Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

spec-kitty-mission-review

Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify spec→code fidelity, FR coverage, drift, risks, and security. Triggers: "review the merged mission", "post-merge mission review", "verify the completed mission", "audit the mission implementation", "mission-level acceptance review", "is this mission releasable", "final review before tagging", "cross-WP coverage audit". Does NOT handle: per-WP review during implementation (use spec-kitty-runtime-review), implement-review loop orchestration (use spec-kitty-implement-review), setup or repair (use spec-kitty-setup-doctor), or glossary maintenance (use spec-kitty-glossary-context).

1.41k repo starsObserved in 2 repos
Testing & Quality
GitHub

adversarial-squad

Deploy a bounded, profile-loaded adversarial review squad at an SDD point-cut (post-spec, post-plan, post-tasks, pre-merge, or an ad-hoc decision) so independent doctrine lenses converge on findings one reviewer would miss. Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass", "pre-spec investigation squad", "brownfield check", "second opinion on this design", "review squad", "run a multi-lens review". Does NOT handle: the implement-review loop (use spec-kitty-implement-review), spec/plan/tasks generation, or direct code editing by the orchestrator. It is an optional, charter/memory-activated enrichment — it never gates a mission.

1.41k repo starsObserved in 1 repos
Testing & Quality
GitHub

spec-kitty-runtime-review

Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only repair requests, direct implementation work, editorial glossary maintenance, or runtime loop advancement.

1.41k repo starsObserved in 1 repos
Testing & Quality
GitHub

spk-gate-accept

Run the Spec Kitty accept gate for a completed mission and verify final readiness before merge.

1.41k repo starsObserved in 1 repos
Testing & Quality
GitHub

spk-gate-mission-review

Run post-merge Spec Kitty mission review for spec-to-code fidelity, FR coverage, drift, risk, and final verdict.

1.41k repo starsObserved in 1 repos
Testing & Quality
GitHub

spk-run-review-wp

Review a Spec Kitty work package through the runtime review surface and approve or reject with structured feedback.

1.41k repo starsObserved in 1 repos
Testing & Quality
GitHub

pr-reviewer

Reviews pull requests in the hyperswitch-prism (UCS) Rust codebase using a strict, fail-closed, scenario-aware review system. Classifies PRs into connector, core-flow, proto, server, SDK, CI/security, and GRACE-generated scenarios, then dispatches specialist subagents per scenario. Use when reviewing any PR, batch-reviewing open GRACE PRs, or re-reviewing after author updates.

1.41k repo starsObserved in 1 repos
Testing & Quality
GitHub

zeus-debugging-playbook

Load when debugging a Zeus failure - a feature silently does nothing, "TypeError x.then is not a function", settings vanished after update, app stuck on "connecting"/infinite loading, CI Lint or Prettier fails though local eslint passes, Jest "unexpected token" on a new dependency, crash in Animated/layout code after RN upgrade, Hermes RangeError/regex stack overflow, identical error repeats on every retry over Tor, "payment timed out" shown as success, back navigation lands on wrong screen, embedded LND won't start or crashes on restart, keychain/settings weirdness on a new device, gRPC stream write reports success but nothing happens, or node start/stop/delete race crashes. Gives a symptom-to-triage table with discriminating experiments and known trap references.

1.40k repo starsObserved in 1 repos
Testing & Quality
GitHub

zeus-diagnostics-and-tooling

How to MEASURE Zeus instead of eyeballing it — find and tail logs (embedded LND lnd.log paths on Android/iOS, LDK Node ldk_node.log, adb logcat tags, Metro/Xcode consoles), use in-app diagnostics (Developer Tools view, Keychain Recovery scanner, log viewers), inspect network traffic (REST/WebSocket/Tor paths, TLS caveats), grep the codebase without generated-file noise, and run the shipped scripts (find-debt.sh, capability-matrix.sh, list-settings-defaults.sh). Load this when you need to answer "where are the logs?", "why is the node stuck syncing/connecting?", "which backend supports feature X?" (measured, not guessed), "how do I see the app's HTTP requests?", or when a grep is drowning in uniffi/protobuf bindings.

1.40k repo starsObserved in 1 repos
Testing & Quality
GitHub