「each」の検索結果

Phase 3 of the feature-pipeline suite. Use this after /fp-plan has received explicit user approval and printed the M2-plan stop hook — when you need to translate an approved numbered plan into committed, pushed code. Triggers on: "implement the plan", "start coding", "commit the plan", "write the code", "fp-implement", "Phase 3", "plan is approved let's code", "next step after plan", "execute the plan", "apply the plan", "make the changes". Reads planApproved and branch from state; refuses to run if approval hasn't been recorded. Commits one atomic change per plan step, pushes after each commit, handles obstacles cleanly, and hands off to /fp-review when done. Never squashes or skips steps — the one-commit-per-step rule keeps the review history readable and rollback surgical.

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。

Fixed-topology, discovery-only extension for Gaia curation. Atomically checkpoints each candidate transition, retries only the failed field, 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。

Multi-agent exploration-to-PR pipeline for safely exploring, fixing, and shipping a feature or CLI. Use when the user says: "explore X", "test and ship X", "run the pipeline on X", "run /feature-pipeline on X", "let's properly investigate X", "stress-test X and file issues", or "take X through the full pipeline." Also triggers on: "find what's broken in X", "test X end-to-end", "do a sandbox review of X", "file issues for X and fix them." Do NOT use for single-file bug fixes or one-off edits — the overhead is only justified when exploration, planning approval, and CI watching all matter. Manages state via scripts/state.sh (jq required). Five phases: LIGHTER explores → ORCHESTRATOR drafts PR → HEAVIER plans (user approves first) → ORCHESTRATOR commits → HEAVIER sandbox review → LIGHTER iterates CI → LIGHTER drift check + summary. Four mandatory stop hooks (M1–M4) gate each phase transition.

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。

Produce the rendered evidence a human-gated frontend PR owes its reviewer: capture each changed surface (plus the before state for anything modified, plus mobile width), then generate one self-contained local HTML page the founder can open and review without checking anything out. Use when a PR is gated by the "Frontend changes are HUMAN-GATED" section of CLAUDE.md, or when the user says "/design-gate", "screenshot evidence for this PR", "prep this for founder review", "build the design evidence page", "what does this look like before and after". The page comes from a template script, not hand-written markup. Output is session-local and never committed. Do NOT use for non-gated changes: typo/grammar/factual fixes in an unchanged block, dead link targets, alt/ARIA fixes with no visual change, cache-bust bumps, or refactors with no rendered diff.

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。

One-fix-at-a-time, approval-gated design fix recovery. Given a checklist of fixes (handover doc, CHECKLIST.md, or inline list), applies each individually, presents a diff, and waits for an explicit APPROVE / REJECT / NO CHANGES decision before committing. Trigger phrases: /design-iteration, "go through the checklist one by one", "fix these one at a time", "bucket recovery", "design fix pass".

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。

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。

Builds a stylized 3D animated ad on the Novoads REST API as a STORYBOARD: four to six beats, each rendered from its own key frame, narration laid into the gaps, a music bed, captions burned on, assembled locally with ffmpeg. Carries the genre's beat formulas (anthropomorphized problem character, protagonist reveal, mascot mechanism scene, composited end card). Use for ANY Pixar-style, Disney-style, 3D animated or animated-film-look ad at ANY length: "Pixar style ad", "3D animated ad", "animated movie look", "cute 3D character ad", "a quick animated ad", "15 second animated ad", "30 second animated ad", "storyboard ad", "several scenes", "animated ad with a voice-over", "little mascots", or a product URL or photo for an emotional animated spot. No one-call tier, so ffmpeg is required. Not for stop-motion clay (use claymation-ad), talking-head UGC (novoads-api), video cloning, or static image ads.

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 hand-sculpted stop-motion CLAY ad on the Novoads REST API as a STORYBOARD: five to eight beats, each rendered from its own key frame, a storyteller narration laid into the gaps, a music bed, captions burned on, assembled locally with ffmpeg. Carries the genre's arc (named protagonist, inciting moment, social beat, quiet despair, sculpted clay infographic, discovery, transformation, resolution card), and also recreates a found clay ad by reading the reference video locally with ffmpeg and Whisper. Use for ANY clay or stop-motion ask at ANY length: "claymation ad", "stop-motion ad", "clay ad", "a quick clay ad", "plasticine characters", "make an ad like this clay one", or a reference video with sculpted clay characters in it. There is no one-call tier here, so ffmpeg is required. Not for the smooth 3D animated look (use pixar-ad, which covers every Pixar-style length), talking-head UGC (novoads-api), or a static image ad.

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。

Divergent ideation across model families — the same brainstorm, but each cognitive frame is handed to a different model (Claude sub-agent, OpenAI Codex, a cheap third via OpenCode) so the ideas diverge by frame and by model priors at once. Use for open design questions, architecture and API shape, naming, schema choices, fuzzy bugs with no known root cause, or on "multi adhd", "brainstorm with everyone", "wide ideas from all models". Skip for lookups, syntax, and anything phrased as "quick", "standard" or "canonical".

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。

Audit essays, reports, literature reviews, dissertations, proposals, and source-backed assignments for high-score academic quality. Use when the user asks whether a paper can get a high grade, wants teacher/rubric feedback addressed, needs a pre-submission review, or needs checks for strict rubric compliance, academic standards, prompt/rubric alignment, argument quality, comparative analysis, evidence hierarchy, table/figure integration, citation specificity, conclusion strength, academic language, source-claim integrity, or evidence boundaries.

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。

Audit a prompt the user is about to send to Claude (or another coding AI) for completeness and effectiveness. Use this skill whenever the user shares a prompt and asks for feedback — phrases like "is this prompt good", "audit my prompt", "review this prompt", "will Claude understand this", "improve this prompt", "is this enough context". Also trigger proactively when you notice the user is about to dispatch a vague, under-specified, or over-constrained prompt for non-trivial work. Checks the 6 essential elements (goal, scope, existing patterns, constraints, verification, done definition), flags what's missing, explains why each gap matters, and produces an improved rewrite. Treat this skill as the litmus test for "Be Claude's PM" — if the prompt fails the audit, the work that follows will probably fail too.

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。

Use when the user wants to be taught an Anthropic product or feature - "teach me Claude Code", "learn Cowork", "academy lesson", "train me on MCP or the Claude API", "quiz me", "next lesson" - or asks for structured learning rather than a one-off answer. Covers Claude Code, Claude.ai, Cowork, Tag, Platform/API, and AI Fluency. Do NOT use for auditing how the user already works (use academy-review) or for mid-task help where the user just wants their task done.

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。

Validates detection coverage by mapping Atomic Red Team tests to ATT&CK techniques, checking which of your detections cover each tested technique, and reporting coverage gaps. Activates for requests to validate detections with atomic tests, map Atomic Red Team to coverage, or find detection gaps against tested techniques.

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。

Uses x64dbg to dynamically debug Windows malware: setting strategic breakpoints on APIs, stepping through unpacking and decryption, dumping memory at the right moment, and manipulating execution to reach hidden code. Activates for requests to debug malware with x64dbg, set API breakpoints, or step through unpacking in a debugger.

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。

Rebuild, re-pin, and republish Pulp's downstream demo/example repos against a new or the latest SDK. Routes natural-language requests — "update the demos to the latest SDK", "rebuild the examples against the new SDK", "check the demos still build on the new SDK", "bump every consumer's SDK pin", "open the SDK-update PRs", "republish the demo packages" — to the `pulp minos` Managed SDK Consumer Sweep: `sweep` (build + measure min-OS floors), `update` (bump each repo's SDK pin, open PRs), and `publish-runbook` (per-repo rebuild/package/publish steps).

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。

Keep a plugin/demo repo's screenshots in sync with its UX. When editor / UI / design-token code changes in an opted-in repo (one carrying .pulp/screenshots.toml), re-capture and refresh every place each shot is consumed — README images, web-demo Open Graph (og.png) images, and gallery thumbnails — consistently across the WAM and WCLAP demo sites. Two capture routes: native headless (render_to_png / pulp-screenshot, Skia) for README / native-editor shots, and live-web headless Chrome (playwright-core) for WAM/WCLAP demo OG + gallery images. Backfills demos missing OG images. This is a PORTING / consistency tool — it re-shoots a repo's OWN UI, it never clones another product's art.

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。

Debug or validate Pulp animations / transitions / scroll behavior using in-process motion fixtures and offline visual analysis. TRIGGER on phrases like "animation is wrong", "transition timing off", "fade too late", "card slides too far", "scroll jumps on restore", "scroll offset wrong on restore", "frame jump in the timeline", "easing looks wonky", "imported Figma motion doesn't match source", "settle time / overshoot / drift / monotonic", "what value does the knob reach at frame N", "record this animation so I can replay it", "this animation is expensive — which one and why", "reduced-motion broken", "scrub a captured fixture". Captures fixtures (.motion.jsonl), and ships assertion helpers (is_monotonic / settling_time_seconds / overshoot / start_delay_seconds / final_value / local_step_outlier_ratio) and the `scroll_geometry` trace for `ScrollView` content-offset / visible-rect / content-size observability. Off by default in prod.

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。

Judge whether a change made things better with demonstrable proxy measures tied to the mechanism it targets, not wall-clock time. Load before choosing acceptance measures for any before/after or A/B claim — CI and fleet speed-ups, build speed, DSP/audio quality, render fidelity. Each proxy names its data source, detection floor and sample size, and every zero is paired with a control on the same instrument.

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。

Teach models new tasks from a handful of examples — prompting strategies, example selection, and in-context learning mechanics.

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。

Reach and sustain inbox zero: triage workflows, filters, templates, batching, and unsubscribing systems. Use when email eats your day or your inbox has become an anxiety source.

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。