Loading...
Loading...
Found 107 Skills
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 when stories and clarified delivery context are ready and you need to produce a structured delivery specification that engineering and cross-functional teams can use for implementation planning and handoff. 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.
Initialize a repository for ASDLC adoption with AGENTS.md and directory structure
Generate a Software Maintenance Plan (SMP) and supporting maintenance documentation for SDLC projects. Compliant with ISO/IEC/IEEE 14764:2022. Covers Maintenance Strategy, MR/PR handling workflow, CCB process, maintenance cost estimation, and all...
Optional AI SDLC research workflow. Use when an AI assistant needs to investigate a customer, market, domain, technology, regulation, competitor, operational question, or implementation uncertainty and produce a routed source inventory plus synthesized findings with confidence, limitations, open questions, and delivery trace targets. Supports `--quick-flow` for focused evidence and `--full-flow` for multi-source and source-diversity gates.
Use when goals, capabilities, and epics are defined and you need to decompose them into features, user stories, acceptance summaries, and cross-functional delivery tasks. 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 resumable task-runtime workflow. Use when an AI assistant needs to start or resume a versioned delivery run, select dependency-ready work, enforce step, failure, and token budgets, retry safely, persist exact stop reasons, recover state from an append-only journal, or require commit evidence at task boundaries. Supports `--quick-flow` for deterministic local runs and `--full-flow` for strict transition review.
AI SDLC declarative workflow planning. Use when an AI assistant needs to validate a versioned workflow, plan typed dependency steps, evaluate bounded conditions, enforce approval gates, attach deterministic hooks, detect cycles, or create safe dependency waves with sequential fallback when host concurrency or isolation is unavailable. Supports `--quick-flow` and `--full-flow`.
Use after backlog decomposition to define prioritization, MVP and release slices, sequencing, readiness, traceability, and JIRA-ready outputs, then score backlog quality for planning and estimation. 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.
Use when the delivery gap review is complete and you need to convert a clarified initiative package into epics, user stories, acceptance criteria, scenario coverage, and priority signals tied to business value. 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.
Use when a PRFAQ, BRD, or equivalent discovery package exists and you need to review it for delivery gaps, contradictions, missing business rules, and insufficient implementation handoff detail before writing user stories or specs. 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.