--- title: "skraft" description: "skraft SDLC pipeline: agents, skills and instructions for outside-in TDD, Clean Architecture, backlog discovery and the RESEARCH→DESIGN→DISTILL→DELIVER engineering pipeline." canonical: https://agentpluginsdirectory.com/plugins/skraft last-updated: 2026-10-11 --- # skraft skraft SDLC pipeline: agents, skills and instructions for outside-in TDD, Clean Architecture, backlog discovery and the RESEARCH→DESIGN→DISTILL→DELIVER engineering pipeline. - Slug: skraft - Publisher: SebastienDegodez - Repository: https://github.com/SebastienDegodez/skraft-plugin - Manifest: plugins/skraft-framework/plugin.json - Version: 1.14.1 - License: GPL-3.0-or-later - Category (editorial): productivity - Skills: 48 (acceptance-review-criteria, adr-eligibility-gate, adversarial-review-lenses, architecture-decisions, architecture-patterns, architecture-review-criteria, bdd-methodology, characterize-brownfield, characterize-with-contracts, clean-architecture-dotnet, clean-architecture-java, clean-architecture-python, clean-architecture-react, clean-architecture-testing, compose-brownfield-prd, contract-testing-dotnet, contract-testing-python, contract-testing-roster, contract-testing, craft-discipline, discovery-review-criteria, github-search-protocol, issue-refinement, issue-triage, mikado-method, mocking-inprocess-dotnet, mocking-inprocess-python, mocking-inprocess-typescript, mocking-microcks-dotnet, mocking-microcks-python, mocking-microcks-typescript, mocking-strategy-roster, mutation-testing, outside-in-tdd, planning-review-criteria, playwright-evidence, qa-reporting, quality-gates-dotnet, quality-gates-evidence-contract, quality-gates-javascript, quality-gates-python, quality-gates-typescript, resolving-stack-commands, skraft-quality-bar, sprint-planning, strangler-fig-method, test-design-mandates, test-refactoring-catalog) - MCP servers: 0 - Stars: 8 - Repository created: 2026-04-16 - Repository last pushed: 2026-10-11 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/skraft - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What skraft does, in the publisher's words > Mise à jour obligatoire: ce fichier est mis à jour à chaque US implémentée. > L'agent qui implémente une US doit cocher la case correspondante et documenter les modules livrés. Le framework vit dans plugins/skraft-framework/src/. Il est livré avec le plugin: aucune dépendance externe. Point d'entrée appelé par com.anthropic.claude-code/hooks/hooks.json (Claude Code, Codex), com.github.copilot/hooks/hooks.json (Copilot installé) et.github/hooks/skraft-framework.json (Copilot sur checkout du repo): - CLAUDE_PLUGIN_ROOT: injecté par le harness Claude Code = chemin du plugin installé dans le cache. Autoritaire. - Fallback glob: si absent, recherche sur disque ~/.claude/plugins/cache/*/skraft/*/src/cli/hook.mjs (via node:fs globSync, pattern à slashes valides aussi sous Windows); le dernier match (install le plus récent) est retenu. Fail-open: toute erreur de glob → liste vide. - Fallback module-relatif: si aucun match cache, la racine est déduite de l'emplacement réel de hook.mjs (../.. → plugins/). From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/SebastienDegodez/skraft-plugin/HEAD/plugins/skraft-framework/README.md ## Skills - acceptance-review-criteria: Use when reviewing DISTILL artefacts (Gherkin scenarios, test plans, implementation plans) for quality, completeness, and alignment. Contains the gate definitions and scoring rubric for the acceptance-designer-reviewer lenses. - adr-eligibility-gate: Use when deciding WHETHER a candidate architectural choice deserves an architecture decision record, before any record is drafted: a story enters DESIGN with a list of candidate choices, a reviewer flags ADR inflation, or someone asks "should I write an ADR for X?", "how many ADRs does this story n… - adversarial-review-lenses: Use when reviewing a phase artifact, a discovery brief, a plan, a design, an acceptance specification, or a slice reported as delivered, and the review has to end in a defensible pass-or-block verdict rather than a list of remarks. Covers judging whether the artifact covers everything that fed in… - architecture-decisions: Use when documenting architecture decisions as ADRs, evaluating trade-offs between alternatives, or managing the lifecycle of existing decisions. Covers ADR template, status transitions, consequence analysis, and quality criteria. - architecture-patterns: Use when selecting architecture patterns for a new feature, performing Event Modeling, defining bounded contexts, choosing DDD tactical patterns, evaluating pattern fitness, or understanding how patterns compose. Covers Event Modeling methodology, DDD strategic design, DDD tactical patterns, Clean… - architecture-review-criteria: Use when reviewing DESIGN artefacts (event models, ADRs, component diagrams, context maps, interface contracts) for quality, DDD compliance, and architectural correctness. Contains gate definitions and scoring rubric for the solution-architect-reviewer lenses. - bdd-methodology: Use when writing, reviewing, or structuring BDD scenarios in Gherkin format. Covers Given/When/Then conventions, scenario outline patterns, background usage, tag strategies, and domain language alignment. Load before any Gherkin authoring. - characterize-brownfield: Use to reverse-engineer an existing/brownfield codebase into structured, confidence-scored characterization artifacts (tech stack, feature inventory, dependency & integration map, existing API contracts, test-coverage traceability, tech debt & risks). Use before composing a PRD, or standalone to un… - characterize-with-contracts: Use to discover or reconstruct a service's API contract and produce characterization (golden-master) tests that lock in its CURRENT behavior, including existing bugs, as a safety net before refactoring a brownfield service. Delegates stack detection and Microcks wiring to contract-testing-roster… - clean-architecture-dotnet - clean-architecture-java - clean-architecture-python - clean-architecture-react - clean-architecture-testing: Use when it is unclear where a test belongs and what it is allowed to talk to, which test project and layer it goes in, whether it gets a real database, an in-memory fake, or no double at all, and whether a value object or a constructor is worth a test of its own. Also use when layer dependencies… - compose-brownfield-prd: Use to compose an HVE-format PRD (17 sections, docs/prds/.md) from brownfield characterization artifacts produced by characterize-brownfield. Maps as-is features, constraints, integrations, coverage and tech debt into HVE PRD sections with FR/NFR IDs and full traceability. Activate on 'write… - contract-testing-dotnet: Use when the contract-testing-roster resolved a.NET stack for a provider-side contract test. Always provides the baseline WebApplicationFactory + HttpClient integration test recipe; when the Microcks opt-in is enabled, additionally provides the MicrocksContainer + TestEndpointAsync(OPEN_API_SCHEMA… - contract-testing-python - contract-testing-roster - contract-testing - craft-discipline - discovery-review-criteria - github-search-protocol - issue-refinement - issue-triage - mikado-method - mocking-inprocess-dotnet - mocking-inprocess-python - mocking-inprocess-typescript - mocking-microcks-dotnet - mocking-microcks-python - mocking-microcks-typescript - mocking-strategy-roster - mutation-testing - outside-in-tdd - planning-review-criteria - playwright-evidence - qa-reporting - quality-gates-dotnet - quality-gates-evidence-contract - quality-gates-javascript - quality-gates-python - quality-gates-typescript - resolving-stack-commands - skraft-quality-bar - sprint-planning - strangler-fig-method - test-design-mandates - test-refactoring-catalog Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.