Loading...
Loading...
Found 174 Skills
Use this when you are about to start Discover for an existing project, but you don't know "which portals can be used as evidence (run/test/ci/contract/ops)" and "which modules should be prioritized (P0/P1/P2)", and you are worried that out-of-control scope will lead to unmaintainable results.
Use when you have confirmed the scope of Discover (P0/P1/P2), and now need to quickly build the Level-0 North Star (memory) and Level-1 map layer index skeleton (components/products) under `.aisdlc/project/`, so that you can supplement evidence by module later without double writing and drift.
Use when you already have a components map and multiple module pages, and now need to converge business modules (products <= 6), fix the entry points for operation, troubleshooting and rollback (ops), and implement DoD access control and incremental Discover (Delta Discover, stale expiration detection) to ensure the knowledge base is usable and maintainable.
Use when you need to turn selected modules (P0 priority first) into single-page module SSOT at the path `.aisdlc/project/components/{module}.md`, and build authoritative entries for API/Data contracts, invariant summaries, evidence entries and structured Evidence Gaps in the same page to meet the DoD gate requirements of Discover.
Repository structure methodology for maximum AI agent effectiveness. Three pillars — context engineering (repo as knowledge product), architectural constraints (deterministic enforcement), garbage collection (active entropy fighting). Use when setting up repos for AI development, diagnosing repeated agent failures, writing AGENTS.md, or designing CI gates and structural tests.
Backlog Grooming Assistant - Auto-activating skill for Enterprise Workflows. Triggers on: backlog grooming assistant, backlog grooming assistant Part of the Enterprise Workflows skill category.
Single Responsibility Principle, ensuring that code files, functions, and modules have clear and single responsibilities. Applicable to all code files.
Use when you need to perform I2 (Implementation Execution) in the Spec Pack of sdlc-dev, implement in batches with `{FEATURE_DIR}/implementation/plan.md` as the only SSOT, run minimal verification, write back audit information, and report at batch checkpoints; stop immediately when encountering blocking or clarification required items.
Create or update the project constitution through interactive phase-based
Technology preference analysis process. When selecting, planning or recommending technical solutions, analyze preferences first before giving suggestions; meanwhile, deposit newly discovered preferences back to this skill.
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.
Implement PRDs/specs with a mandatory precheck review before coding. Use when a user asks to implement a PRD/feature spec/requirements doc or says "implement PRD/spec". Perform a preflight review, raise questions on scope/consistency/risks, then implement after confirmation.