Skip to main content
Exécutez n'importe quel Skill dans Manus
en un clic
gaia-research
Profil créateur GitHub

gaia-research

Vue par dépôt de 75 skills collectés dans 5 dépôts GitHub.

skills collectés
75
dépôts
5
mis à jour
2026-07-26
explorateur de dépôts

Dépôts et skills représentatifs

gaia-release
Développeurs de logiciels

Helper for release operations, compilation of changelogs between tags, version lockstep syncing, and promotion of GitHub releases from canary/pre-release to latest/production. Use when the user asks to "compile the changelog", "promote release to latest", "tag a release", or do version release operations.

2026-07-16
pr
Développeurs de logiciels

Push committed changes and create a draft PR on GitHub. Use when you have staged changes ready to push and want to open a draft PR for early feedback or documentation.

2026-07-15
trust-methodology-consult
Autres occupations informatiques

Consult this skill BEFORE proposing a fix to any CLI gap or schema gap that touches evidence, trust magnitude, evidence types, evidence grades, the TM formula, or star-level promotion gates. Also read it whenever an issue mentions citations, stars, commits, contributors, views, reviewers, percentile, arxiv, github-stars-own, repo-own, social-signal, benchmark-result, peer-review, self-attestation, fusion-recipe, verifier-attestation, or proxy-containment — those are the 10 canonical evidence types and the raw inputs that feed their formulas. Also read it when asked whether a skill qualifies for a given star level (0★–6★): the Star Bar and promotion gates live in `META.md`, not in the TM methodology page. Reading both prevents proposing a calibration that satisfies the TM grade threshold but violates a Star Bar installability or link requirement.

2026-07-13
ev-link-validation
Analystes en assurance qualité des logiciels et testeurs

Phase 4 of the Gaia evidence verification pipeline. Checks every URL in the evidence data lake for HTTP liveness — catches dead links (404, 403, timeout, connection errors) before evidence is ingested into the registry. Use this skill when: running the full /ev-pipeline, asked to "validate links", "check evidence URLs", "run link validation", "find dead links in the data lake", "check HTTP status of evidence sources", or "verify evidence links still work". Also useful standalone when you suspect evidence sources have gone stale after a long gap between pipeline runs. Wraps validate_sources.py, which uses Firecrawl CLI to scrape each unique URL and records pass/fail status in a markdown report. Requires Firecrawl CLI to be installed and authenticated.

2026-07-13
ev-pipeline
Autres occupations informatiques

Top-level orchestrator for the Gaia Registry evidence verification pipeline. Run this when you want to do a full evidence pass — collecting raw sources, verifying live GitHub star counts, adversarially auditing for quality/formatting issues, and checking that every URL is reachable — all in one coordinated sequence. Trigger phrases: "run the evidence pipeline", "full evidence pass", "verify evidence", "evidence verification pipeline", "run ev-pipeline", "check all evidence", "audit the data lake", "evidence quality sweep", "refresh evidence", "validate evidence sources". Also aliased as /evidence-verification-pipeline. Use the individual sub-skills (ev-collection, ev-star-verification, ev-adversarial-audit, ev-link-validation) only when you need to re-run one phase in isolation; for end-to-end work, always start here.

2026-07-13
evidence-verification-pipeline
Autres occupations informatiques

Canonical entry point for the full Gaia evidence verification pipeline. Invoke as /evidence-verification-pipeline or /ev-pipeline — both names trigger this skill. Use whenever you need to run all four evidence phases end-to-end: collecting raw evidence from the data lake, verifying live GitHub star counts, running adversarial auditing for noise and URL errors, and checking link health via Firecrawl. Also use when someone says "run the evidence pipeline", "verify the evidence lake", "audit evidence", "run ev-pipeline", "full evidence check", "pipeline run", "prepare evidence for ingestion", or "refresh the data lake". This is the pre-ingestion step — run it before importing any evidence into the registry.

2026-07-13
gaia-ingest-batch
Autres occupations informatiques

Batch wrapper for /gaia-ingest. Ingests a bounded set of already-verified evidence rows through CLI-only writes, uses --no-build on every row, appraises Trust Magnitude for every affected named skill, then runs exactly one build and validation pass. Use for an L4-approved intake after /ev-pipeline.

2026-07-13
gaia-ingest
Autres occupations informatiques

Atomically ingest one already-verified evidence row into one named Gaia skill using the CLI, then appraise Trust Magnitude and propose—never silently apply—a calibration. Use after /ev-pipeline has verified an approved intake source, or whenever a curator says "ingest evidence", "add verified evidence", "gaia-ingest", or "turn this source into registry evidence".

2026-07-13
Affichage des 8 principaux skills collectés sur 62 dans ce dépôt.
gaia-blog-post
Rédacteurs techniques

Standardized playbook for authoring high-signal, real-evidence-backed blog posts for Gaia Research. Enforces a research-first pipeline with mandatory web search and source verification before writing, three adversarial reviewer passes (factual correctness, fabrication detection, readability), Nova voice style guide, anti-slop guardrails, SVG graphs over long text, and Milim thumbnail generation.

2026-07-24
gaia-blog-post
Rédacteurs techniques

Standardized playbook for authoring high-signal, low-noise blog posts for Gaia Research. Enforces single-topic deep dives, anti-slop guardrails, no unratified roadmap claims, show-don't-tell evidence, SVG graphs over long text, Nova's writing persona, and Milim thumbnail generation via milim-editorial-thumbnail skill.

2026-07-23
milim-editorial-thumbnail
Graphistes

Create or refine calm, flat 16:9 Gaia Research editorial thumbnails featuring a tiny Milim within vast everyday slice-of-life scenes. Emphasizes dramatic scale (Milim 4-6% frame height), flexible positioning (left, center, right), expansive negative space (88-92%), varied emotions, and dynamic color palettes.

2026-07-23
milim-editorial-thumbnail
Graphistes

Create or refine calm, flat 16:9 Gaia Research editorial thumbnails featuring a tiny Milim within vast everyday slice-of-life scenes. Emphasizes dramatic scale (Milim 4-6% frame height), flexible positioning (left, center, right), expansive negative space (88-92%), varied emotions, and dynamic color palettes.

2026-07-23
gaia-image-production
Graphistes

Gaia Research image-generation harness for pi-image-gen/gpt-image-2 and Termux Antigravity OAuth workflows. Use when generating, iterating, refining, cropping, upscaling, making transparent cutouts, compressing, or ledgering visual assets for Gaia Research, especially Context Diet, Milim/Nova, hero, OG, social images, and blog editorial thumbnails.

2026-07-23
mockup-iteration
Graphistes

Interactive visual iteration loop for generating and refining mockups before finalizing an asset commission. Use when the user wants to generate, preview, and adjust concept art or mockups iteratively.

2026-07-11
visual-audit
Analystes en assurance qualité des logiciels et testeurs

Playwright visual + mobile cut-off audit for the Gaia Research Next.js site. Use before/after any UI, CSS, layout, or responsive change, or when the user asks to check visuals, screenshots, mobile view, horizontal scroll, or content being cut off. Screenshots every key page across desktop and phone widths, detects horizontal overflow and names the culprit element, and flags console errors.

2026-07-11
preview-image
Développeurs de logiciels

Opens an exact local image file in the device browser through a private localhost server, with an optional copy to Android Downloads. Use when the user wants to inspect a generated, workbench, or repository image at full size on-device.

2026-07-10
Affichage des 8 principaux skills collectés sur 10 dans ce dépôt.
5 dépôts affichés sur 5
Tous les dépôts sont affichés