본문으로 건너뛰기
cccskills
무료GitHub에 공개

gaia-trace-timeline

Audit and repair Gaia user-tree timelines so every skill's current rank is explained by a chain of Hero's Journey events. Trigger this skill when: a contributor's profile chart shows a stale rank (e.g. still shows 3★ after a demotion to 1★); someone asks to "trace what happened" to a skill's rank; `validate_timelines.py` is failing in CI; you need to backfill missing `demote` or `rank_up` events before cutting a release; a skill was reclassified or Star-Bar-reset and the user tree was never updated; or any time the registry node and user tree disagree on a skill's current level. Uses `scripts/trace_timeline.py` (dry-run + apply) and `scripts/validate_timelines.py` (CI gate). Do NOT hand-edit `timeline[]` arrays — the script synthesises properly labelled events with `previousValue`/`newValue` so the rank chart plots correctly.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md4.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

gaia-trace-timeline

The profile Hero's Journey (rank chart + event list) is rendered from the contributor's user tree (skill-trees/<owner>/skill-tree.json) — its timeline[] and unlockedSkills[]. Rank changes are typically applied to the registry node (registry/named/<handle>/<skill>.md) via gaia dev calibrate / reclassify, but that change is never automatically mirrored into the user tree. The result: a skill silently charts at its old rank — a 3★→1★ demotion that looks like it never happened.

This skill finds that drift and backfills the missing events so each timeline explains the current rank.

Workflow

1. Find the drift

The CI gate is the authoritative source of disagreements:

python scripts/validate_timelines.py

It lists every owned named skill whose unlockedSkills level or latest level-bearing timeline event disagrees with the current registry level in registry/named-skills.json. Run this first — it gives you the complete work list so you do not miss any drifting skill.

2. Trace one skill (dry-run)

Before writing anything, inspect what events would be appended:

python scripts/trace_timeline.py <handle>/<slug>

The output labels each event (from registry node) when the .md records the level change, or (reconciled) when no source event exists anywhere (an undocumented registry-side recalibration). The reconciled case synthesises a clearly labelled event dated just after the skill's latest existing event — it does not invent history, it documents the gap honestly.

3. Apply

Set GAIA_OPERATOR_OVERRIDE=1 so the mutating script clears the Verifier auth gate (required in CI and any non-Verifier environment):

# Single skill
GAIA_OPERATOR_OVERRIDE=1 python scripts/trace_timeline.py <handle>/<slug> --apply

# All drifting skills at once
GAIA_OPERATOR_OVERRIDE=1 python scripts/trace_timeline.py --all --apply

Prefer trace_timeline.py over the raw CLI for level changes — the script fills previousValue/newValue on each event so the rank chart plots correctly. The CLI equivalent (gaia dev timeline ... --action demote) omits those fields and produces a flat event line in the chart.

Use the raw CLI only for a one-off hand-authored note:

gaia dev timeline <handle>/<slug> --user <owner> --action demote \
  --timestamp 2026-06-02T23:48:18Z --notes "Star-Bar hard reset (META §2.4): …"

4. Regenerate and verify

GAIA_OPERATOR_OVERRIDE=1 gaia dev docs   # regenerate profiles/charts
python scripts/validate_timelines.py        # must print ✓ for all skills

Before committing, discard timestamp-only churn in generated artifacts:

git checkout HEAD -- registry/gaia.json docs/graph/gaia.json \
  registry/gaia.gexf docs/css/tokens.css

These files get touched by gaia dev docs even when the content is unchanged — staging them inflates the diff and trips unrelated CI guards.

Finding the reason for a demotion note

An accurate event note prevents future confusion. Cross-reference git history — demotions usually arrive in a sweep commit:

git log --oneline -- registry/named/<handle>/<slug>.md
git log --oneline --all | grep -iE "demot|star-bar|calibrat|reclassif"

Common causes and the META reference to cite in the note:

CauseNote text
Star-Bar hard resetStar-Bar hard reset (META §2.4): no verified blob link
ReclassificationType change (Unique→Basic) caps max rank
Evidence rot / dead linkBroken evidence demerit — link no longer resolves

Guardrails

  • Only audit a contributor's own named skills — the ones whose history their profile presents. Do not touch other users' trees.
  • Never hand-edit timeline[] to fabricate ranks. Always route through trace_timeline.py so events carry the correct shape and levelHistory is rebuilt from the full event run.
  • The registry .md timeline is the authoritative source the script reads; keep it and the user tree consistent.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

ci-churn

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gaia-research/gaia-skill-tree232026년 10월 23일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gaia-research/gaia-skill-tree232026년 10월 23일 업데이트

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".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gaia-research/gaia-skill-tree232026년 10월 23일 업데이트

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".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gaia-research/gaia-skill-tree232026년 10월 23일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gaia-research/gaia-skill-tree232026년 10월 23일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gaia-research/gaia-skill-tree232026년 10월 23일 업데이트

gaia-research의 스킬 모두 보기

이 스킬의 문제 신고