con un clic
ai-first-sdlc-practices
ai-first-sdlc-practices contiene 46 skills recopiladas de SteveGJones, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
Parallel map-reduce bulk ingest for large source sets. Map phase dispatches read-only knowledge-extractor agents (≤N-wide, default Haiku) emitting per-source JSON extracts; Python routes extracts by target library file (fuzzy-merging new topics, pre-allocating new files, flagging oversized topics); reduce phase dispatches one agent-knowledge-updater per file (parallel, one writer per file); single shelf-index rebuild + one log.md entry. Resumable. Supersedes kb-ingest-batch.
Initialise a project for knowledge base use. Appends the [Knowledge Base] section to the project's CLAUDE.md, creates the library/ directory structure, optionally seeds with three example library files from the Agentic SDLC research, and reports next steps. Run once after installing sdlc-knowledge-base.
Drive agent-knowledge-updater over a batch of staged files in library/raw/. Tracks progress in .batch-progress.json for resume support. Sequential by default; --parallel <N> opt-in (max 5). Single shelf-index rebuild and one consolidated log.md entry at the end.
Health-check the project knowledge base. Looks for contradictions between files, stale claims that newer sources have superseded, orphan files with no inbound cross-references, important concepts mentioned but lacking their own page, missing cross-references, and data gaps. Returns a structured report; does not auto-fix.
Stage source files into library/raw/, converting non-markdown formats via markitdown (PDF/DOCX/PPTX/XLSX/HTML/CSV) or pandoc (TeX/EPUB/RST/ORG). Adds provenance frontmatter. No agent dispatch.
Pure-Python knowledge base statistics dashboard. Reads shelf-index and log.md; emits Inventory, Layer distribution, Domain distribution, Recent Activity, and Staleness sections. No agent dispatch. Read-only.
Manage the project's layer vocabulary — list allowed layers with file counts, add new layers, or safely remove unused layers. Reads the shelf-index for usage data; writes CLAUDE.md atomically. No agent dispatch.
Rebuild the knowledge base shelf-index with hash-based change detection. Incremental by default — only re-extracts files whose content has changed since the last index. Use after ingesting new sources, after editing library files, or whenever the librarian agent reports a stale index.
Filter and summarise the cross-library KB audit log. Reports confidentiality events (attribution drops, synthesis aborts, dispatcher failures, no-evidence markers, cross-library promotions) over a date range, by event type, and by source handle.
Configure SDLC team formation and SDLC method for this project. Asks the four-option SDLC method question (solo / single-team / programme / assured), then recommends and installs team plugins based on project type, language, tech stack, and support needs.
Generate boilerplate `# implements:` annotation for a function based on the artefact ID, inserting it as the first line of the function body.
Dispatch a structured cross-phase review of a phase artefact. MANDATORY for design-spec and test-spec; the gate validator checks for the resulting review record before passing. Recommended for requirements-spec.
Parse all `# implements:` annotations in source code and emit `library/_code-index.md` as a shelf-index. Also extracts cross-module import edges and writes `library/_dependency-edges.md`. Idempotent — re-running produces byte-identical output if no annotations or imports changed.
Guide the team through writing a change-impact record for IEC 62304 / FDA / ISO 26262 ASIL C+ projects. Surfaces the affected REQ/DES/TEST/CODE artefacts and captures human-attested verification approach.
Run all 5 decomposition validators (req-has-module, code-annotation-maps-to-module, visibility-rule-enforcement, anaemic-context-detection, granularity-match) on the project, reporting violations.
Mint a new REQ ID in the Assured project's namespace, with module assignment, and append it to the requirements-spec.
Add a satisfies link from a DES → REQ, TEST → REQ/DES, or CODE annotation → ID, validating that the target exists in the registry.
Render module-scoped human-readable traceability for a single module — REQs, DESs, TESTs, code locations with anchor links, plus the module-dependency graph as a markdown edge-list.
Commission a project to the Assured (Method 2) SDLC bundle — install plugin, scaffold programs.yaml, set granularity and regulatory context, configure change-impact-gate.
Commission a project to the Programme SDLC bundle. Tailored entry point with Programme-specific audience guidance; equivalent to /sdlc-core:commission --option programme.
Run a Programme phase gate validator (requirements / design / test / code) against docs/specs/<feature-id>/. Block on missing artefact or broken cross-phase reference.
Instantiate a phase artefact (requirements-spec / design-spec / test-spec) from the Programme bundle's template into docs/specs/<feature-id>/. Refuses to overwrite existing artefacts.
Export the REQ↔DES↔TEST traceability matrix for a feature in csv or markdown format. Phase D ships csv + markdown; Phase E (Assured) extends with standard-specific formats.
Commission a project to an SDLC option bundle (solo / single-team / programme / assured). Asks structured questions, recommends an option × level, installs the bundle, and records the decision in .sdlc/team-config.json.
Mock skill shipped by the sample bundle for installer testing
Query the project knowledge base. Wraps the research-librarian agent. The librarian reads the shelf-index, identifies the 2-4 most relevant library files for the question, deep-reads only those, and returns structured evidence with citations. Stateless — reads the index fresh on every query.
Onboarding workflow for cross-library KB query in a consulting practice. Discovers existing user-scope library registrations, prompts for additions, validates each library, helps activate the relevant ones for the current project, runs a smoke test, and reports a clear "ready" or "issues to fix" verdict. Use --verify-only to skip prompting and just validate existing setup (sub-task 23 of
File a librarian query result back into the library as a new page with provenance tracking. Karpathy's "good answers can be filed back into the wiki as new pages" insight made concrete. The library compounds from explorations, not just from external sources.
Register an external knowledge base library in the user-scope global registry at ~/.sdlc/global-libraries.json. Validates that the target path exists, contains a _shelf-index.md, and parses its format_version. Optional helper — hand-editing the JSON is also supported.
Pick an existing workflow for a task or author a new one — recommends workflow + team formation, or generates a fresh workflow YAML with command prompts and team validation.
Install Archon, build the sdlc-worker Docker images, and configure SDLC workflows. Run once after installing the sdlc-workflows plugin.
Run an SDLC delegated workflow via Archon. Wraps the archon CLI with project-aware defaults.
Guided coaching for delegation team lifecycle — create, update, delete, or review the workforce. The primary interface for team management and fleet-level visibility.
Check the status of running or recent SDLC delegated workflows.
Create a pull request with full validation. Use when ready to submit work for review.
Build a team Docker image from a manifest in .archon/teams/. Resolves plugin paths, generates Dockerfile with additive copy-only, makes plugins read-only, bakes team CLAUDE.md.
Validated commit — runs quick checks before committing. Use when ready to commit changes.
Create a new feature with proposal, retrospective, and branch. Use when starting new development work.
Package source files into plugin directories using release-mapping.yaml. Use when preparing a plugin release.
Generate a GitHub Actions workflow for SDLC validation. Use when setting up CI/CD for a new project.