本文へ移動
cccskills
無料GitHub で公開

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.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.9 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

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.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

ci-churn

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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".

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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".

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

gaia-research のスキルをすべて見る

このスキルの問題を報告する