gaia-research/gaia-skill-tree / .agents/skills/gaia-quick-curate
gaia-quick-curate
VerifiedInspect or exercise the paused gaia curate orchestration scaffold for one source URL. The command persists an INITIALIZED run ledger and reports status. Its former transition stubs were pruned, so no automated curation or merge pipeline runs. Outward discovery belongs to /gaia-frontier, and manual L4-gated curation is supported via /gaia-full-pipeline or /gaia-consult. Use only for scaffold development, status inspection, or dry-run contract work. Trigger phrases: "/gaia-quick-curate", "inspect gaia curate", "curate scaffold", "quick curate status". For batch/multi-page runs use gaia-curate-dynamic; for crawler branches use gaia-bot-curate; for pending intake proposals use gaia-draft-curate.
gaia-quick-curate
gaia curate is currently a paused orchestration scaffold. It can create
and persist a run ledger, reload one with --resume, and print status. A fresh
run deliberately pauses at INITIALIZED; the non-executing transition method
stubs beyond that point were an orchestration skeleton, NOT working automation,
and have been pruned. The CLI does not perform automatic discovery, evidence
verification, ingest, calibration, GitHub issue/PR work, or merging.
Do not describe this skill as an automated two-gate pipeline, claim that it will advance through all 25 states, or promise "one URL in, one merged PR out." The state names record the intended workflow shape only.
For an implemented, human-directed curation workflow, use /gaia-full-pipeline for phase routing or /gaia-consult for command guidance. For outward ecosystem intelligence and discovery leads, use /gaia-frontier.
Migration notice
Under the Founder Frontier Ruling (2026-10-26), the unimplemented future-transition
Python stubs in CurationOrchestrator were pruned as obsolete scaffolding, NOT
working automation:
- Outward ecosystem discovery is canonically owned by
/gaia-frontier. - Manual, bounded L4-gated curation remains valid and supported via
/gaia-full-pipelineand/gaia-consult. - Status inspection and historical ledger loading are preserved in
gaia curateand this compatibility skill (/gaia-quick-curate).
Current command surface
gaia curate <url> [--generic <id>] [--discover] [--dry-run]
gaia curate --resume <run-id> [--status]
| Input | Current behavior |
|---|---|
<url> | Creates a run ledger, pauses at INITIALIZED, and prints status. |
--generic <id> | Records a suggested generic ID; it does not apply a mapping. |
--discover | Records discovery intent; it does not run discovery yet. |
--dry-run | Records dry-run intent; no curation transitions are implemented. |
--resume <run-id> | Loads an existing ledger by run ID. |
--status | Prints the loaded or newly created run's status. |
Run state is stored at:
.gaia/curation/runs/<run-id>/state.json
The ledger currently starts in INITIALIZED. Although
src/gaia_cli/curation/state.py declares 25 intended state names, that list is
retained for historical runs and ledger compatibility, not evidence that an
automated workflow exists. SCAFFOLD_PAUSE_STATES in the orchestrator prevents
a fresh run from entering unimplemented transitions.
Safety and merge authority
The scaffold has no authority to mutate the registry or GitHub today. If its
runtime is implemented later, all registry writes must still use the canonical
Gaia CLI mutation path, approval gates must be explicit and resumable, and the
final merge to main must remain founder-gated. This skill must never merge the
final PR to main; a human founder makes that decision after reviewing the
evidence, diff, and CI state.
Live source locations
| Concern | Path |
|---|---|
| CLI command entry | src/gaia_cli/commands/curate.py |
| Run ledger and 25-state design skeleton | src/gaia_cli/curation/state.py |
| Pause guard and status inspector | src/gaia_cli/curation/orchestrator.py |
| URL-resolution helper | src/gaia_cli/curation/url_resolver.py |
| Run state | .gaia/curation/runs/<run-id>/state.json |
There is no live src/gaia/curate/state_machine.py, gate UI, or control-panel
comment renderer. Do not invent those paths or report future components as
implemented.
When to use another skill
| Need | Use |
|---|---|
| Outward discovery and ecosystem intelligence | /gaia-frontier |
| Implemented phase-by-phase curation | /gaia-full-pipeline |
| Curation command/reference lookup | /gaia-consult |
| Batch or multi-source discovery | /gaia-curate-dynamic |
Crawler bot/* branches | /gaia-bot-curate |
| Pending intake proposals | /gaia-draft-curate |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |