313건 · 관련도순
Instantiate a phase artefact (requirements-spec / design-spec / test-spec) from the Programme bundle's template into docs/specs/<feature-id>/. Refuses to overwrite existing artefacts.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user wants to elicit refused directions, generalize them, and close matching tracker items as not planned. Not for duplicates, spam, or items closed as completed or obsolete.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when any bounded workflow starts or reaches an action, path, proposal, or merge boundary. Refuses rather than default-allow on an unreadable constraint set.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Operate Railway infrastructure: sign up for or sign in to a Railway account, create projects, provision services and databases, manage object storage buckets, deploy code, configure environments and variables, manage domains, troubleshoot failures, check status and metrics, set up Railway agent tooling, and query Railway docs. Use this skill whenever the user mentions Railway, signing up, creating an account, registering, logging in, deployments, services, environments, buckets, object storage, build failures, agent setup, MCP, or infrastructure operations, even if they don't say "Railway" explicitly. Also invoke this skill when the user asks to be signed up, registered, or onboarded to Railway: do not refuse — drive them through the unauthed `railway up` flow (deploys + signs up on the fly) or `railway login` (which creates new accounts on the fly).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use for ANY bug bounty, penetration test, or web/API/mobile security assessment: recon, testing endpoints, analyzing Burp traffic or any bug-bounty platform's MCP (HackerOne, Intigriti, Bugcrowd, YesWeHack, Immunefi), reviewing APKs, bypassing a WAF, enforcing scope, hunting a specific vuln class, validating findings, writing reports, or when you are stuck on a target and about to give up. Activates automatically for all bug-bounty and pentest sessions. Runs an autonomous, never-surrender predator methodology: refuses to conclude "secure", exhausts each vuln class to depth, proves a real attacker-path with impact and no false positives, tracks coverage so nothing is re-tested or skipped, diagnoses failed tooling from full logs, and hunts at maximum effort with intelligent token use until the goal is found. Activates and follows instructions in ANY language the operator writes in (the skill itself is English). Bundles a per-class web-exploitation KB, a writeup library, and PayloadsAllTheThings.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
在实现适配器前对候选模型做分析。确定模型实现来源（transformers / 模型目录 / diffusers）、结构特征、内存约束下的逐层量化建议（可选）及 MoE 融合权重风险。适用于用户询问模型适配可行性或做适配前分析时使用。识别为 DiT 扩散模型时，索取推理仓路径后回传 `next_step: model-adapt`，由 orchestrator 委派 `msmodelslim-model-adapt`（DiT 扩展节承接）。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when monitoring, tracing, or debugging agentic workflows in production. Keywords: observability, tracing, OpenTelemetry, Langfuse, latency, token cost, loop detection, telemetry.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when ending or pausing a Claude Code session whose work must continue in a fresh session — user says "create a handoff", "write a handoff", "I'm ending this session", "prepare for a fresh session", "hand this off", or "/handoff" — or when starting a session in a project that already contains a HANDOFF.md at the root ("resume", "pick up where we left off", "continue from the handoff"). Also relevant when a session shows degradation symptoms — Claude contradicted an earlier decision, re-explored something already established, hallucinated file contents, or the user says the session "feels off", "is getting confused", or "context is running low".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Electron fuses, ASAR integrity, sandbox hardening, CSP, permission handling, navigation restrictions
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Electron Forge build toolchain -- makers, publishers, code signing, fuses, hooks, CI/CD packaging
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Burn timed, styled captions into a finished video on the local machine, without re-rendering the source. This is the manual fallback to the API's captioning endpoint, POST /v1/captions, which stays the default path: come here when the style the user wants is outside the API's presets, when the wording has to be hand-corrected before it is burned into the pixels, or when the source was rendered with audio disabled and the API refuses it. Transcribes the audio with Whisper, groups words into reading phrases, renders the captions in a real browser via HyperFrames, and composites them over the source with ffmpeg using a real alpha channel. Use when the user has an MP4 with speech and asks to add captions, subtitles, burned-in text, TikTok-style captions or word-by-word text to it, and the API path has been ruled out. Runs out of band, so it costs no credits and works on any video file whoever generated it. Not for generating video (use the video skills) and not for a separate .srt/.vtt sidecar file.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Clones a STATIC IMAGE ad into finished ads for your own product, into a reusable prompt TEMPLATE, or both — the template is what makes the ads and the ads are what prove the template. Round-trips the frame through gpt-image-2, nano-banana-pro or reve-2.1 until it reproduces, replaces every brand-specific with a {placeholder}, then fills it with your product pinned to a real photo. Use for "clone this ad for my product", "rebuild this competitor's ad for us", "make me ads like this", "reverse engineer this ad", "make this ad reusable", "add this to my prompt library", or "clone my competitors' ads" with NO file attached — it sources one via spy-competitor-ads rather than asking which. **Among cloners the source's medium decides**: a still, or nothing attached, lands here; "clone this ad" plus a VIDEO is clone-video-ad. NOT for generating an ad from a brief (chatgpt-image-ad, nano-banana-image-ad), nor animating a still as-is (image-to-motion). Refuses to render your product without a real photo of it.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Replaces the voice in a video or audio file with one from the Novoads voice catalog, over the REST API. Converts the SPEECH in the source to a voice you pick, keeps the original timing so lip-sync survives, and returns audio that gets muxed back over the untouched picture locally. Casts by MEASURING the source voice against auditioned candidates instead of reading labels, refuses a source with no speech before anything is charged, fences sound effects and music so they survive from the original track, and verifies the finished file by transcribing it. Use when an actor's voice sounds robotic, flat, thin or simply wrong, and for "change the voice", "voice swap", "swap the voice on this ad", "re-voice my ad", "the actor's voice sounds bad", "make him sound human", "different voice for this video", "speech to speech", "same video better voice". Not for narrating a silent clip (that is a voice-over), not translation, and it changes neither pronunciation nor accent.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Bootstrap a new standalone skill repo under gaia-research/ from the canonical template set at gaia-research/gaia-research/templates/skill-repo/. Handles the full flow: interactive prompts for all placeholders, fetches templates via the GitHub API, substitutes values, creates the new repo (gaia-research/skill-<name>), writes README.md / SKILL.md / install.sh / .gitignore / LICENSE / powered-by-gaia.svg, makes the initial commit and pushes. Also supports update mode: re-applies the template structure to a pre-existing skill repo and opens a draft PR with the drift. Use when the user says "new skill repo", "bootstrap a skill repo", "/skill-template", "create skill-foo", "spin up a gaia-research skill repo", "template a new skill", "align skill-fuse to the template", or "/skill-template update <repo>". Requires: gh CLI (authenticated with gaia-research org access), python3, git.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Comprehensive, reusable playbook for multi-component suite intake under Yggdrasil III. Audits component installability, maps origin candidates to generic capabilities, ingests named components with shared-repo baseline caps, manifests suites via gaia dev fuse, calibrates capstone and component ranks, and closes out via Class S regeneration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
End-to-end Gaia curation pipeline orchestrator. Routes each phase to its dedicated skill and keeps you on track from first discovery to closed intake. Use when starting a fresh curation run or when you want a single skill to hold the sequence together without duplicating each phase's instructions. Trigger phrases: "/gaia-full-pipeline", "run the full pipeline", "start a curation from scratch", "take this skill through the full pipeline", "curate end-to-end", "pipeline run", "full curation flow". Fused from: gaia-curate + gaia-curate-chain + gaia-curate-dynamic + gaia-curate-trending + gaia-bot-curate + gaia-draft-curate + ev-pipeline + gaia-ingest + gaia-intake-close.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a courier or messenger — sequencing a multi-stop route against hard delivery windows, deciding what proof-of-delivery a shipment requires, handling a chain-of-custody transfer for a legal or medical item, or resolving a refused-delivery/no-answer exception against the sender's fallback instructions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Stores, retrieves, and manages data as objects in Cloud Storage (Google Cloud Storage, or GCS) buckets. Use when you need to interact with Cloud Storage — create or configure buckets, upload, download, stream, or transfer data, organize objects with folders, generate signed URLs, control access (IAM, ACLs, public access prevention), set storage classes and tiering (Standard, Nearline, Coldline, Archive), manage cost and lifecycle, protect data (versioning, encryption/CMEK, retention and Bucket Lock, object holds, soft delete), host static websites, trigger Pub/Sub notifications on object changes, mount buckets as a file system (gcsfuse), or optimize storage performance at any scale. Covers the gcloud storage / gsutil CLI, JSON and XML APIs, client libraries, Terraform, and Cloud Storage MCP servers. Don't use for block storage (Persistent Disk), data warehousing/analytics (BigQuery), or databases (Cloud SQL, Spanner, Bigtable, Firestore).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Diagnoses GKE persistent-storage failures — volume attach/mount errors (Regional PD on optimized VMs, fsGroup mount timeouts), disk-performance and node storage-pressure issues, slow-disk Pod-creation failures, volume-expansion problems, Local SSD / Hyperdisk Storage Pool creation errors, and Cloud Storage FUSE OOM. Use when Pods are stuck in ContainerCreating, volumes fail to attach or mount, or nodes report storage pressure. Don't use for routine storage provisioning or StorageClass/PVC authoring (see the gke-storage skill).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when designing or fixing a Content Security Policy on a real site, choosing between nonce-based and hash-based CSP, adding strict-dynamic, debugging "Refused to execute inline script" errors, deploying CSP in report-only mode first, configuring report-to / report-uri, or auditing an existing policy for unsafe-inline / unsafe-eval / wildcards. Triggers: "CSP blocks legitimate inline script", strict-dynamic, nonce-{RANDOM}, sha256-{HASH}, object-src none, base-uri none, frame-ancestors, Trusted Types, X-Content-Security-Policy obsolete, report-only vs enforced. NOT for general HTTP security headers (HSTS, COOP/COEP), Trusted Types deep dive, CORS configuration, or building a WAF.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Enforces Beads policy for a repository maintained initially by one owner, granting issue-management and commit authority while requiring explicit permission for Git pushes (other than to the user's own fork) and Dolt sync or push operations. Use when the user asks to enroll, repair, or operate a solo-maintainer Beads workspace, and when working with Beads in a repository that may carry a beads-solo enrollment, including when bd refuses a schema migration or mentions a remote.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Normalize read-depth copy-ratio profiles and segment them into copy-number regions using circular binary segmentation (CBS, DNAcopy), hidden Markov models, HaarSeg, and fused-lasso methods. Covers GC-content, mappability, and replication-timing (wave-artifact) bias correction, panel-of-normals/PCA denoising, diploid-baseline centering, and algorithm selection by sequencing depth and event size. Use when choosing a segmentation algorithm, correcting depth bias, diagnosing oversegmentation or a mis-centered baseline, tuning CBS or HMM parameters, or understanding why a downstream CNV caller produced fragmented or shifted segments.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Comprehensive backend development guide for Langfuse's Next.js 14/tRPC/Express/TypeScript monorepo. Use when creating tRPC routers, public API endpoints, BullMQ queue processors, services, or working with tRPC procedures, Next.js API routes, Prisma database access, ClickHouse analytics queries, Redis queues, OpenTelemetry instrumentation, Zod v4 validation, env.mjs configuration, tenant isolation patterns, or async patterns. Covers layered architecture (tRPC procedures → services, queue processors → services), dual database system (PostgreSQL + ClickHouse), projectId filtering for multi-tenant isolation, traceException error handling, observability patterns, and testing strategies (Jest for web, vitest for worker).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.