Skip to content

gaia-research/gaia-skill-tree / .agents/skills/dev-ingest-named

dev-ingest-named

Verified

Playbook for landing one evidence-approved single-skill intake whose L4 topology is a NEW fusion generic plus one named implementation: create the generic and its prerequisites, create the named skill, ingest each verified evidence row, and appraise Trust Magnitude — then stop at the calibration gate. Use when: an intake issue carries intake:topology-approved and intake:evidence-approved, the promotion PR review/meta/intake-<N> is open, and a reviewed evidence manifest exists. Triggers: "ingest the approved intake", "land intake #N", "add the generic and named skill for this intake", "run the ingest for the evidence-approved batch". Not for suites (use gaia-fuse-full-suite), not for an existing generic (add the named skill with `gaia dev add --named` directly), and not for star calibration (dev-calibrate).

FileKindSize
SKILL.mdskill md7.8 KB
trigger-prompts.mdmarkdown1.4 KB

trigger-prompts.md

View on GitHub
# dev-ingest-named — trigger prompts

Used to check that realistic requests select this playbook, and that near misses
do not. Not a skill entry point: this file is a reference asset only.

## Should select dev-ingest-named

- "Intake #2452 has topology and evidence approved and the promotion PR is open. Land the generic, the named skill and the evidence rows."
- "Run the ingest for the evidence-approved batch: create the new fusion generic from the L4 decision, then add the named skill and its verified rows."
- "The L4 ruling made a new generic for this skill. Add it with its prerequisites, add the named implementation, ingest the manifest and appraise it, but don't calibrate yet."
- "Turn the reviewed evidence manifest for this single-skill intake into CLI-written rows and tell me the Trust Magnitude."

## Should not select it (use the named alternative)

- "Fuse all of obra's named skills into a suite capstone." → gaia-fuse-full-suite
- "Set leonxlnx/cook to 3★ based on its Trust Magnitude." → dev-calibrate
- "Add this skill; it maps to the existing design-generation generic." → `gaia dev add --named` directly (generic exists, this playbook stops with GENERIC_EXISTS)
- "Find new evidence for this skill." → ev-discovery / ev-pipeline
- "Is this a new generic or a duplicate?" → gaia-curate (topology is an L4 decision, not an ingest)
- "Open the promotion PR and stage the generated docs." → gaia-review-meta-close
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall