gaia-tm-inspect
Use this skill when the user wants to 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 i
SKILL.md.claude/skills/gaia-tm-inspect/SKILL.md
GitHub/gaia-tm-inspect
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.
Scope (authority map §2): inspect mode reports the effective named TM, which sums own
rows plus resolved generic inheritance. If the genericSkillRef node does not resolve, say
"generic: not evaluated" and do not call the total final.
Two Modes
Inspect Mode — single skill deep-dive
/gaia-tm-inspect <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 → min(cap) → × type weight → × freshness → × creator/engagement (social-signal only) → × inheritMultiplier (inherited rows only) → × plateau → final score - Dead rows (score = 0.0) and why (missing views, stars below threshold, deranked verifier, etc.)
- Fusion-recipe summary if
suiteComponentsis present: component count, graded origins, Fusion Score (informational, 0 TM) - 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
/gaia-tm-inspect --leaderboard
Full ranked table grouped by Overall Trust Grade band (floors and the S diversity gate: authority map §3).
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 /gaia-tm-inspect <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 /gaia-tm-inspect --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 reference
Formulas, weights, caps, dedup, inheritance, grade floors, star gates and appraisal scope
live in one canonical place: docs/agents/curation-authority-map.md.
This skill does not restate them. Cite the map section when you explain a score. If the
map and src/gaia_cli/trustMagnitude.py ever disagree, the engine wins and the map is
the bug.
fusion-recipe scores 0 TM. Structure is reported by the informational Fusion Score (META.md §2.1e). Over
Ndistinct non-variant nodes in the resolved structural closure:FS = 0whenN = 0;FS = 20 × Nwhen1 ≤ N ≤ 10;FS = 200 + 20 × √(N − 10)whenN > 10. Fusion Score gates no star, rank or Trust Grade. When you report one, also state that published TM fell for suites and fusions because this row went to 0 TM. No evidence row, star count, or rank was edited (META.md §2.1e).
Common dead-row causes (engine-verified, map §1)
social-signalwith views < 1000 → 0.github-stars-ownwith stars ≤ 10 → 0. Only onegithub-stars-ownrow scores (plateau max 1).benchmark-resultthat is not catalog-eligible (unknown or rejectedbenchmarkId, or a non-scoring lane) → excluded.- A second row of the same type at the same canonical URL → collapsed. Dedup is within type:
github-stars-own+repo-ownat one URL both count. - Rows beyond a stackable type's plateau max-rows → 0.
- Shared suite-root repository evidence on a suite component → capped at 50.0 TM per component.
- A verifier-attestation from a deranked verifier → excluded (null).
skillCountInReponever reduces a score. There is no repository-count divisor.