원클릭으로 Manus에서 모든 스킬 실행

trust-appraise-all

스타16

포크8

업데이트2026년 7월 2일 18:04

Use this skill when the user wants the full existing-registry Trust Magnitude inspector: understand why a named Gaia skill has a particular star rank, what its Trust Magnitude (TM) score is, which evidence rows are contributing (or dead), how far it is from the next grade, or what evidence to add to move the needle. Also use when asked for a full leaderboard of all named skills ranked by TM. Triggers: "why does X have 3 stars", "what's the TM for X", "inspect TM", "explain the score for X", "what evidence would rank up X", "show leaderboard", "rank all skills by TM", "what's dragging down X's score", "dead evidence rows", "how close is X to grade A/S".

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

gaia-research

gaia-research/gaia-skill-tree

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

/trust-appraise-all

Breaks down the Trust Magnitude (TM) score for any named Gaia skill, or produces a full ranked leaderboard. TM is the composite evidence score that gates star promotions — understanding it tells you exactly why a skill is ranked where it is and what would change that.

Two Modes

Inspect Mode — single skill deep-dive

/trust-appraise-all <skillId>

<skillId> is the contributor/name path (e.g. garrytan/gstack, mattpocock/grill-me, obra/superpowers).

Output includes:

Each evidence row with the full score chain: base magnitude → × type weight → × freshness → × mothership/creator/engagement → × inheritMultiplier → × plateau → final score
Dead rows (score = 0.0) and why (missing views, stars below threshold, deranked verifier, etc.)
Fusion-recipe summary if suiteComponents is present: component count, graded origins, raw fusion magnitude
Total TM, overall grade, and exact points to the next grade threshold
Most efficient evidence type to add for the next TM jump

Leaderboard Mode — all skills ranked

/trust-appraise-all --leaderboard

Full ranked table grouped by grade band:

Band	TM Threshold
S	>= 250
A	>= 100
B	>= 50
C	>= 20
Ungraded	< 20

Columns: Rank, Skill ID, TM, Grade, Level, Contributor.

How to Run It

# Inspect a single skill
GAIA_OPERATOR_OVERRIDE=1 python scripts/inspectTrustMagnitude.py --skill <skillId>

# Full leaderboard
GAIA_OPERATOR_OVERRIDE=1 python scripts/inspectTrustMagnitude.py --leaderboard

The script loads named skills from registry/named/, resolves fusion recipes from registry/nodes/, and calls explainTrustMagnitude() in src/gaia_cli/trustMagnitude.py.

Agent Instructions

For /trust-appraise-all <skillId>:

Run the inspect command for the requested skill.
Present a concise table of evidence rows: type, source, and final score. Group live rows above dead rows.
Call out dead rows and explain the specific reason each one contributes 0 (e.g. "social-signal: 820 views — below 1k floor").
State the next-grade gap plainly: "needs X more TM to reach grade Y (currently Z)".
Recommend the single highest-impact evidence type to add, with reasoning (e.g. "one peer-review with 3 reviewers adds ~90 TM — more than doubling current score").

For /trust-appraise-all --leaderboard:

Run the leaderboard command.
Present the output grouped by grade band.
Flag any skills with many evidence rows but low TM — dead rows are likely culprits worth a follow-up inspect.

Trust Magnitude Formula Reference

artifact_score = magnitude × type_weight × freshness × mothership × creator × engagement
TM = Σ(artifact_scores), with social-signal capped at 80 across all rows

Per-type magnitude formulas

Type	Magnitude Formula	Weight	Cap
fusion-recipe	20×N (N≤10); 200+20√(N-10) (N>10)	1.5	—
github-stars-own	stars / 1000	1.0	200
proxy-containment	(externalStars/1000)×0.8 (min 10k stars)	1.0	160
verifier-attestation	30 × verifiers	1.5	—
benchmark-result	percentile (field required — omitting it scores 0)	1.4	100
arxiv	citations / 5	1.0	100
peer-review	25 × reviewers	1.2	—
repo-own	commits/200 + contributors²×2	0.6	60
self-attestation	10	0.5	10
social-signal	log10(views)×8 (min 1k views)	1.0	80 (sum cap)

Grade thresholds

Grade	TM Floor	Additional Gates
S	250	distinctTypes >= 3 AND has non-self-producible evidence
A	100	—
B	50	—
C	20	—
Ungraded	< 20	—

Common dead-row causes to watch for

social-signal with views < 1000 → scores 0 regardless of type weight
github-stars-own and repo-own pointing to the same URL → deduped; only the higher score counts
benchmark-result missing percentile field → magnitude = 0
Large suite with github-stars-own at the repo root → per-skill contribution tiny due to / skill_count_in_repo divisor; use social-signal or peer-review instead

이 저장소의 다른 Skills

같은 저장소

gaia-release

gaia-research/gaia-skill-tree

Helper for release operations, compilation of changelogs between tags, version lockstep syncing, and promotion of GitHub releases from canary/pre-release to latest/production. Use when the user asks to "compile the changelog", "promote release to latest", "tag a release", or do version release operations.

2026-07-1616

gaia-research/gaia-skill-tree

Push committed changes and create a draft PR on GitHub. Use when you have staged changes ready to push and want to open a draft PR for early feedback or documentation.

2026-07-1516

trust-methodology-consult

gaia-research/gaia-skill-tree

Consult this skill BEFORE proposing a fix to any CLI gap or schema gap that touches evidence, trust magnitude, evidence types, evidence grades, the TM formula, or star-level promotion gates. Also read it whenever an issue mentions citations, stars, commits, contributors, views, reviewers, percentile, arxiv, github-stars-own, repo-own, social-signal, benchmark-result, peer-review, self-attestation, fusion-recipe, verifier-attestation, or proxy-containment — those are the 10 canonical evidence types and the raw inputs that feed their formulas. Also read it when asked whether a skill qualifies for a given star level (0★–6★): the Star Bar and promotion gates live in `META.md`, not in the TM methodology page. Reading both prevents proposing a calibration that satisfies the TM grade threshold but violates a Star Bar installability or link requirement.

2026-07-1316

ev-link-validation

gaia-research/gaia-skill-tree

Phase 4 of the Gaia evidence verification pipeline. Checks every URL in the evidence data lake for HTTP liveness — catches dead links (404, 403, timeout, connection errors) before evidence is ingested into the registry. Use this skill when: running the full /ev-pipeline, asked to "validate links", "check evidence URLs", "run link validation", "find dead links in the data lake", "check HTTP status of evidence sources", or "verify evidence links still work". Also useful standalone when you suspect evidence sources have gone stale after a long gap between pipeline runs. Wraps validate_sources.py, which uses Firecrawl CLI to scrape each unique URL and records pass/fail status in a markdown report. Requires Firecrawl CLI to be installed and authenticated.

2026-07-1316

ev-pipeline

gaia-research/gaia-skill-tree

Top-level orchestrator for the Gaia Registry evidence verification pipeline. Run this when you want to do a full evidence pass — collecting raw sources, verifying live GitHub star counts, adversarially auditing for quality/formatting issues, and checking that every URL is reachable — all in one coordinated sequence. Trigger phrases: "run the evidence pipeline", "full evidence pass", "verify evidence", "evidence verification pipeline", "run ev-pipeline", "check all evidence", "audit the data lake", "evidence quality sweep", "refresh evidence", "validate evidence sources". Also aliased as /evidence-verification-pipeline. Use the individual sub-skills (ev-collection, ev-star-verification, ev-adversarial-audit, ev-link-validation) only when you need to re-run one phase in isolation; for end-to-end work, always start here.

2026-07-1316

evidence-verification-pipeline

gaia-research/gaia-skill-tree

Canonical entry point for the full Gaia evidence verification pipeline. Invoke as /evidence-verification-pipeline or /ev-pipeline — both names trigger this skill. Use whenever you need to run all four evidence phases end-to-end: collecting raw evidence from the data lake, verifying live GitHub star counts, running adversarial auditing for noise and URL errors, and checking link health via Firecrawl. Also use when someone says "run the evidence pipeline", "verify the evidence lake", "audit evidence", "run ev-pipeline", "full evidence check", "pipeline run", "prepare evidence for ingestion", or "refresh the data lake". This is the pre-ingestion step — run it before importing any evidence into the registry.

2026-07-1316

name	trust-appraise-all
description	Use this skill when the user wants the full existing-registry Trust Magnitude inspector: understand why a named Gaia skill has a particular star rank, what its Trust Magnitude (TM) score is, which evidence rows are contributing (or dead), how far it is from the next grade, or what evidence to add to move the needle. Also use when asked for a full leaderboard of all named skills ranked by TM. Triggers: "why does X have 3 stars", "what's the TM for X", "inspect TM", "explain the score for X", "what evidence would rank up X", "show leaderboard", "rank all skills by TM", "what's dragging down X's score", "dead evidence rows", "how close is X to grade A/S".
version	1.1.0
genericSkillRef	registry-inspection

/trust-appraise-all

Two Modes

Inspect Mode — single skill deep-dive

/trust-appraise-all <skillId>

<skillId> is the contributor/name path (e.g. garrytan/gstack, mattpocock/grill-me, obra/superpowers).

Output includes:

Each evidence row with the full score chain: base magnitude → × type weight → × freshness → × mothership/creator/engagement → × inheritMultiplier → × plateau → final score
Dead rows (score = 0.0) and why (missing views, stars below threshold, deranked verifier, etc.)
Fusion-recipe summary if suiteComponents is present: component count, graded origins, raw fusion magnitude
Total TM, overall grade, and exact points to the next grade threshold
Most efficient evidence type to add for the next TM jump

Leaderboard Mode — all skills ranked

/trust-appraise-all --leaderboard

Full ranked table grouped by grade band:

Band	TM Threshold
S	>= 250
A	>= 100
B	>= 50
C	>= 20
Ungraded	< 20

Columns: Rank, Skill ID, TM, Grade, Level, Contributor.

How to Run It

# Inspect a single skill
GAIA_OPERATOR_OVERRIDE=1 python scripts/inspectTrustMagnitude.py --skill <skillId>

# Full leaderboard
GAIA_OPERATOR_OVERRIDE=1 python scripts/inspectTrustMagnitude.py --leaderboard

The script loads named skills from registry/named/, resolves fusion recipes from registry/nodes/, and calls explainTrustMagnitude() in src/gaia_cli/trustMagnitude.py.

Agent Instructions

For /trust-appraise-all <skillId>:

Run the inspect command for the requested skill.
Present a concise table of evidence rows: type, source, and final score. Group live rows above dead rows.
Call out dead rows and explain the specific reason each one contributes 0 (e.g. "social-signal: 820 views — below 1k floor").
State the next-grade gap plainly: "needs X more TM to reach grade Y (currently Z)".
Recommend the single highest-impact evidence type to add, with reasoning (e.g. "one peer-review with 3 reviewers adds ~90 TM — more than doubling current score").

For /trust-appraise-all --leaderboard:

Run the leaderboard command.
Present the output grouped by grade band.
Flag any skills with many evidence rows but low TM — dead rows are likely culprits worth a follow-up inspect.

Trust Magnitude Formula Reference

artifact_score = magnitude × type_weight × freshness × mothership × creator × engagement
TM = Σ(artifact_scores), with social-signal capped at 80 across all rows

Per-type magnitude formulas

Type	Magnitude Formula	Weight	Cap
fusion-recipe	20×N (N≤10); 200+20√(N-10) (N>10)	1.5	—
github-stars-own	stars / 1000	1.0	200
proxy-containment	(externalStars/1000)×0.8 (min 10k stars)	1.0	160
verifier-attestation	30 × verifiers	1.5	—
benchmark-result	percentile (field required — omitting it scores 0)	1.4	100
arxiv	citations / 5	1.0	100
peer-review	25 × reviewers	1.2	—
repo-own	commits/200 + contributors²×2	0.6	60
self-attestation	10	0.5	10
social-signal	log10(views)×8 (min 1k views)	1.0	80 (sum cap)

Grade thresholds

Grade	TM Floor	Additional Gates
S	250	distinctTypes >= 3 AND has non-self-producible evidence
A	100	—
B	50	—
C	20	—
Ungraded	< 20	—

Common dead-row causes to watch for

social-signal with views < 1000 → scores 0 regardless of type weight
github-stars-own and repo-own pointing to the same URL → deduped; only the higher score counts
benchmark-result missing percentile field → magnitude = 0
Large suite with github-stars-own at the repo root → per-skill contribution tiny due to / skill_count_in_repo divisor; use social-signal or peer-review instead