Loading...
Loading...
Found 47 Skills
AI SDLC host adapter and capability negotiation workflow. Use when an AI assistant needs to validate a host adapter manifest, map portable workflow operations to host-native operations, negotiate capabilities and limits, select deterministic semantic-preserving fallbacks, or explain why a host cannot run a plan. Supports `--quick-flow` and `--full-flow`.
Use when PRFAQ, BRD, PRD, product brief, workflow, or equivalent initiative artifacts exist and you need to review them for planning gaps, unclear scope, weak priorities, missing actors, and backlog-blocking ambiguity before decomposing work. 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 planning inputs are clear enough and you need to map business goals, roles, capabilities, and outcome-oriented epics before detailed backlog decomposition. 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 evidence-backed project context and bounded task-pack workflow. Use when an AI assistant needs to onboard to a repository, detect stack and commands, map ownership and test topology, check context drift, conditionally select task sources, exclude secrets, or allocate a freshness-aware context pack within an explicit token budget. Supports `--quick-flow` for focused evidence and `--full-flow` for stricter repository coverage.
AI SDLC Git-flow branching workflow. Use when an AI assistant starts implementation work, needs to create or verify a task branch, checks branch/spec alignment, or prepares to hand off a completed user-visible task to validation and commit prep. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution.
AI SDLC evidence-backed retrospective workflow. Use when delivery work is complete or paused and an AI assistant needs to capture observations, connect them to validation or artifact evidence, formulate reviewable process or policy improvement proposals, assign ownership, and preserve the rule that policy changes require an accepted decision. Supports `--quick-flow` for focused learning and `--full-flow` for strict evidence and decision gates.
Use when QA scope and strategy are defined and you need to generate detailed, executable test cases plus smoke, regression, and user acceptance suites tied to requirements, roles, workflows, and risks. 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 after QA strategy and test-case synthesis to build the requirements-to-test traceability matrix, identify missing coverage and test blockers, and score readiness for QA execution. 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 this when you need to execute the AI SDLC (Spec Pack) process in the sdlc-dev repository, select/chain together skills from the demand side (raw/solution/prd/prototype/demo) and implementation side (plan/execute/finishing), and use guardrails to avoid context drift, incorrect directory writes, or skipping critical steps under pressure.
Use this when you need to initialize a new Spec Pack in the AI SDLC workflow of this repository (create a three-digit numbered branch and the `.aisdlc/specs/{num}-{short-name}` directory), or when you are unsure about input parsing, short name rules, UTF-8 BOM file path parameter passing, script invocation methods, or output artifacts when executing `spec-init`.
Audit how agent context (CLAUDE.md / AGENTS.md / rules / skills) lines up with the code across a set of repositories and generate a self-contained HTML report — a short list of specific "things to check" (context behind the code, thin coverage for the codebase, oversized files, no per-area context), plus per-repo raw metrics and a folder tree comparing folder LOC to context coverage. Use when the user wants to audit context coverage across repos, "which repos are missing CLAUDE.md", "where is our agent context thin or stale", "context coverage across my org / projects folder", or "/context-coverage". Works on a local folder of clones or a whole GitHub org via the gh CLI.