테스트·보안 스킬

Treat tokens as a coding swarm's cost-of-goods-sold and legibility engine while accounting for finite subscription allowance when per-call price is unknown. Covers provider windows, remaining-usage evidence, burn forecasts, preemptive checkpoint/model switching, per-agent budgets, compaction, shared digests, context degradation, and spend metering. Activate on: "token budget", "context budget", "compaction strategy", "briefing as compression", "context rot", "summarization collapse", "COGS for agents", "subscription usage remaining", "five-hour or weekly limit", "burn forecast", "model switch before limit", or "/context-economics-for-agent-swarms". NOT for: memory architecture (use always-on-agent-architecture), single-prompt wording (use prompt-engineer), mechanism-design proofs (use nisan-et-al-2007-algorithmic-game-theory), physical containment (use sandboxed-adversarial-test-harness), or production rebodiment and fencing (use agent-resurrection-and-body-continuity).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build, debug, optimize, and deploy ComfyUI workflows for diffusion image, video, and audio generation. Activate on: ComfyUI workflow, ComfyUI custom node, ComfyUI API, ComfyUI Manager, KSampler, FLUX in ComfyUI, Wan 2.2 ComfyUI, Hunyuan video ComfyUI, LTX video ComfyUI, IPAdapter, ControlNet ComfyUI, Kijai wrapper, ComfyDeploy, RunComfy, ComfyUI security, GGUF quantization, TeaCache, Nunchaku, ACE-Step ComfyUI, F5-TTS ComfyUI, subgraphs ComfyUI. NOT for: A1111/Forge/Invoke (different UIs), training pipelines from scratch, non-diffusion ML models, or general image-API integrations (use generative-video-2026 / generative-music-audio / media-gen-deployment).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects and fixes color contrast violations using WCAG 2.1 guidelines and perceptual analysis. Expert in contrast ratio calculation, color blindness simulation, and providing accessible alternatives. Activate on "check contrast", "color accessibility", "WCAG audit", "readability check", "contrast ratio", "hard to read", "can't see text". NOT for general color theory (use color-theory-palette-harmony-expert), brand color selection (use web-design-expert), or non-visual accessibility (use ux-friction-analyzer).

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.

Build production computer vision pipelines for object detection, tracking, and video analysis. Handles drone footage, wildlife monitoring, and real-time detection. Supports YOLO, Detectron2, TensorFlow, PyTorch. Use for archaeological surveys, conservation, security. Activate on "object detection", "video analysis", "YOLO", "tracking", "drone footage". NOT for simple image filters, photo editing, or face recognition APIs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit LLM token cost estimates against actual API usage. Activate on 'cost verification', 'token estimate accuracy', 'API cost audit', 'estimation variance'. NOT for pricing lookups, budget planning, or cost optimization strategies.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

App Store and Google Play submission automator with Fastlane, screenshot automation, metadata management, and TestFlight/internal testing. Activate on: app store submission, Fastlane, TestFlight, Google Play Console, screenshot automation, metadata management, app review, code signing, provisioning profiles. NOT for: CI/CD pipeline setup (use github-actions-pipeline-builder), app architecture (use react-native-architect), analytics (use mobile-analytics-crash-reporting-expert).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Own whether a multi-document product-architecture binder is internally consistent, complete against its stated customer/contingency/architecture coverage, and honest about which older product ambitions it has absorbed, superseded, deferred, contradicted, orphaned, or rejected. Use when running a binder Architect of Record pass, before an implementation chain cites a binder chapter as ready, when a proof-gate owner is missing, or when reconciling the binder against the older ambition corpus (website, plans, examples, ADRs). NOT for auditing a single Claude Skill bundle's structure or frontmatter (use skill-hygiene), rendering a single-PM accept/reject verdict on one finished deliverable (use port-daddy-user-surrogate-pm-review), or sequencing/stewarding a roadmap's sidequests once a gap or operator decision has been surfaced (use legible-roadmap-with-sidequests).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audits an Articles of Agreement contract — the daemon-witnessed agreement every official Port Daddy agent signs covering registration, transcript reporting, tool-use gating, file claims, parley conduct, budget limits, and operator control — against the enforcement-beats-hope bar: a clause counts as safe only when it resolves to a concrete, daemon-observable mechanism with a defined denial shape, never a promise the agent might honor. Use when drafting a new agent's Articles, reviewing a compliance-level (C0-C6) claim, deciding whether a clause is genuinely enforced or merely documented, or auditing whether an agent's claimed identity can be trusted. NOT for securing the inbound event-to-spawn path (fleet-event-spawn-trust), designing the relay's transport PKI and signing keys (pd-relay-zero-trust), or tracking an agent's identity and reputation across its whole lifetime after it signs (agent-identity-continuity-reputation).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan or audit the cross-layer Harbor cooperative editor: Loro replicas for humans and agents, governed edit claims, salvage authority, and transport across shared, LAN, and remote harbors. Use when a change spans editor collaboration, identity, recovery, or transport contracts. For a single GPUI pane use gpui-rust-console; for motion use rust-gpui-motion; for a shader use gpui-shaders. NOT for non-collaborative screens, web editors, or generic Rust development.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Verify every visual-evidence artifact (screenshot/GIF/recording) attached to a PR carries a provenance manifest binding it to real daemon-backed truth — daemon port, run id, transcript head hash, agent node id, commit, and an honest real/fixture/mock source label — and that operator-control-panel PRs cover the required set of proof states. Use when gating a PR's proof artifacts before merge, auditing whether a "LIVE" visual claim is backed by a real daemon run versus a reused or fixture-backed mock, or defining the required state-coverage set for a control-panel change. NOT for the capture technique itself — headless Playwright, `screencapture -x -l`, non-interruptive capture (use port-daddy-agent-skill's visual-evidence doctrine), designing the receipt body schema an artifact attaches to (use agent-work-receipt-designer), or the broader dogfood/Potemkin product-quality bar (use multi-agent-authoring-product-bar).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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`).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Author a pull request an AI coding agent can actually get merged: a scoped, coherent diff; a Summary and Test Plan backed by real evidence; correct triage of required-and-blocking CI gates versus external/advisory checks (e.g. a Cloudflare Pages preview build); draft-while-WIP discipline; named fixup commits for real review findings; and a clean landing through a merge queue without force-pushing or bypassing branch protection. Use when opening, updating, triaging red CI on, or landing an agent-authored GitHub PR. NOT for this repo's internal release ceremony, actor embodiments, or contributor mirror-sync mechanics (use port-daddy-internal-dev), tracking backlog/issue lifecycle across a board (use agent-issue-tracker-workflow), or deciding what to build next / sequencing a roadmap (use legible-roadmap-with-sidequests).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Designs and audits deterministic, authority-filtered partitions of trust-typed context for already admitted bodies or abstract continuation slots. Use when causal context, obligations, disclosure boundaries, vector-space identity, capacity, and omission proofs must survive partitioning. NOT for spawning or admitting agents, choosing worker count, retrieving arbitrary knowledge, writing successor prompts, or granting tools, leases, identity, or effect authority.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Safety-case design for always-on agents with episodic memory. Covers data hygiene, privacy and security risk surfaces, cost controls, scope, user dependency concerns, retention, incident containment, and responsible deployment evidence. It identifies hazards and asks for named controls, tests, owners, and residual uncertainty; it does not provide legal, clinical, youth-safety, or jurisdictional determinations. Activate on: "agent safety", "always-on agent privacy", "agent cost control", "persistent agent risks", "AI companion safety", "agent data hygiene", "runaway agent costs", "parasocial AI risk", "/always-on-agent-safety". NOT for: architecture design (use always-on-agent-architecture), input design (use always-on-agent-inputs), application brainstorming (use always-on-agent-applications), healthcare compliance specifically (use hipaa-compliance).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Designs and audits closed, ordered, replay-safe message protocols between already admitted agent bodies. Use when a multi-agent exchange needs explicit epochs, audiences, per-sender sequencing, gathers, terminal fences, acknowledgements, and deterministic replay. NOT for selecting or spawning agents, granting identity or authority, choosing a runtime topology, general human facilitation, wire transport implementation, or deciding whether evidence is true.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design or audit an agent identity, credential, session, continuity, and reputation plan. Use when attributed outcomes must survive key rotation, restart, recovery, or review; when choosing Elo, TrueSkill, a contextual bandit, or an LLM judge; and when making Sybil, newcomer, calibration, collusion, and evidence limits explicit. Produces a supplied-plan consistency audit, never proof of observed delivery, cryptographic identity, or live enforcement. NOT for proving personhood, global Sybil resistance, or an unobserved delivery.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design and audit a pricing function for variable-cost agent labor. Choose among per-seat, metered, credits, hybrid, and outcome pricing; name buyer value and cost metrics separately; calculate a reproducible cost floor; require pre-commitment guardrails; and stress-test declared personas. Use for offline pricing-design evidence, not billing implementation or runtime control. NOT for production billing, payment collection, or runtime spend enforcement.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Declare an agentic application's interaction disclosure, state, context, capabilities, and effect-control boundaries. Use for a reviewable design specification and static consistency audit before implementation. NOT for proving that controls are deployed or enforced, exposing private chain-of-thought, selecting a model/router, or designing a multi-agent protocol.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Migrate configuration from Bluejay voice AI testing platform to Coval. Use when customer says "migrate from bluejay", "bluejay migration", "import bluejay config", or needs to transfer agents, simulations, metrics, and schedules from Bluejay to Coval.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit an existing Coval evaluation setup for coverage, misleading scores, missing evidence, judge validation and execution risk. Read-only; use when inheriting an eval or deciding whether its results support a release decision.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

End-to-end Coval accent testing workflow. Creates one persona per accent (each using a distinct accent voice and mirroring your Standard Customer behavior), launches one run per accent against the same voice agent + test set + metrics, polls for completion, builds a per-persona comparison table from the results, and creates the saved multi-run report (grouped by Persona) via the public API. Use when a user wants to follow the Testing Across Accents cookbook (https://docs.coval.dev/guides/testing-across-accents) without doing each step by hand.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.