테스트·보안 스킬

Critically audit agent skills and remove content that is outdated, disproven, model-specific, or based on poorly cited sources. Load when improve-skills runs its per-skill cycle, when the user asks to prune skills, remove outdated techniques, check if skills are still valid, verify citations in skills, audit skill sources, or update skills for a new model release. Also triggers on "are these skills still valid", "check for obsolete techniques", "verify skill citations", or "update skills for GPT-5/Claude 4/Gemini 2". Runs before split-skill and compress-skill — removing bad content first means the remaining content is worth preserving.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Deliver multi-file changes in thin vertical slices — implement, test, verify, commit, repeat. Load when implementing a feature from a plan, building across more than one file, refactoring, or when tempted to land a large change in one pass. Also triggers on "incremental implementation", "vertical slice", "thin slice", "one slice at a time", "don't do it all at once". Routes single-file fixes to direct execution. Pairs with test-driven-development and git-workflow-and-versioning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit, improve, and compress every skill in the repo using live research. Load when the user asks to improve skills, audit the skill library, upgrade existing skills, refresh with new research, do a skill health check, or says "improve all skills", "update the skill library", "skill audit", or "run an improvement pass". Applies live domain research, fixes structural gaps, checks for skill linking opportunities, then rewrites and resizes each skill. Supports TARGETED mode (`TARGET=<skill> [SKIP_RESEARCH=true]`) for single-skill fixes, including learn-from-chat restructure escalations. All skills are in scope including meta skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apply one logical code change with mandatory impact mapping, git snapshot, verification, and automatic revert on failure. Load when the user asks for a safe edit, verified change, one change at a time with rollback, or codespine-style edit loop. Also triggers on "safe change", "edit with verification", "don't break the build", "revert if tests fail", or any non-trivial code edit where blast radius matters. Always runs dependency-mapping first. Pairs with incremental-implementation for multi-slice work; this skill is one atomic verify cycle per invocation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Score an unbuilt business idea on desirability, viability, feasibility, distribution wedge, why-now, founder-market-fit, market size, alternatives, defensibility, capital intensity, and regulatory/ethical risk — and return a GO / ITERATE / KILL verdict with kill criteria and a next kill test. Load when the user asks to evaluate a business idea, score a startup idea, screen an idea, decide whether to pursue this venture, do an idea review, or says "is this a good business idea", "should I build this", "evaluate this startup", "screen this idea", "go/no-go on this idea", "kill or pursue". Sub-skill of `venture-exploration`. Calls `fermi` for sizing, `assumption-mapping` for hidden beliefs, optional `pre-mortem` / `adversarial-hat` for high-stakes ideas. Does NOT evaluate built products — for that use `reality-check`.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit project and global memory for bloat, stale decisions, duplicates, contradictions, unsafe content, missing provenance, broken routing, and over-budget global files. Load when the user asks to audit memory, clean memory, check memory health, or verify memory quality.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orchestrator for the experimentation skill suite — turn assumptions and product questions into rigorous, well-instrumented experiments and decision-grade readouts. Routes through backlog → spec → runbook → readout based on user need and existing artefacts. Platform-agnostic with PostHog as the primary binding. Load when the user asks to design an experiment, A/B test something, set up an experiment, run a holdout, test a hypothesis, decide what to test next, read out experiment results, analyse a test, or says "should we A/B test this", "experiment on the landing page", "is this lift real", "ship or kill this test", "what should we test next", "build an experiment backlog", "test the pricing page", "validate this with an experiment".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Translate an approved experiment spec into a launch runbook — platform binding (PostHog primary), feature flag setup, assignment unit, exposure event definition, instrumentation QA, dashboard wiring, ramp plan, monitoring, and rollback procedure. Platform-agnostic core with one strong PostHog adapter shipped; GrowthBook, Statsig, LaunchDarkly, Optimizely, and Eppo documented as a single mapping table the user adapts. Load when a spec is approved and ready to launch, or when the user says "set up the experiment", "wire this up in PostHog", "implement the test", "create the runbook", "launch checklist for this test", or when the experimentation orchestrator routes here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turn assumptions, funnel opportunities, and product questions into a prioritised, feasibility-checked experiment backlog. Filters by traffic reality, metric latency, and method feasibility — not just ICE/RICE scoring. Maintains a living portfolio with status (idea → designed → running → readout → archived). Load when the user says "what should we test next", "build an experiment backlog", "prioritise our tests", "where should we experiment", "what's worth testing", or when the experimentation orchestrator routes here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design automated evaluation pipelines for LLM and agent systems — combining deterministic checks, statistical metrics, and LLM-as-judge scoring into repeatable, CI-integrated eval suites. Load when the user asks to set up automated evals, design an eval pipeline, integrate evals into CI/CD, create an eval suite, do eval-driven development, or says "automate my evals", "CI eval integration", "evaluation pipeline", "continuous evaluation", "monitoring eval quality", "set up regression testing for my agent". Sub-skill of eval-output orchestrator.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Map symbol dependencies, callers, and blast radius before editing code. Load when the user asks what depends on a symbol, what breaks if they change something, blast radius of a change, reverse dependencies, or which tests cover a function. Also triggers on "who calls this", "impact of changing", "dependency map", "what uses this", "find callers", or before any non-trivial edit when safe-change is not yet active. Pairs with codebase-understanding for broad architecture; this skill is symbol-scoped and edit-gated.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Test and debug browser UIs using Chrome DevTools MCP — DOM inspection, console errors, network requests, performance traces, and visual verification. Load when building or debugging anything that renders in a browser, verifying a UI fix, profiling Core Web Vitals in a real page, or the user asks for browser testing with DevTools. Requires chrome-devtools MCP configured. Not for backend-only or CLI work. Pairs with frontend-design and performance-optimization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Harden an application against common security risks — validate inputs at boundaries, least-privilege access, safe secrets handling, dependency hygiene, and secure defaults. Load when shipping user-facing code, adding auth/session flows, handling untrusted data, exposing APIs, or the user asks for "security hardening", "OWASP hardening", "secure this feature". Not for skill-library security gates (use secure-skill family).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Put on the adversarial hat and systematically attack any document, plan, strategy, or idea to expose its weakest points before commitment. Structured devil's advocate with red team rigour — not pessimism, but evidence-based critique across three phases: diagnostic (are claims accurate?), creative (is the problem artificially constrained?), challenge (are solutions robust?). Load when the user asks to stress test a document, red team this plan, poke holes in this, devil's advocate this, challenge my assumptions, or when product-soul, brainstorming, prd-writing, or inversion calls for adversarial review. Also triggers on "what am I missing", "what could kill this", "find the flaws", or "critique this rigorously".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Surface every assumption embedded in a plan, strategy, or document, assess how critical and how validated each one is, and identify which ones to test first. Load when the user asks to map assumptions, surface hidden beliefs, find what must be true for this to work, run an assumption audit, or when deep-thinking diagnoses an assumption frame. Also triggers on "what are we assuming", "what must be true for this to work", or "find the untested beliefs". Based on David Bland and Alex Osterwalder's assumption mapping method from Testing Business Ideas.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run Mom Test–style customer-discovery interviews to validate or kill an unbuilt idea — generate a non-leading interview guide, conduct or coach the conversations, and synthesize signal vs compliments. Load when the user asks to do customer discovery, run problem interviews, validate an idea with users, run a Mom Test, design an interview guide, or says "talk to customers", "validate the problem", "interview users", "Mom Test this", "did real users want it", "synthesize my interviews", "I just talked to N people". Sub-skill of `venture-exploration`. Hard-bans "would you use this?", solution-pitching, friend/family-only ICP, and treating compliments as validation. Calls `secure-*` before synthesizing any pasted external transcripts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit UI, docs, or prose for AI-generated tells in design and copy, then fix approved findings. Use when the user says de-slop, slop check, "looks AI-generated", or wants copy humanized.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Verify a code change end-to-end in the current worktree: identify what changed, run the relevant tests, get the app running, drive a browser over the affected areas, and report a verdict with screenshots. Generic across project types (Laravel/Herd, Node/bun, frontend, CLI, library). Use when the user wants to verify/QA/smoke-test a change, check that a PR or branch works, validate uncommitted work, or says "/flow", "verify this change", "does this PR work", "test and click through this". Optional target: PR number/URL, branch/ref, or worktree path; default is the current working changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when authorship order, CRediT contribution roles, or AI-assistance attribution must be recorded transparently for a manuscript, when an author dispute needs an evidence trail, or before a contributorship statement is required at submission; this skill maintains the human-attribution ledger of who contributed what and in which role (authorship order, CRediT taxonomy, revision responsibilities), which is distinct from the disclosure-metadata audit owned by ai-disclosure-auditor.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when authoring a new manuscript, thesis chapter, or abstract from scratch in Turkish and English in parallel — building the claim skeleton first, then drafting Turkish and re-authoring English — not for auditing parity between existing versions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a construct, scale, or key term crosses Turkish and English and conceptual equivalence must be audited: translation and back-translation, construct drift, and culturally bound meaning, before measurement or cross-cultural claims.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.