- Skills
- 91
- 仓库
- 1
- 职业覆盖
- 6
- 场景覆盖
- 4
- Stars
- ★ 1
pkirsanov 的 Skills 91
smackerel-trace-capture
Wire Smackerel's concrete validate-plane stack into the framework trace-driven defect-discovery method. Use when running live-category tests (integration/e2e/e2e-ui/stress) against the ephemeral test stack; capturing SLO or trace evidence; hunting latency/error/perf bugs from spans; querying the test-stack Jaeger or Prometheus; or touching `.specify/runtime/observability`. Concrete smackerel endpoints + the exact `capture-slo.sh` command; do NOT duplicate `bubbles-observability-adapter` — this only adds the wiring.
smackerel-no-defaults
Enforce Smackerel's NO-DEFAULTS / fail-loud SST policy. Use when editing config, Docker Compose, deploy adapters, docs, instructions, skills, env handling, host bind addresses, or any runtime value that could be hidden by fallback syntax.
bubbles-workflow-mode-resolution
Resolve a Bubbles workflow mode against `bubbles/workflows.yaml`, including template inheritance, status ceilings, gate wiring, and decision policy. Use when picking a mode for a request, when a guard reports a mode-related failure, or when extending workflows.yaml with a new mode or template. Covers natural-language intent routing and the workflow registry consistency rules.
bubbles-workflow-execution-loops
Run per-round synchronous workflow execution loops correctly. Use when orchestrating a multi-round workflow, dispatching specialist subagents, handling round-based remediation, or interpreting a workflow mode's execution policy. Covers authorized direct execution, dispatch-and-wait, batch-then-summarize prohibition, and mapped-mode execution.
bubbles-vscode-agent-constraints
Design agents that fit the VS Code Copilot Chat runtime instead of fighting it. Use when authoring or editing any `*.agent.md`; when adding `tools:`, `agents:`, `handoffs:`, `model:`, `user-invocable:`, or `disable-model-invocation:` frontmatter; when designing an orchestrator that dispatches specialists; when a design implies agent-calls-agent-calls-agent chaining; when a subagent dispatch silently no-ops or an agent cannot be selected in the dropdown; or when writing a governance rule about delegation that the runtime cannot actually enforce. Prevents multi-level-subagent designs, prose-only dispatch laws, and frontmatter/body contradictions.
bubbles-upkeep-cadence
How to schedule, dispatch, and record recurring operational upkeep tasks (backup, restore-drill, BCDR-drill, patch-cycle, secret-rotation, flag-cleanup, compliance-sweep). Use when authoring or modifying `config/upkeep-calendar.yaml`, when investigating a missed task, when reading the upkeep ledger, or when adding a new task type.
bubbles-test-integrity
Enforce real, specification-driven test quality during any test work. Use when writing tests, implementing scope test plans, reviewing test coverage, or validating DoD test items. Triggers include writing tests, adding test coverage, implementing scope tests, reviewing test plans, marking test DoD items, and verifying Gherkin scenario coverage.
bubbles-test-environment-isolation
Enforce ephemeral-only backing stores for any test category that touches mutable state (integration, e2e-api, e2e-ui, stress, load). Use when authoring or reviewing test compose files; when changing test setup/teardown; when defining test-data policy in copilot-instructions; when writing tests that touch a real DB, message bus, cache, queue, file system, or external integration; when reviewing PRs that introduce a new persistent entity. Triggers include new docker-compose.test*.yml files, test-port allocation, test-database creation, "MUST clean up after" policy text, and parallel-test infrastructure work.
bubbles-technical-prose
Write generated technical prose that a reader can act on without re-reading. Use when authoring or reviewing spec.md, design.md, report.md, scopes.md, managed docs, agent modules, refusal messages, or result-envelope narrative. Covers sentence length, banned punctuation, active voice, one instruction per sentence, and note-versus-warning form. Never applies to verbatim evidence, human-owned uservalidation.md, or release-packet narrative.
bubbles-supply-chain-source-locking
Lock build-time dependency resolution to an explicit allowlist of trusted registries/sources so dependencies can never be pulled from an arbitrary or implicit upstream. Use when adding or editing a dependency manifest or lockfile (Cargo.toml/Cargo.lock, package.json/package-lock.json, go.mod/go.sum, requirements.txt/constraints); when configuring a package-source file (cargo-deny config, .npmrc, GOPROXY/GOFLAGS env, pip index config); when wiring or reviewing a lint/pre-push gate that touches dependency installation; when reviewing a PR that adds a new external dependency, a new registry, or a git/path dependency; or when investigating dependency-confusion, typosquat, or malicious-mirror risk. Distinct from deploy-time artifact provenance (cosign/SLSA/SBOM/Trivy) — see "Two Axes" below.
bubbles-status-transition
Transition a Bubbles spec/scope/bug status safely through the framework's gate checks. Use when changing state.json status (`in_progress` → `done`, `done_with_concerns`, `blocked`, `specs_hardened`, etc.), promoting an artifact, or running pre-push checks. Covers the mechanical transition guard and the grandfather clause for historical done specs.
bubbles-spec-template-bdd
Enforce spec.md adherence to .specify/templates/spec-template.md with Gherkin-style BDD scenarios and tech-agnostic requirements.
bubbles-skills-first-discovery
Discover which Bubbles policy skill applies to the current task. Use as the first step when an agent is uncertain which governance module to load, when a user asks about Bubbles policy without naming a specific module, or when onboarding a new agent that should lean on skills instead of bulk-loading agent-common.md. Maps common situations to the right skill.
bubbles-skill-authoring
Guidance for creating or updating repo-local skills under .github/skills. Use when adding procedural workflows, checklists, or reusable resources that must follow repository governance.
bubbles-scope-workflow-runtime
Operate Bubbles scope artifacts correctly during planning, implementation, testing, and validation. Use when creating a new scope, deciding between single-file and per-scope-directory layout, writing a Test Plan, choosing DoD shape, picking the next scope to work, or honoring scope isolation during multi-scope work.
bubbles-result-envelope
Compose a valid Bubbles result envelope at the end of every agent invocation. Use when finishing any Bubbles agent task and about to return control to the orchestrator, when routing work to another specialist via a packet, or when emitting a continuation envelope from a read-only/advisory surface. Covers outcome vocabulary, finding accounting, addressedFindings/unresolvedFindings, and next-owner routing.
bubbles-repo-readiness
Verify-first repo-readiness checks for downstream repos. Use when auditing whether a repo is agent-ready, checking onboarding-doc drift, validating that documented commands map to real repo command surfaces, or improving repo hygiene without mixing it into certification.
bubbles-release-train-model
How to operate the trunk + release-train + per-train-flag-bundle model. Use when cutting/promoting/rolling-back/retiring a release train, when declaring a feature flag, or when designing a feature spec that targets a specific train.