364건 · 관련도순
Generate 15–20 research directions from a question, topic, or data opportunity, then narrow them to 5–7 candidates. Receive ranked ideas with feasibility assessments, key risks, confidence scores, and reasons for rejecting the others.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Review OpenAPM specification changes through four specialist perspectives covering schemas, registries, dependency resolution, and web architecture. The skill combines findings and mechanical checks into one advisory comment, separating immediate fixes from work deferred to later versions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Review pull requests, branches, or uncommitted changes across eight areas, including security, correctness, and tests. Verify findings against the code, group problems by type, and assess whether the change needs redesign or smaller fixes.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Get a second opinion from Google Gemini on Google Ads, SEO metadata, or code changes. Choose a pass/fail review, a challenge that probes weaknesses, or an open consultation on strategy and implementation.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Understand how unfamiliar code works from a security perspective. The skill maps architecture, follows untrusted input through the code, and searches for similar vulnerability patterns, with file and line references to support static analysis and finding validation.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Test changed screens or explore an entire app in a real browser. Check interactions, accessibility, and mobile layouts, then document failures with screenshots, reproduction steps, expected results, and suggested fixes.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
The rules the reference agents enforce in code for third-party content, writes, grounding, identity, and memory, each with its module, plus two adversarial-eval rules. Load when handling untrusted tool results, guarding a write tool, or scoping what an agent remembers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this variant) — prefer that skill unless you explicitly want this one. Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy terms, stress-testing with concrete scenarios, cross-referencing code, and updating CONTEXT.md + ADRs inline as decisions crystallise. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-with-docs-codex", "grill me against the docs then have codex review", "stress-test this against our domain model then get a second model on it", or is about to build something high-stakes in a project with established terminology/ADRs and wants alignment, documentation, AND a cross-model sanity check. Builds on Matt Pocock's grill-with-docs (MIT). NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Discipline for the seam between two SDKs (or two sides of one contract) that the same hand writes. The failure mode: "we own both sides" produces dirty contracts no foreign reviewer would accept. The exercise: pretend the other side is FFI, IPC, or a network protocol you cannot rewrite. Spawn an adversarial subagent profiled as the producer's maintainer; negotiate the change as a feature request, not a PR. Companion to $sdk-design. Language-agnostic — applies to a TS package + its consumer, a Rust crate + its WASM binding, two services sharing a wire format, or any other boundary the same author writes both ends of.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this for "design a landing page", "build a settings screen", "make me a website", "design the onboarding", "ออกแบบหน้าเว็บ", "ทำหน้า landing", "ออกแบบ UI", "ทำแอป". It runs the pipeline no single skill covers: the house doctrine, a written Brief Inference so the result is not the statistical mean, a committed visual direction, tokens, build, the objective gates, then an adversarial critic. Hands off to data-dashboard for dense data screens, redesign for existing UI, and image-to-code when a reference image is given.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Verify a WordPress plugin's Abilities API registrations: enumerate abilities, check that callback behavior matches each annotation's claim (the adversarial readonly-but-writes detection), validate permissions and schemas, and validate audit documents produced by wp-abilities-audit.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Fail closed on published draft XQUIC code pull requests before ready-for-review state. Use when asked to pre-review a code PR or move it out of draft; verify current base-to-head code, protocol conformance, validation coverage, adversarial bad cases, hot-path performance, and memory safety in a five-part local report.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Adversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Adversarial visual-layout audit of a Quarto `.qmd` or Beamer `.tex` deck. Flags overflow, font inconsistency, box fatigue, spacing, and alignment issues. Use when user says "visual audit", "check the layout", "does this overflow?", "look for visual issues", "audit the slides", or after reworking a deck's appearance. Does NOT check writing or pedagogy — pair with `/proofread` or `/pedagogy-review`.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.