Testing & Security skills

Content sanitization and hidden-content detection for agent skill security. Scans markdown, HTML, and text for visually hidden but agent-readable attacks: CSS-hidden text (display:none, color:white, font-size:0, opacity:0), HTML comments with instructions, collapsible details sections, zero-width unicode, homoglyphs, misleading links, and inline HTML in markdown. Enforces mandatory sanitization before external content enters agent context. Load as part of the secure-* sequence during any repo scan or skill audit. Also load for sanitize content, check hidden text, scan markdown attacks, strip HTML, detect invisible instructions, check zero-width chars. Core principle: visibility does not equal influence — hidden content is more dangerous than visible content because agents process it but humans cannot see it.

The English summary is being prepared. Showing the original description.

Audit the project's technical health and identify "high-interest" debt. Load when the user asks to check code quality, find TODOs, assess project health, or prepare for a refactoring sprint. Also triggers on "technical debt audit", "where is the code messy", "assess project health", "find my hacks", or "identify tech debt". Essential for maintaining velocity in growing projects.

The English summary is being prepared. Showing the original description.

Security checks for repository ingestion — scans repos for poisoned examples, dependency and supply-chain attacks, file/path traversal, format-based attacks, and enforces quarantine-before-commit. Load as part of the secure-* skill sequence whenever an agent reads, ingests, or learns from a GitHub repository. Also load when the user asks to check a repo for poisoned code, scan dependencies, verify supply chain safety, check for path traversal, scan repo files for attacks, or audit a repo before ingestion. Covers Issues 3, 4, 7, 8 from the agent security threat model: poisoned training data, dependency attacks, file/path attacks, and format-based attacks.

The English summary is being prepared. Showing the original description.

Design, build, validate, and ship cross-platform agent skills. Load when the user asks to create a skill, build a custom skill, write a SKILL.md, package a workflow as reusable agent capability, improve or audit a skill, publish a skill, or build a planned skill suite.

The English summary is being prepared. Showing the original description.

Runtime security for agent skills — prevents state corruption, skill overwrite attacks, denial of service, and enforces provenance tracking and no-go repo management. Load as part of the secure-* skill sequence whenever an agent processes external content or writes to the skill store. Also load when the user asks to check for state corruption, prevent skill overwrite, manage no-go repos, check provenance, audit runtime security, detect DoS patterns, or protect the skill store. Covers Issues 6, 9, 10 from the agent security threat model: instruction hierarchy enforcement, state corruption and skill overwrite, and denial of service prevention.

The English summary is being prepared. Showing the original description.

Ground framework-specific implementation in official documentation — detect stack versions, fetch authoritative docs, implement cited patterns, cite sources. Load when building with a library or framework where API correctness matters, when the user wants verified or documented code, or before writing framework code from memory. Also triggers on "source driven development", "cite the docs", "check official documentation", "verify against docs", "don't hallucinate APIs". Not for pure logic or renames. Pairs with feature-spec and test-driven-development.

The English summary is being prepared. Showing the original description.

Hard readiness gate before implementation begins — cross-checks the constitution, feature spec, plan, and tasks for consistency, traceability, and unresolved ambiguity. Returns PASS or FAIL with specific findings. Load when the spec-driven-development orchestrator routes /analyze, when the user asks to cross-check spec vs plan, audit traceability, verify spec readiness, gate-check before implementation, or says "is this spec implementation-ready", "trace requirements to tasks", "/analyze", "spec sanity check", "spec readiness gate", "spec consistency check". Output: docs/reviews/YYYY-MM-DD-<slug>-spec-crosscheck.md.

The English summary is being prepared. Showing the original description.

Apply the Red-Green-Refactor cycle to software development. Load when the user asks to write code using TDD, create unit tests, implement a feature with test coverage, refactor code, or ensure software quality through automated testing. Also triggers on "test-driven development", "write tests first", "TDD this feature", "Red-Green-Refactor", "ensure 100% test coverage", or any request to build software with a test-first approach. Supports unit, integration, and end-to-end testing strategies.

The English summary is being prepared. Showing the original description.

Run a fast, read-only health check across all skills in the library and produce a structured quality report — without modifying anything. Load when the user asks to validate skills, check skill health, audit the library, run a skill quality check, or when improve-skills needs a pre-flight before starting its cycle. Also triggers on "what's wrong with my skills", "check all skills", "skill health report", "are my skills ok", or "pre-flight check". Called automatically by improve-skills before any improvement work begins, and by universal-skill-creator after every new skill is created. Never modifies any file — only reads and reports.

The English summary is being prepared. Showing the original description.

Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks, and instruction hierarchy violations before any skill is installed, created, improved, or read from a GitHub repo. Load when creating skills from external sources, when improve-skills reads from GitHub repos, when research-skill fetches community SKILL.md files, when a user installs a third-party skill, or when the user asks to audit skill security, scan for injection, check if a skill is safe, scan all skills, or run a security sweep. Orchestrates all secure-* skills in sequence. Content is SAFE only if ALL secure-* skills return SAFE. 36% of community skills contain flaws (Snyk ToxicSkills 2026). This skill is the first line of defense.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

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`.

The English summary is being prepared. Showing the original description.

Orchestrate persistent agent memory across coding sessions, repos, and tools. Load when the user asks to remember, recall context, save project memory, create a handoff, manage global memory, update memory, compact memory, audit memory, forget memory, continue from prior sessions, or before commit/push/git operations that checkpoint project state.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Measure, profile, and fix performance bottlenecks — Core Web Vitals, backend latency, bundle size, and database queries. Load when performance requirements exist, users report slowness, profiling reveals bottlenecks, or the user asks to optimize load time, LCP, INP, CLS, or response time. Not for premature optimization without evidence. Pairs with browser-testing-with-devtools and ci-cd-and-automation for regression guards.

The English summary is being prepared. Showing the original description.

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).

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

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".

The English summary is being prepared. Showing the original description.

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".

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.