Loading...
Loading...
Found 38 Skills
Enforces spec-before-code workflow for AI-driven development. Automatically selects Spec-Kit or OpenSpec mode, triages complexity (quick/standard/thorough), recovers session context, and applies quality gates (G0-G4) with automated review loops at every stage. Use this skill whenever the user says "/super-spec", "spec first", "规范先行", or starts any feature, bugfix, or refactor — especially in projects with .spec-mode, .specify/, or openspec/ directories. Even if the user doesn't explicitly ask for spec-driven workflow, activate this skill for any non-trivial code change to prevent skipping the design phase. Orchestrates: Spec-Kit/OpenSpec (OPSX) + planning-with-files + ui-ux-pro-max (v2.0, 67 styles, 161 palettes, 13 stacks) + Superpowers (TDD, code review, verification, debugging, spec/plan review loops, subagent model selection).
Use when a feature, bugfix, review, planning, implementation, verification, commit, push, or PR task needs orchestration across multiple project skills. Maestro is the entry point for full-cycle engineering work: classify the request, choose the right domain/framework skills, enforce planning/build/publish gates, and carry the task from intake to done without replacing the specialized skills it coordinates.
Protocol orchestrator CLI — drives SPIR, ASPIR, AIR, and BUGFIX protocols via a state machine. ALWAYS check this skill before running any `porch` command. Use when you need to check project status, approve gates, signal phase completion, or manage protocol state. Also use when a builder asks about gate approvals or phase transitions.
Use when planning work (to create items and tasks), when starting implementation (to mark tasks in-progress), when completing work (to mark tasks done), or to check backlog status. Manages .backlogmd/ for features, bugfixes, refactors, and chores.
Use when implementing any Swift or SwiftUI feature or bugfix, before writing implementation code
Standard end-to-end workflow for shipping a feature/bugfix from a Jira task to a merged GitLab MR. Use when the user references a Jira task ID (WRA-XX, etc.), asks to "start a task", "create branch from task", "review the last change", "review the whole branch", "commit and push", "create a merge request", "review the MR !N", "post review result to the MR", "fix all issues", or "merge the request". Covers branch naming, commit format, MR creation, micro + macro code review (3-agent parallel), fix loop, and merge.
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
Use when implementing any feature or bugfix, before writing implementation code
Write a bounded fresh-context prompt or file for continuation, implementation, research, refactor, bugfix, review, or review-fix work.
File or link CawPlan defects from failed/blocked TestRail Results via QA Insights A4. Use when: SQA wants to turn a TestRail Failed/Blocked Result into a CawPlan Ticket, paste a tests/view URL to file a defect, review an A4 defect draft, create a BUGFIX/FEATURE ticket, or link an existing ticket back to TestRail defects. Cold start with tests/view MUST call execution failures --test-id BEFORE defects draft; never use test_id as the draft path result_id. A4 write path (create-ticket) MUST use --body-file or --body JSON — never field flags like --description or --result-id. NOT for: importing test cases (use `cawplan-testcase-import`); creating TestRail Plans/Runs (use `cawplan-testplan-layout`); release risk assessment; generating requirements or test points.
Inkblot git branch naming convention. Use when creating a branch, checking out a feature/bugfix branch, naming a PR branch, or when the user asks to start work on a Jira ticket.
Write the test first, watch it fail, then write the least code that passes. Covers where the test belongs, what makes it honest, what a passing test proves and what it does not, recovering when code was written before the test, and starting a bug fix from a red run. A test nobody watched fail proves nothing. Use when implementing a feature or a bugfix, when a test was written after the code, when a test passes the first time you run it, or when the user says "write tests for this", "add coverage", or "TDD this". Not for judging tests inside a change under review, and not for choosing a test framework.