gaia-research/gaia-skill-tree / .agents/skills/gaia-curate-trending
gaia-curate-trending
VerifiedUse for discovery-only global trending curation across configured sources; for one source page use gaia-curate. Snapshots configured external skill sources, prioritizes five-candidate pages for L4 review, and stops before trust, evidence, intake, or registry mutation.
Gaia Curate Trending
Read ../gaia-curate/CURATION-CORE.md first. This ranks what reviewers should inspect now. It is external discovery, not Gaia's internal Trending API, not evidence, and not a trust signal. “Global” means every configured public source in the run manifest; never claim exhaustive web coverage.
Source manifest
Require a versioned manifest with bounded lanes and cursors:
contractVersion: curate-trending-manifest-v1
windowDays: [7, 30]
pageSize: 5
sources:
- id: source-id
lane: marketplace | source-repository | github-topic
url: https://...
cursor: null
Real marketplaces and source repositories are primary lanes. Package registries, MCP directories, model hubs, and extension listings are lead sources only: quarantine each lead until it resolves to an actually fetched upstream SKILL.md that passes the core artifact gate. Unknown sources become newSourceSuggestions; discovery must not edit registry/skill-sources.md.
Snapshot and trend bands
Persist source-native observations for 7-day and 30-day windows: observed time, source rank/label, first-seen time, listing or download delta when exposed, repository star delta when exposed, and cross-source recurrence. Repository stars may prioritize inspection but are never inherited as implementation evidence or used for TM.
Assign one band mechanically in this priority order:
HOT: the source explicitly labels the artifact trending/top and it recurs on another configured source during the window.RISING: a comparable prior snapshot exists and at least one source-native rank/download/star delta is positive.NEW: first observed inside the selected window and neither higher band applies.STEADY: comparable snapshots exist with no positive trend signal.UNKNOWN: comparable history is missing, contradictory, or unavailable.
Store the raw observations and rule that produced the band. Never ask a model to calculate the band and never convert it to evidence, grade, class, star level, TM, or acceptance.
Manual page loop
Process at most five candidates per source page, and exactly one active candidate per model turn:
- fetch the source page and persist its next cursor;
- resolve each lead to a canonical repository path and immutable commit when possible;
- fetch and parse the real
SKILL.md; - exact-dedupe by normalized repository/path, canonical URL, cited origin, and content hash;
- query the generic snapshot and supply at most three mapping options;
- request one bounded core decision;
- validate and persist before advancing;
- on invalid/ambiguous output,
DEFER; never infer acceptance.
Allowed human/operator controls are NEXT, STOP, RESUME <run-id>, and one core decision for the active candidate. STOP writes a resumable checkpoint; it does not discard completed packets.
Output and handoff
Write runtime snapshots and resumable state under generated-output/curate-discovery/<run-id>/:
run.json
source-snapshots.json
candidates.jsonl
decisions.jsonl
deferred.jsonl
L4-REVIEW.md
L4-REVIEW.md lists candidate, trend band, source, existing-generic mapping, bounded disposition, and flags. Validate every row as discovery-packet-v2; copy final review packets to the Core-owned registry-for-review/discovery-packets/ path, then stop at L4. V1 is read-compatible only, not normative output. A shortlist decision is not intake, evidence, named-star, or mutation approval. Only Core's explicit post-L4 ratification seam via gaia dev ratify and gaia push may feed intake.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |