healthy.

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (1)

  • SKILL.md2.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

gaia-steward-observe

Responsibility

Run the detector fleet once against the checkout head and produce a receipt that says, per detector, whether it observed, could not observe, or was not evaluated. Nothing else.

Input

  • A Git worktree of gaia-skill-tree (the detectors read Git's index, not the filesystem).
  • Optional driver inputs under the ignored .gaia/steward/inputs/: ci-runs.json, advisories.json, test-history.json. Their absence is a not-evaluated state, never an error and never healthy.

Output

gaia steward full run --observe --json
python scripts/check_steward_coverage.py --receipt .gaia/steward/receipts/<run>.json

The receipt (steward-receipt-v1) carries coverageKnown, coverageUnknown, notEvaluated, openDebt and authorityCounts. The checker turns it into a live state per detector: actively-observed only when listed in coverageKnown; everything else is unknown-unavailable.

Authority ceiling

Read-only. Writes only ignored state under .gaia/steward/ and the run record in the Steward ledger. No repair, dispatch, branch or PR.

Stop conditions

  • Any detector in coverageUnknown: report it first and stop treating the run as clean; Class A is blocked for the run.
  • The observation budget in POLICY.yaml is exceeded: stop and report.

Idempotency

Observing the same head twice yields the same debt ids (debt:{kind}:{slug}:{digest}); re-observation updates lastSeen, never duplicates debt.

Failure states

StateMeaning
coverageUnknowna required input was missing, truncated or unreadable
notEvaluatedan optional driver input was not supplied
blocked resultat least one detector was unknown

Validation

python scripts/check_steward_coverage.py
python -m pytest tests/steward/test_controller.py tests/steward/test_coverage_regressions.py -q

Tests

tests/steward/test_controller_resolution.py, tests/steward/test_routine_coverage.py, tests/steward/test_steward_skills.py.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Measure CI churn cost for a pull request: how many commits and how many CI-compute seconds were burned on avoidable "fix the CI" push rounds. Use when you want to understand the efficiency cost of a PR's iteration cycle, get actionable pre-push check suggestions, or include a churn summary in a pipeline report. Triggers: "ci churn", "how much CI did we burn", "avoidable commits", "ci efficiency", "wasted CI time", "churn report", "/ci-churn". Called automatically by /fp-drift at pipeline close.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

Produce the rendered evidence a human-gated frontend PR owes its reviewer: capture each changed surface (plus the before state for anything modified, plus mobile width), then generate one self-contained local HTML page the founder can open and review without checking anything out. Use when a PR is gated by the "Frontend changes are HUMAN-GATED" section of CLAUDE.md, or when the user says "/design-gate", "screenshot evidence for this PR", "prep this for founder review", "build the design evidence page", "what does this look like before and after". The page comes from a template script, not hand-written markup. Output is session-local and never committed. Do NOT use for non-gated changes: typo/grammar/factual fixes in an unchanged block, dead link targets, alt/ARIA fixes with no visual change, cache-bust bumps, or refactors with no rendered diff.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

One-fix-at-a-time, approval-gated design fix recovery. Given a checklist of fixes (handover doc, CHECKLIST.md, or inline list), applies each individually, presents a diff, and waits for an explicit APPROVE / REJECT / NO CHANGES decision before committing. Trigger phrases: /design-iteration, "go through the checklist one by one", "fix these one at a time", "bucket recovery", "design fix pass".

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

Playbook for correcting a named skill's star level to match its computed Trust Magnitude grade, with an independent post-calibration verification pass and a CLI-logged timeline event (never hand-written). Use when: recalibrating a skill's level, fixing a stale or drifted star rating, running a batch of `gaia dev calibrate` corrections, or confirming a past calibration actually landed. Triggers: "calibrate <skill>", "recalibrate the trust magnitude backlog", "promote/demote <skill> to N stars", "why is <skill> still N stars", "verify a calibration actually landed", "Hall of Heroes ranking is wrong".

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

Close out a completed EPIC / sprint end-to-end: author a fact-verified meta-post announcing what shipped, archive the EPIC's handovers, snapshot orchestrator memory, gate the integration→main merge on CI-green + explicit human go, drive the version bump (merge-commit conventions that auto-sync classifies), and verify the release reached the registry/PyPI. Use when the user says "close out EPIC <n>", "wrap up the sprint", "ship the meta shift", "/epic-close", or asks to finalize an integration branch that is ready to merge to main. Generalizes the EPIC 1002 (Yggdrasil II) close-out. This skill orchestrates — it authors founder docs directly (superadmin) and delegates code/regen to workers; it NEVER merges to main without the human gate.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

Run this skill for Phase 3 of the evidence verification pipeline — the adversarial audit step. Use when you need to check the evidence data lake for bad data before ingestion: dead links, wrong URL formats (tree/ vs blob/), subjective wording ("elite", "high-quality"), stale migration notes, benchmark catalog misuse/vendor-claim leakage, or skills whose star evidence conflicts with classified evidence level. Triggers on phrases like: "audit the data lake", "adversarial check", "ev-adversarial-audit", "check for noise in evidence", "flag bad evidence", "run the audit phase", "quality check the by-type files", or any reference to Phase 3 of the pipeline.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

See all skills by gaia-research

Report a problem with this skill