Skip to content
cccskills
FreePublished on GitHub

gaia-suite-intake

Comprehensive, reusable playbook for multi-component suite intake under Yggdrasil III. Audits component installability, maps origin candidates to generic capabilities, ingests named components with shared-repo baseline caps, manifests suites via gaia dev fuse, calibrates capstone and component ranks, and closes out via Class S regeneration.

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

Works withGitHub

Run score Not tested

See how to install

Files included (1)

  • SKILL.md12.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

gaia-suite-intake

End-to-end playbook for ingesting, structuring, and calibrating multi-component skill suites under Yggdrasil III.

A suite is a cohesive collection of specialized skills authored by a contributor or team, anchored by a central capstone skill that coordinates or unifies them (e.g. gsd-build/get-shit-done, leonxlnx/taste-skill, obra/superpowers). Ingesting a suite requires orchestrating multiple interlocking layers: component installability, generic capability mappings, shared repository evidence capping, suite manifestation via gaia dev fuse, branch-aware calibration, and Class S artifact regeneration.


Yggdrasil III Normative Rules & Invariants

Before executing any intake steps, verify understanding of these foundational invariants:

  1. Type Axis Collapse:
    • The starless node type is strictly {basic, fusion}.
    • extra, ultimate, and unique are retired as types — never write them to node JSON.
  2. Derived Branch Taxonomy:
    • Branch (standard / suite / unique) is derived dynamically, never hard-coded.
    • A skill carrying suiteComponents sits on the Suite branch at any rank (1★–6★).
    • Standalone skills without suiteComponents sit on standard (1★–3★) or unique (4★–6★).
  3. Trust Magnitude as Sole Promotion Authority:
    • The legacy per-star Evidence Floor is completely retired.
    • fusion-recipe rows contribute 0 TM (Issue #1600). Structural composition is reported separately via Fusion Score, which gates no rank.
  4. Shared Repository Evidence Cap:
    • Sub-components inheriting repository evidence from a shared parent repo are capped at SUITE_COMPONENT_REPOSITORY_CAP = 50.0 TM per component (META.md §2.1, trustMagnitude.py).
    • Repository adoption alone cannot promote sub-components beyond Grade B (50 TM / 3★) without independent corroboration.
  5. Branch-Aware 4★ Gate (META.md §4 / Issue #1741):
    • 4★ Promotion Requirement: Requires Overall Trust Grade A (TM ≥ 100) and live verified blob evidence (The Star Bar, META.md §2.4).
    • Unique Branch (standalone, no suiteComponents): 4★ Unique requires bucket-level Origin on its generic bucket (META.md §4.1).
    • Suite Branch (capstone carrying suiteComponents): 4★ Extra does NOT require bucket-level Origin on its generic bucket. The capstone represents the suite cluster rather than a single generic bucket monopoly. Suite origin requirements apply at 5★ Ultimate (proposer must hold Origin on ≥1 of the suiteComponents per META.md §4.2).
    • Precedents: leonxlnx/taste-skill (4★ Extra, origin: false on generic design-generation), gsd-build/get-shit-done (4★ Extra).

Inputs

Gather these before beginning:

InputDescriptionExample
contributorGitHub organization or usernameleonxlnx
suite-slugIdentifier for the suite capstonetaste-skill
repo-urlCanonical GitHub repository URLhttps://github.com/leonxlnx/taste-skill
default-branchDefault git branch of the upstream repomain
componentsList of sub-skill directories / filesbrandkit, minimalist-skill, ...

Phase 1: Upstream Suite Inspection & Installability Audit

Inspect the upstream repository structure and audit every component before touching the registry.

1.1 Repo Structure & Component Identification

Inspect the remote repository using gh or clone locally in a temporary directory:

gh repo view <owner>/<repo> --json defaultBranchRef,stargazerCount,description

Locate all component SKILL.md files:

  • Typical layouts: skills/<component-name>/SKILL.md, plugins/<name>/SKILL.md, or top-level directories.
  • Identify the capstone: the primary entry point, meta-orchestrator, or root skill that references or coordinates the components.

1.2 Frontmatter & Lifecycle Audit

For each component SKILL.md, verify:

  • Frontmatter exists with valid YAML fences (---).
  • Required fields: name, description.
  • Instructions / CLI usage: verify how the skill is executed (e.g. npx, uvx, shell script, or harness prompt).

1.3 The Star Bar (Installability Gate)

Per META.md §2.4:

  • Any skill promoted to 3★ or higher MUST have a verified GitHub BLOB link pointing to a concrete file (e.g. https://github.com/<owner>/<repo>/blob/<branch>/.../SKILL.md), never a bare repo root.
  • A missing verified blob link is a hard reset to 1★ (Awakened).
  • Construct the exact blob URL for every component and confirm HTTP 200 reachable.

Phase 2: Origin Candidate Analysis & Generic Mapping

Map every component (and the capstone) to a generic capability bucket in registry/nodes/.

2.1 Capability Resolution

For each component:

  1. Search existing generic nodes:
    grep -rn "name: " registry/nodes/
    # or search by id slug
    find registry/nodes -name "*.json" | grep -i "<keyword>"
    
  2. If a matching generic bucket exists:
    • Check existing named implementations in that bucket:
      grep -rl "genericSkillRef: <generic-id>$" registry/named/
      
    • If bucket has no implementations, it is vacant. The incoming component is a primary Origin candidate.
    • If bucket has an incumbent: evaluate whether the incoming component is demonstrably more renowned. If not, incoming component will have origin: false.
  3. If no matching generic capability exists:
    • Create a starless generic basic node:
      gaia dev add <new-generic-id> \
        --name "<Generic Capability Name>" \
        --description "<Precise, vendor-agnostic capability description>" \
        --type basic \
        --no-build
      
    • The incoming component is the sole implementation and therefore an Origin candidate.

Phase 3: Ingestion of Named Components & Evidence Scoring

Ingest components programmatically via gaia dev verbs. Never hand-edit JSON or frontmatter.

3.1 Register Named Skills

For each component:

gaia dev add --named <contributor>/<component-slug> \
  --generic-ref <generic-id> \
  --name "<Component Display Name>" \
  --title "<RPG Title / Clean Name>" \
  --description "<Component description>" \
  --links github="https://github.com/<owner>/<repo>/blob/<branch>/<path>/SKILL.md" \
  --no-build

Also register the named capstone:

gaia dev add --named <contributor>/<suite-slug> \
  --generic-ref <capstone-generic-id> \
  --name "<Suite Capstone Display Name>" \
  --title "<Suite Title>" \
  --description "<Suite overview description>" \
  --links github="https://github.com/<owner>/<repo>/blob/<branch>/<path-or-readme>" \
  --no-build

3.2 Add Verified Evidence Rows

Gather verified repository metrics from GitHub API:

  • stargazerCount: Total stars on the suite repository.
  • commits: Total commit count.
  • contributors: Total contributor count.
  • createdAt / sourceStartedAt: Creation timestamp of repo/file.

A. Capstone Evidence

Add repository adoption evidence to the capstone:

gaia dev evidence <contributor>/<suite-slug> \
  --type github-stars-own \
  --source "https://github.com/<owner>/<repo>/blob/<branch>/<path>" \
  --stars <stargazerCount> \
  --source-started-at "<YYYY-MM-DD>" \
  --notes "<stars> stars on <owner>/<repo> repository" \
  --no-build

gaia dev evidence <contributor>/<suite-slug> \
  --type repo-own \
  --source "https://github.com/<owner>/<repo>" \
  --commits <commitCount> \
  --contributors <contributorCount> \
  --source-started-at "<YYYY-MM-DD>" \
  --notes "<commits> commits, <contributors> contributors" \
  --no-build

B. Component Evidence & Shared Repo Cap

Add component-level evidence. Sub-components residing in the shared repository inherit adoption signals, but Yggdrasil III enforces:

  • skillCountInRepo: Set to the total number of components sharing the repository.
  • SUITE_COMPONENT_REPOSITORY_CAP = 50.0 TM: The scoring engine automatically bounds shared repository evidence so that adoption alone caps at 50 TM (Grade B).
gaia dev evidence <contributor>/<component-slug> \
  --type github-stars-own \
  --source "https://github.com/<owner>/<repo>/blob/<branch>/<path>/SKILL.md" \
  --stars <stargazerCount> \
  --skill-count <componentCount> \
  --source-started-at "<YYYY-MM-DD>" \
  --no-build

Phase 4: Suite Manifestation via gaia dev fuse

Critical Rule: Running gaia dev update-named --suite-components alone is insufficient. gaia dev docs and gaia dev build will strip suiteComponents from Named Skill frontmatter unless a backing suite manifest exists at registry/suites/<contributor>/<suite-slug>.json.

Use gaia dev fuse to establish the manifest and wire the graph in one atomic operation:

gaia dev fuse <generic-suite-id> \
  --name "<Suite Name>" \
  --description "<Suite fusion description>" \
  --prereqs <comp1-generic-id>,<comp2-generic-id>,... \
  --named-capstone <contributor>/<suite-slug> \
  --suite-components <contributor>/<comp1>,<contributor>/<comp2>,... \
  --no-build

Verification:

  1. Confirm manifest exists: test -f registry/suites/<contributor>/<suite-slug>.json
  2. Confirm frontmatter wiring:
    grep -c "suiteComponents:" registry/named/<contributor>/<suite-slug>.md
    

Phase 5: Calibration of Capstone & Component Origins

5.1 Appraise Trust Magnitude

Run the appraisal tool on the capstone and all components:

python scripts/trust_appraise.py --skill <contributor>/<suite-slug>

Or use the detailed inspector:

GAIA_OPERATOR_OVERRIDE=1 PYTHONPATH=src python3 scripts/inspectTrustMagnitude.py --skill <contributor>/<suite-slug>

Verify:

  • Capstone TM score and Overall Trust Grade.
  • fusionScore: Structural composition reading (informational, does not feed TM).

5.2 Capstone Calibration (4★ Extra)

Evaluate the promotion gate:

  • Condition: Capstone has Overall Trust Grade A (TM ≥ 100) and verified blob link.
  • Suite Branch Invariant: Capstone does NOT require bucket-level Origin on its generic bucket! Origin on generic bucket is strictly for Unique branch standalone skills (META.md §4.1). Suite origin requirements apply at 5★ Ultimate (Origin on ≥1 suiteComponent per META.md §4.2).
  • Apply calibration:
    gaia dev calibrate <contributor>/<suite-slug> 4★ --no-build
    

5.3 Component Calibration & Origin Assignment

  1. Origin Assignment: For components that are the sole or most renowned implementation of their generic bucket:
    gaia dev update-named <contributor>/<component-slug> --origin true
    
  2. Component Star Calibration: Calibrate each component to its TM grade band:
    • Grade B (TM ≥ 50) → 3★ (must have verified blob link)
    • Grade C (TM ≥ 20) → 2★
    • Ungraded (TM < 20) → 1★
    gaia dev calibrate <contributor>/<component-slug> <N★> --no-build
    

Phase 6: Single-PR Closeout with Class S Documentation Generation

6.1 Single Dev Build

Run exactly one build pass to compile the registry and generate Class S site assets:

GAIA_OPERATOR_OVERRIDE=1 PYTHONPATH=src python3 -m gaia_cli.main dev build

6.2 Preflight Hygiene & Staging

Use scripts/review_meta_close.py to prevent leaks, drop CRLF noise, and stage only allowlisted artifacts:

# 1. Review status (must show 0 leaks in PR)
python scripts/review_meta_close.py status -v

# 2. Stage intended artifacts for this contributor
python scripts/review_meta_close.py stage --contributor <contributor> --apply

# 3. Verify clean index
python scripts/review_meta_close.py check

# 4. Run UTF-8 safe validation
python scripts/review_meta_close.py validate

6.3 Staged Artifacts Checklist

Verify that git diff includes only:

  • registry/nodes/ (new/updated generic nodes)
  • registry/named/<contributor>/ (capstone and component .md files)
  • registry/suites/<contributor>/<suite-slug>.json (suite manifest)
  • registry/named-skills.json & tracked registry files
  • docs/graph/ (Class S graph assets: gaia.json, gaia.gexf, named/index.json)
  • docs/badges/_assets/<contributor>/ & docs/og/<contributor>/

6.4 Branch & PR Opening

git checkout -b review/meta/<contributor>-<suite-slug>
git commit -m "feat(suite): ingest <contributor>/<suite-slug> suite with <N> components"
git push origin review/meta/<contributor>-<suite-slug>
gh pr create --title "feat(suite): ingest <contributor>/<suite-slug> suite" \
  --body "Ingests <contributor>/<suite-slug> suite under Yggdrasil III. Calibrates capstone to 4★ Extra on Grade A TM."

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 23, 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 23, 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 23, 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 23, 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 23, 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 23, 2026

See all skills by gaia-research

Report a problem with this skill