Skip to content
cccskills
FreePublished on GitHub

gaia-fuse-full-suite

Fuse all of a contributor's named skills into a single fusion node (suite capstone) in the registry. Use when the user says "fuse <contributor>'s skills", "create a suite for <contributor>", "build a capstone for <user>", "fuse all of <user>'s named skills", "create a suite fusion", "consolidate <contributor> into one skill", or explicitly types /gaia-fuse-full-suite. Also triggers when a contributor has accumulated 3+ named skills and the user asks what to do next with them, or when someone asks "can we make a suite from these?". This skill: collects component IDs from registry/named/<contributor>/, verifies nodes exist, researches evidence and appraises Trust Magnitude, runs `gaia dev fuse` to write the fusion node and suite manifest, validates, and opens a PR on a review/meta/ branch.

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (1)

  • SKILL.md8.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

gaia-fuse-full-suite

Fuse every named skill attributed to a contributor into a new fusion node, link it as the suite capstone, record a fuse timeline event, and open a PR.

A fusion node is the right abstraction when a contributor has built a coherent body of named skills that together form a recognisable suite. The fusion step makes that relationship explicit in the graph: prerequisites point to the fusion node, and the fusion node's evidence anchors the whole cluster's credibility.

Taxonomy (Yggdrasil II)

Ratified 2026-07-07. Read CONTEXT.md § Taxonomy v6 before writing any copy.

  • The type axis is starless-only and collapsed to exactly {basic, fusion}. extra, ultimate, and unique are retired as types — never write them to a node.
  • Ultimate (5★ Suite) and Apex (6★ Suite) survive only as rank names, never as taxonomy words. A fused capstone is a Fusion, not "an Ultimate".
  • Branch (standard / suite / unique) is derived at read time, never declared. A Named Skill carrying suiteComponents is suite at any rank.
  • The per-star Evidence Floor is retired. Trust Magnitude is the sole promotion gate.

Programmatic-First — use the CLI

Per CLAUDE.md, all registry mutations go through gaia dev verbs. Do not hand-write node JSON — gaia dev fuse writes the fusion node, the suite manifest, the back-links, and the timeline event, and it always emits type: fusion into registry/nodes/fusion/. Hand-edits skip timeline logging and are how schema-invalid nodes reach the registry.

Inputs

Gather these before starting. Infer from context when obvious; ask when ambiguous.

InputDescriptionExample
contributorGitHub username of the named contributorobra
fusion-idkebab-case ID for the new fusion nodesuperpowers
fusion-nameHuman-readable display nameSuperpowers
capstone-idNamed capstone to link (contributor/slug)obra/superpowers
source-urlCanonical repo or landing page (for evidence research)https://github.com/obra/superpowers

If the contributor already has a fusion node with this ID and it has a fuse timeline entry, abort early and report the existing entry — there is nothing to do.

Workflow

1. Collect components

ls registry/named/<contributor>/

For each .md file, parse the YAML frontmatter and extract:

  • genericSkillRef — the component skill ID
  • level — used in the summary table
  • title — the named title

Fail loudly (do not silently skip) if any file is missing genericSkillRef, or has status: awakened. Awakened skills have not been named yet and cannot participate in a fusion — their inclusion would undercount what the suite represents.

2. Verify component nodes exist

For each genericSkillRef, confirm a node JSON file exists under registry/nodes/basic/ or registry/nodes/fusion/. Report any missing IDs and abort — missing nodes must be registered via gaia dev add before the fusion can proceed. Do not create stub nodes inline.

3. Check for an existing fusion node

gaia dev list --generic | grep '<fusion-id>'
  • Already exists + has fuse timeline entry → abort (report URL).
  • Already exists, no fuse entry → update mode; gaia dev fuse merges rather than clobbers.
  • Does not exist → proceed to creation.

4. Research evidence and appraise Trust Magnitude

Fetch source-url with WebFetch and record the signals that will feed TM scoring:

  • GitHub star count and trajectory
  • Multi-platform adoption (unrelated hosts shipping it)
  • Active release tag / version ≥ 1.0
  • Published academic paper, peer review, or official specification

Log each source through the CLI so it is graded and timestamped:

gaia dev evidence <fusion-id> "<url>" --type <evidence-type> --evaluator <your-handle>

Then appraise:

gaia appraise <fusion-id>

Rank decision — Trust Magnitude is the sole gate. There is no per-star Evidence Floor under Yggdrasil II; do not assert a star level from an evidence grade alone. For the Suite branch the published gates are:

  • 4★ Extra — Origin Contributor recorded + TM ≥ 100
  • 5★ Ultimate — Origin in suiteComponents + 5 A-graded origins in suiteComponents + TM ≥ 250
  • 6★ Apex — the full 6-predicate Apex Gate (see META.md)

If the appraised TM does not clear a gate, record the rank the TM supports and say so in the PR. Do not round up.

5. Run the fusion

gaia dev fuse <fusion-id> \
  --name "<fusion-name>" \
  --description "<one sentence synthesising what the suite achieves>" \
  --prereqs <component-id-1>,<component-id-2>,... \
  --named-capstone <capstone-id> \
  --suite-components <named-id-1>,<named-id-2>,...

This writes registry/nodes/fusion/<fusion-id>.json with type: fusion, upserts the suite manifest at registry/suites/<contributor>/<slug>.json, back-links derivatives on every component node, appends the fuse timeline event, and rebuilds the graph and docs.

Notes:

  • --type is not a flag. gaia dev fuse always produces a fusion node; the type is derived structurally from the presence of prerequisites.
  • suiteComponents is a Named-Skill-only field. Never write it onto the starless node.
  • Do not write a branch field — branch is computed at read time.
  • Pass --no-build only if you are batching several fusions; run one build at the end.

6. Validate

PYTHONIOENCODING=utf-8 gaia dev validate

All checks must pass. Common failures and fixes:

  • Reference integrity — a missing derivative or prerequisite; re-run the fuse with the complete --prereqs list.
  • DAG cycle — a component points back to itself through the fusion node; remove the self-referencing derivative.
  • Fusion constraints — the recorded rank exceeds what Trust Magnitude supports; lower the rank via gaia dev calibrate, or log stronger evidence and re-appraise.
  • Meta sync — registry/ and the bundled snapshot diverged; re-run the build step.

Do not open a PR until validation is clean.

7. Commit and open PR

Branch: review/meta/<fusion-id>-fusion

Per CLAUDE.md Guard E, a change to registry/nodes/ or registry/named/ must ship the regenerated Class S artifacts (docs/graph/*) in the same PR.

git checkout -b review/meta/<fusion-id>-fusion origin/main
git add registry/nodes/fusion/<fusion-id>.json \
        registry/nodes/basic/<component-id>.json \
        registry/suites/<contributor>/ \
        registry/named-skills.json \
        docs/graph/
git commit -m "feat(registry): fuse <contributor>/<suite-name> into /<fusion-id> <rank> fusion

- Add /<fusion-id> fusion node capstoning N named <contributor> skills
- Back-link derivatives on all N component nodes
- Add fuse timeline event (action: fuse, <today>)
- Regenerate Class S artifacts (docs/graph/*)

gaia dev validate: all checks pass (<total> skills, <edge> edges)."
git push -u origin review/meta/<fusion-id>-fusion

PR body template:

## Summary

- New fusion node **/<fusion-id>** (<rank>) capstoning N named <contributor> skills
- Fuse timeline event recorded; components back-linked via `derivatives`
- Evidence: <one-line summary of source and signals>
- Trust Magnitude: <TM> (gate for <rank> is <threshold>)

## Component skills

| ID | Named Title | Rank |
|---|---|---|
| <id> | <title> | <rank> |

## Rank rationale

<Which TM gate the appraisal cleared — cite the appraised TM from step 4>

## Validation

- `gaia dev validate` — all checks pass

Output

Report back concisely:

  • PR URL
  • Fusion node ID and rank
  • Number of components fused
  • Appraised Trust Magnitude and the key signals behind it
  • Validation result

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

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.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

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.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

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".

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

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".

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

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.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

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.

The English summary is being prepared. Showing the original description.

gaia-research/gaia-skill-tree23Updated Oct 24, 2026

See all skills by gaia-research

Report a problem with this skill