4,874 件 ・ 関連度順
概要と使いどころ
Run bounded, read-only semantic advisory sidecar passes for candidate mapping, issue triage, upstream diffs, evidence verification triage, and meta audit hints. Enforces monthly spend limits with explicit fallback to worker-luna.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Inspect or exercise the paused gaia curate orchestration scaffold for one source URL. The command currently persists an INITIALIZED run ledger and reports status; its 25 named workflow states and transition methods are a design skeleton, not an implemented automated curation or merge pipeline. Use only for scaffold development, status inspection, or dry-run contract work. For live curation, use gaia-full-pipeline or gaia-consult. 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.
日本語の概要は準備中です。原文の説明を表示しています。
Triage and classify pending Gaia skill intake batches in registry-for-review/. Use for gaia push intake proposals, draft skill batches, and deciding whether proposals should proceed to canonical curation. This skill is read-only and never promotes skills itself.
日本語の概要は準備中です。原文の説明を表示しています。
Discovery-only global trending extension for Gaia. Snapshots configured external skill sources, prioritizes five-candidate pages for L4 review, and stops before trust, evidence, intake, or registry mutation.
日本語の概要は準備中です。原文の説明を表示しています。
Harness-neutral, discovery-only Gaia curation extension. A Sol/Terra-class orchestrator preflights capacity, shards safe volume work to configurable Luna workers, converges risky cases, and stops at human L4 review.
日本語の概要は準備中です。原文の説明を表示しています。
Review a Gaia curation PR or branch as a read-only merge gate. Use for canonical registry promotion, schema, evidence, prerequisite, nomenclature, installability, and generated-artifact checks. Route intake batches to /gaia-draft-curate and unrelated PRs to /review.
日本語の概要は準備中です。原文の説明を表示しています。
Close out a review/meta branch that lands an evidence-ingest / curation batch: create the named nodes, ingest verified evidence, appraise Trust Magnitude, calibrate stars, wire suites, correct upstream naming, stage ONLY the intended artifacts (dropping CRLF churn and blocking leaks), validate, and open the PR. Use when a curation/ingest batch is verified and ready to land, or when the user says "close the review/meta branch", "land the ingest batch", "wrap up the intake PR", "/gaia-review-meta-close". Wraps the deterministic hygiene in scripts/review_meta_close.py and gates the judgment calls (calibration, Origin, suite promotion, naming, merge) behind explicit human checkpoints.
日本語の概要は準備中です。原文の説明を表示しています。
Discovery-only Gaia curation for one manually selected source page. Fetches and normalizes up to five real SKILL.md candidates, deduplicates and maps them for human L4 review, then stops without evidence scoring or registry mutation.
日本語の概要は準備中です。原文の説明を表示しています。
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; benchmark-result rows also require a Phase 2B report and explicit human gate approval.
日本語の概要は準備中です。原文の説明を表示しています。
Top-level orchestrator for the Gaia Skill Tree evidence verification pipeline. Run this when you want to do a full evidence pass — collecting raw sources, verifying live GitHub star counts, running Phase 2B benchmark-source verification, 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.
日本語の概要は準備中です。原文の説明を表示しています。
UI design and implementation for real product surfaces with taste-first critique, reference routing, project-specific design briefs, variation comparison, and implementation verification. Use when Codex should redesign, build, polish, or critique frontend UI by reading project context, exploring taste, routing through `references/catalog.md`, synthesizing `PROJECT_DESIGN.md` or `design.md`, using investment gates to avoid wrong taste/reference/scope, implementing in the existing stack, and evaluating whether the result is actually better. Best for app screens, dashboards, landing pages, query tools, product surfaces, and design explorations; not for backend-only work or tiny cosmetic edits.
日本語の概要は準備中です。原文の説明を表示しています。
Updates this skill pack from upstream, and owns the consent that decides whether it ever updates on its own. Checks whether the clone is behind, asks the user — update now, always keep me up to date, not now, or never ask again — and carries out the answer: applies the update through ./scripts/update.sh, records the consent flag the SessionStart hook already reads, snoozes on an escalating ladder, or turns the check off for good. Summarizes what changed between the two commits from the CHANGELOG. Use when the user asks to update or upgrade the pack, get the latest skills or the newest version, when the session banner reports that updates are available, when they ask whether their clone is current, when they want unattended updates switched on or off, or when they want to stop being asked. It never applies an update without an answer, and notify-only is the default.
日本語の概要は準備中です。原文の説明を表示しています。
Clones a VIDEO ad end to end for a different product or offer, on the Novoads API. The deliverable is a finished rendered MP4 — the WHOLE ad, not its opening, and not a template. Reads the source's style, pacing, camera work, dialogue and tone, adapts it into a Seedance 2.0 prompt, prices it, renders it, files the source beside the clones and diffs each clip's transcript against the approved script. Use for "clone this video ad", "recreate this video for my brand", "make this ad but for my product" when the source is a video, "clone my competitors' VIDEO ads", or a video ad handed over with a product photo. **Among cloners the source's medium decides, not the wording**: "clone this ad" plus a video lands here; a still, or nothing attached, is clone-image-ad, and animating a still as-is is image-to-motion. This pack has no hook-only skill: for the opening alone, clone the whole ad and cut. If it does not move, wrong skill.
日本語の概要は準備中です。原文の説明を表示しています。
Run any installed skill on several models at once — you, OpenAI Codex, OpenCode and whoever else the profile names — and show what each one made of it side by side. Every model gets the same prepared copy of the skill and works read-only. Use for "/multi:skill <name>", "run this skill on every model", "run <skill> through multi", or any skill whose answer you want from more than one model.
日本語の概要は準備中です。原文の説明を表示しています。
Scaffold a PhysicsIntern research workspace in the current folder. Run only when the user explicitly invokes it to set up a new physics/maths research workspace.
日本語の概要は準備中です。原文の説明を表示しています。
Prepare or open a GitHub or Gitea pull request with an explicit AI-authorship disclosure, change classification, reproducible reviewer verification steps, and optional Mermaid diagram. Use whenever the user asks to prepare, write, open, create, push, ship, or get changes ready for a PR or review. Unless the user explicitly asks for a draft-only result, create or reuse a dedicated branch, verify the change, commit scoped files, push the branch, and then create the PR with gh or tea.
日本語の概要は準備中です。原文の説明を表示しています。
Plan a feature before writing any code. Use this skill at the START of non-trivial feature work — when the user says they want to "add", "build", "implement", "create", "develop", or "ship" a feature, endpoint, component, page, service, or capability. Especially trigger when the user's prompt is short or under-specified ("add a dashboard", "build an auth flow", "let's do user activity reports") — those need planning, not direct execution. The skill walks through requirements clarification, codebase exploration, sketches a Mermaid architecture/flow diagram of the proposed design, and produces a plan.md document the user can hand off to a fresh AI session for execution. Skip only when the change is genuinely trivial (typo fixes, single-line tweaks, renames). When in doubt, plan.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user wants their way of working with Claude assessed — "review my session", "how am I using Claude Code", "audit my setup / workflow", "am I following best practices", "coach me", "what should I improve" — or pastes a Claude.ai/Cowork/Tag transcript and asks how they could have worked better. Do NOT use for reviewing code changes (that is code review) or for teaching a product from scratch (use academy-learn); this skill only reviews how the human works with Claude.
日本語の概要は準備中です。原文の説明を表示しています。
Builds a safe, isolated environment for detonating and analyzing malware using virtualization, host-only or simulated networking, and snapshotting. Activates for requests about creating a malware lab, sandbox VM, isolated analysis environment, or safe detonation setup.
日本語の概要は準備中です。原文の説明を表示しています。
The measurement surface for ALL Pulp DSP and audio-pipeline work — read it BEFORE writing or gating DSP, not only when something already sounds wrong. Covers the C++ harness (signal generators, metrics, assertions, RenderScenario, contracts), the offline Audio Doctor (magnitude/frequency response, THD/THD+N, phase/group delay), and their Python sibling the Audio Quality Lab (tools/audio/quality-lab — null residual + alignment, LTAS log-spectral distance, spectral flux/centroid, HNR, Theil-Sen drift slope, Kaiser-sinc resampling, license-guarded corpus, regression-net ratchet). TRIGGER on AUTHORING work — "build/design an oscillator/filter/synth/effect", "add a DSP module", "what should the acceptance gate be", "how do I measure aliasing / anti-aliasing / alias floor", "null against a reference", "is this DSP correct", "choose a tolerance", "golden/regression corpus for audio", "measure drift or jitter", "A/B two renders" — AND on DEBUGGING work — "is there sound / no audio / I hear nothing", "does this filter/compressor/synth/delay produce the right signal", "prove the DSP / prove the contract", "measure the frequency response", "what's the THD / is it distorting", "what's the group delay / phase response / measured latency", "magnitude response curve", "render a test tone and assert", "audio regression", "64-frame works but 128 is silent", "sample-rate change pitch-shifted it", "describe what's in this buffer", "audio doctor", "compare before/after a DSP refactor". Reach for this BEFORE hand-rolling any FFT, null test, alias measurement, pitch tracker, or golden-render script — most of it already exists in one of the two lanes. Test/tool layer over HeadlessHost — deterministic, no audio device, no speakers. Off the realtime thread entirely.
日本語の概要は準備中です。原文の説明を表示しています。
Building and shipping a Forge app (Modular, Instrument, MIDI, FX, and the sequencer work to come) as a signed installer somebody else can actually use. Covers the seam between the Forge and Pulp repos, what a green signal does and does not prove, shipping the runtime rather than only the binary, and the wiring gaps that make a finished feature behave like a missing one.
日本語の概要は準備中です。原文の説明を表示しています。
Work in Pulp's bounded JSFX lane using source-only examples, subset validation, and explicit exclusions like no `@gfx`.
日本語の概要は準備中です。原文の説明を表示しています。
Research, author, validate, render, and archive data-only Pulp Sample Heritage profiles. Use when creating or revising a sampler character profile, importing or exporting Heritage JSON, proving profile behavior with analytic and listening fixtures, recording evidence and trademark-safe provenance, or preparing a caller-owned profile artifact bundle.
日本語の概要は準備中です。原文の説明を表示しています。