本文へ移動
cccskills
無料GitHub で公開

honesty-mode

Toggle the badges-page Honesty Mode build-time flag on or off. ON makes the README badge generator emit direct /badges/_assets/<handle>/<file>.svg URLs (no Cloudflare Worker, no ?repo= validation). OFF restores worker-validated URLs. Use when the user says "/honesty-mode on", "/honesty-mode off", "turn honesty mode on/off", or asks for the current honesty-mode state.

gaia-research/gaia-skill-tree
インストール方法を見る

含まれるファイル（1）

  • SKILL.md4.4 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。

honesty-mode

Flip the HONESTY_MODE build-time constant in docs/badges/index.html and document the flip. There is no runtime UI for this flag — the on-page pill is read-only — so changing it always means editing the source.

What the flag controls

In docs/badges/index.html (script block near the top):

const HONESTY_MODE = true;   // or false
ValueCopied-markdown URLWhere it works
true (default backup)https://gaiaskilltree.com/badges/_assets/<handle>/<file>.svgAnywhere — bypasses worker, no ?repo=
falsehttps://gaiaskilltree.com/badges/<handle>/<file>.svg?repo=<repo>Only when the Cloudflare Worker is deployed and run_worker_first = true

When the user says /honesty-mode on, set the constant to true. When they say /honesty-mode off, set it to false. When they ask for status without an argument, just report the current value — don't edit.

Workflow

  1. Parse the argument. Accept on, off, true, false, enable, disable (case-insensitive). If the argument is missing or just status, report the current value of HONESTY_MODE from docs/badges/index.html and stop.

  2. Read the current value. Grep for const HONESTY_MODE = in docs/badges/index.html. If the line is missing, surface that and stop — the flag may have been ripped out per the removal plan in docs/badges/CLAUDE.md.

  3. No-op check. If the requested state already matches, say so and stop. Don't open a PR for a no-op edit.

  4. Edit the constant. Use Edit to change const HONESTY_MODE = true; ↔ const HONESTY_MODE = false;. Touch nothing else in the file — the indicator paint, badgeMarkdownUrl(), and detection logic all read from this single constant.

  5. Verify the chip painting still matches. Sanity-check that the indicator-paint lines (honestyPill.dataset.state = HONESTY_MODE ? "on" : "off" and the .bd-honesty-state text) are still present and read from the constant. If they've drifted, fix them in the same edit.

  6. Don't run gaia dev docs. This flag only affects docs/badges/index.html — none of the generated artifacts (registry/gaia.json, docs/graph/, tree.md) depend on it. A rebuild is unnecessary noise.

Branch + PR convention

Per CLAUDE.md § Branch Naming, this is a design/ change (website behavior, docs/ HTML/CSS/JS).

  1. Branch. git checkout -b design/honesty-mode-{on,off} from the current branch (or main if the user asks for a clean branch). Don't push to main.

  2. Commit. Single commit, message:

    design(badges): set HONESTY_MODE = {true|false} [skip-gen]

    Include [skip-gen] so the Regenerate and Commit Artifacts workflow doesn't loop on this — there's nothing to regenerate.

  3. Push and open PR. git push -u origin <branch> then gh pr create with a body that:

    • States the new value (HONESTY_MODE = true / false).
    • Explains the practical effect (which URL shape lands in the user's clipboard).
    • Links to docs/badges/CLAUDE.md for the full rationale.
    • Does NOT mark the PR as ready-to-merge if turning OFF — call out the worker-deployed prerequisite from docs/badges/CLAUDE.md § "When to flip Honesty Mode OFF".

  4. Report PR URL back to the user. Don't merge.

Anti-patterns

  • Don't add a runtime toggle back. The whole point of this flag being build-time is that "the URL you see copied is the URL everyone else gets." See docs/badges/CLAUDE.md § "Why no runtime/localStorage toggle?".
  • Don't touch _assets/ detection or local previews. Those always read from _assets/ regardless of mode — that's how the page renders before the worker runs. Honesty Mode only swaps the copied markdown URL.
  • Don't bump versions. This change touches one HTML file's script constant; the three-file version lockstep (pyproject / cli-npm / gaia.json) doesn't apply.
  • Don't edit worker/index.js. The worker stays as-is — Honesty Mode just routes around it for embedded badges.

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。

ログインしてレビューを書く

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

design-gate

無料

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

design-iteration

無料

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

dev-calibrate

無料

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

epic-close

無料

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

ev-adversarial-audit

無料

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