2.4K skills · sorted by relevance
Cloudflare Pages and Workers deployment checklist for wrangler deploys, secret audits, D1 migrations, Worker-compatible SDK checks, and browser-auth verification. Use when shipping Cloudflare changes to production. NOT for general CI/CD architecture, non-Cloudflare deployments, or post-launch UX QA.
The English summary is being prepared. Showing the original description.
Practical incident-response runbook for a suspected or confirmed ComfyUI / GPU-daemon compromise. Triage, scope, contain, forensic collection, weight-integrity verification, rebuild from clean snapshot, postmortem. NOT for hygiene scans on a healthy box (use supply-chain-defense-for-ml-extensions), and NOT for runtime hardening of a fresh deployment (use gpu-hosted-asset-hardening).
The English summary is being prepared. Showing the original description.
Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.
The English summary is being prepared. Showing the original description.
Frame multi-agent designs through explicit environment, autonomy, information, coordination, commitment, incentive, and verification assumptions. NOT for endorsing multi-agent architecture without need or claiming runtime correctness from conceptual methods.
The English summary is being prepared. Showing the original description.
Audit a compliance-ladder design (C0-C6) and transcript-fidelity ladder (T0-T5) plus their adapter conformance fixtures — Codex, Claude Code, Cloudflare, Ollama/LM Studio, custom stdio/HTTP agents — for the two failure modes that make a C-badge or T-fidelity label a lie: the ladder disagreeing with itself across doc/schema/ui/probe surfaces, and a level being reachable by self-report because no daemon-witnessed negative probe actually tries to forge it. Use when designing or freezing a compliance ladder, wiring an adapter conformance probe suite, deciding whether a numeric C-badge or T-label is safe to ship, or investigating a self-attestation or observed-to-controlled bypass risk. NOT for auditing a cryptographic protocol or whitepaper for adversarial soundness (`redteam-review`), writing TLA+/formal invariants for a daemon monitor (`runtime-verification-for-agents`), or agent identity, successor linkage, and reputation across restarts (`agent-identity-continuity-reputation`).
The English summary is being prepared. Showing the original description.
Design a normalized, machine-readable "work receipt" that answers what changed, why, by whom, and with what validation, for any AI-coding-agent task regardless of backend (Claude Code, Codex, Cursor, Aider, CI, or homegrown). Use when defining a receipt schema, normalizing heterogeneous agent logs into one evidence shape, gating PR merges on artifact-backed proof, or designing an OSS maintainer's fast-reject/fast-merge workflow. NOT for validating a DAG node's output against its own schema (use output-contract-enforcer), continuous runtime monitoring of a live coordination daemon (use runtime-verification-for-agents), or general Port Daddy claims/notes/salvage mechanics (use port-daddy-agent-skill).
The English summary is being prepared. Showing the original description.
Analyze a Coval adversarial / red-team testing report and turn it into an agent-hardening plan. Use when a user provides a Coval report URL, report export, run IDs, screenshots, or a per-scenario scorecard from an adversarial sweep and wants evidence-backed next steps such as prompt/guardrail changes, refusal hardening, verification fixes, escalation routing, or expanded attack coverage.
The English summary is being prepared. Showing the original description.
Maps intelligence for local SEO: geo-grid rank tracking, GBP profile auditing via API, review intelligence across Google/Tripadvisor/Trustpilot, cross-platform NAP verification, competitor radius mapping, and LocalBusiness schema generation. Three tiers: free (Overpass + Geoapify), DataForSEO, and DataForSEO + Google. Use when user says "maps", "geo-grid", "rank tracking", "GBP audit", "review velocity", "competitor radius", or "SoLV".
The English summary is being prepared. Showing the original description.
Extract exactly what the person typed in a Claude Code session (script, no agent context spent), have a fresh agent write a faithful structured summary under it, and optionally have an adversarial agent judge whether the working agent is still on track. Use at a checkpoint, before a handoff, after a compaction, when a long session may have drifted from what the owner asked, or when told to 'summarize what I said' or 'check we're on track'.
The English summary is being prepared. Showing the original description.
Real tests: a fresh agent walks the live product against sealed checks proven to catch a planted break. Use when told to use safety-net, to check whether an area really works now, or around a change too wide for one agent to see every break. NOT for one automated test (use forcing-function-tests).
The English summary is being prepared. Showing the original description.
Delegating work down to subagents: briefs, report statuses, independent review. Use when writing an implementer or verifier brief, dispatching a subagent to build, fix, or verify work you own, or a subagent reports DONE, blocked, or concerns. NOT for campaign-scale doctrine (use campaign-pattern).
The English summary is being prepared. Showing the original description.
Run the full on-track check on a conversation, project, or keyword the owner names: find the sessions, extract exactly what he typed, dispatch independent judges who go to the live product as him and report what was missed, plan the remedy, and return one page — what he will see, what is missing, the plan. Use when told to check whether work is on track, to audit a project that has drifted, on 'run the on-track check on X', or when a long campaign is about to freeze, hand off, or claim done.
The English summary is being prepared. Showing the original description.
Working playbook preloaded into the reviewer helper; the coach updates its Lessons after each round. Use only when acting as reviewer or coaching it. NOT for writing a verifier brief (use subagent-dispatch).
The English summary is being prepared. Showing the original description.
End-to-end execution of a scouted third-party provider access campaign. Use when a Provider Access Launch task is ready_to_submit or scouted easy_execute and needs account or app registration, scopes, reviewer assets, Vault credential custody, the canonical connection, and real verification.
The English summary is being prepared. Showing the original description.
Pre-commitment attack on a plan by an agent that did not write it. Use when presenting a feature-deep-dive plan, assigning vision-to-fleet briefs, moving a register to build mode, ratifying a scope list, or coding a new contract or table. NOT for built work or DONE reports (use subagent-dispatch).
The English summary is being prepared. Showing the original description.
The bar every automated test or guard must clear: green only when the real system works. Use when writing, fixing, or reviewing a test, mock, stub, fixture, snapshot, or self-test; adding a regression test for a bug; or about to call work done because tests pass.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "PR を出す前に確認して", "check if this branch is ready to merge", "run pre-PR checks", "PRを作る前にチェックして", or wants to verify a branch before opening a pull request. Executes verification commands, validates Conventional Commits format, and confirms documentation is updated, then reports whether gh pr create is safe to run.
The English summary is being prepared. Showing the original description.
Spring Bootプロジェクトの検証ループ：ビルド、静的解析、カバレッジ付きテスト、セキュリティスキャン、リリースまたはPR前の差分レビュー。
The English summary is being prepared. Showing the original description.
Claude Codeセッションのための包括的な検証システム。
The English summary is being prepared. Showing the original description.
Laravelプロジェクトの検証ループ — 環境チェック、リンティング、静的解析、カバレッジ付きテスト、セキュリティスキャン、デプロイメント準備。
The English summary is being prepared. Showing the original description.
Djangoプロジェクトの検証ループ：マイグレーション、リンティング、カバレッジ付きテスト、セキュリティスキャン、リリースやPR前のデプロイ準備チェック。
The English summary is being prepared. Showing the original description.
Consult Claude Code from Codex for a second opinion while Codex remains responsible for implementation and verification. Use when the user asks Codex to collaborate with Claude, consult Claude, ask Claude for a plan, get a Claude review, delegate analysis to Claude, or says "Claudeと一緒に", "Claudeに相談", "Claudeにレビューしてもらう", "Claudeの意見も聞く", or "Claudeと計画を立てる". Also use when an explicit independent planning or review pass from Claude would materially reduce risk on a complex coding task.
The English summary is being prepared. Showing the original description.
Use when a running Spark or DSH web service needs real-browser verification — page load, client-plugin boot errors, console errors, failed requests, or onboarding/dialog rendering — with the repository's own Playwright chromium.
The English summary is being prepared. Showing the original description.
[21] UNDERSTAND. Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and structured investigation notes. Use when the task requires investigation, root-cause analysis, or mapping unknown areas. Always maintain a research log file that captures findings, hypotheses, and next branches; use web.run when external verification is needed.
The English summary is being prepared. Showing the original description.