Loading...
Loading...
Found 46 Skills
Portable AI SDLC shared-helper runtime. Use when an AI assistant installs, verifies, diagnoses, or repairs project-scoped AI SDLC skills whose deterministic scripts depend on shared state, artifact, context, path, TOON, migration, or index modules. This is an installation dependency, not a lifecycle entry point.
Use when stories, specs, BRDs, APIs, workflows, or equivalent delivery artifacts exist and you need to review them for testability, missing business rules, unclear behavior, scope ambiguity, and QA blocking gaps before generating tests. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.
AI SDLC package trust and privacy-preserving local metrics workflow. Use when an AI assistant needs to verify package origin, file integrity, harness compatibility, declared capabilities, provenance evidence, or generate reproducible aggregate run, retry, budget, coverage, and freshness metrics without collecting source, prompts, commands, or diffs. Supports `--quick-flow` and `--full-flow`.
AI SDLC business analysis workflow. Use when an AI assistant needs to frame a feature or change before implementation, derive actors, workflows, business rules, assumptions, acceptance criteria, and richer spec context for requirements and design. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.
AI SDLC reusable quality-lens workflow. Use when an AI assistant needs to challenge a requirement, design, plan, test strategy, change, or delivery artifact through pre-mortem, adversarial, edge-case, stakeholder-conflict, reversibility, abuse-case, operational-failure, or assumption lenses and finalize evidence-backed findings with ownership and traceability. Supports `--quick-flow` for selected high-value lenses and `--full-flow` for the complete applicable registry.
AI SDLC approvals, sandbox, and command rule workflow. Use when an AI assistant needs to decide whether to request escalated permissions, explain sandbox failures, propose prefix_rule approvals, avoid unsafe command patterns, or document why a command was or was not rerun outside the sandbox. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution.
AI SDLC commit preparation workflow. Use when an AI assistant is asked to commit repository changes, prepare an auditable commit message, stage files safely, include SDD traceability, verify branch/spec alignment, or verify the working tree before committing. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution.
AI SDLC backend validation workflow. Use when an AI assistant needs to validate Go, SQL, API, provider integration, SDD, or documentation changes in this repository and choose focused deterministic checks without running unrelated expensive tests by default. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution.
Optional AI SDLC evidence-council workflow. Use when an AI assistant needs to review a high-impact topic through several explicit perspectives, orchestrate simulated lenses or truly independent reviewer executions, and synthesize evidence-backed agreements, conflicts, proposals, owners, and unresolved questions without allowing panel members to rewrite authoritative artifacts. Supports `--quick-flow` for labeled simulated review and `--full-flow` for stricter panel and evidence coverage.
AI SDLC Conventional Commit workflow. Use when an AI assistant drafts, validates, reviews, or fixes commit messages in this repository, especially when commits must include SDD spec references, validation summaries, or safe conventional commit subjects. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution.
AI SDLC installation diagnostics and safe upgrade planning. Use when an AI assistant needs to inspect harness prerequisites, repository layout, module and skill registration, detect actionable installation problems, compare versioned file inventories, preview additions/modifications/removals/schema migrations, or produce backup and rollback plans without applying an upgrade. Supports `--quick-flow` and `--full-flow`.
Use after PRFAQ and BRD creation to run a strict final quality review, identify gaps or contradictions, and assign a readiness score before design or development starts. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.