cy-execute-task
Execute PRD Task
Execute one PRD task from exploration through tracking updates.
Required Inputs
- Task specification markdown.
- PRD directory path.
- Task file path.
- Master tasks file path.
- Auto-commit mode.
- Optional workflow memory directory path.
- Optional shared workflow memory path.
- Optional current task memory path.
Workflow
-
Ground in repository and PRD context.
- Read the provided task specification.
- Read the repository guidance files named by the caller.
- Read the PRD documents under the provided directory, especially
_techspec.mdand_tasks.md. - Read ADRs from the
adrs/subdirectory of the PRD directory to understand the architectural decision context for this task. - After reading all sources, check for conflicts between the task specification, techspec, and ADRs. If any requirements contradict each other, stop and report the conflict instead of guessing — do not proceed to step 2.
- If the caller provides workflow memory paths, use the installed
cy-workflow-memoryskill before editing code. - Reconcile the current workspace state before new edits.
-
Build the execution checklist.
- Extract deliverables, acceptance criteria, and every explicit
Validation,Test Plan, orTestingitem into a numbered working checklist. - Print the full checklist before starting implementation so it is visible and trackable.
- Capture the concrete pre-change signal that proves the task is not finished yet.
- Use this checklist as a gate: mark each item done as evidence is produced during implementation, and do not proceed to validation until every checklist item has been addressed.
- Extract deliverables, acceptance criteria, and every explicit
-
Implement the task.
- Keep scope tight to the task specification.
- Follow repository patterns and real dependency APIs.
- Record meaningful out-of-scope work as follow-up notes instead of silently expanding the task.
-
Validate and self-review.
- Run every test and validation command listed in the task specification — not just the repository-wide verification.
- Use the installed
cy-final-verifyskill. This step is mandatory regardless of auto-commit mode — always verify before claiming completion. - Perform a self-review after verification and resolve every blocking issue before proceeding.
-
Update task tracking.
- If workflow memory paths were provided, update the memory files first — record decisions, learnings, and touched surfaces before updating tracking status.
- Use the caller-provided task file path and master tasks file path.
- Mark subtasks complete only when the implementation and evidence are actually complete.
- Change task status to completed only after clean verification and self-review.
- Read
references/tracking-checklist.mdwhen applying status, checklist, or commit updates. - Sequence: memory update (if applicable) -> task file checkboxes -> task status -> master tasks file -> commit (if applicable).
-
Handle commit behavior.
- If auto-commit is enabled, create one local commit after clean verification, self-review, and tracking updates.
- If auto-commit is disabled, leave the diff ready for manual review and commit.
- Never push automatically.
Error Handling
- If the pre-change signal cannot be reproduced directly, capture the strongest available baseline signal and state the limitation.
- If validation fails, keep the task status unchanged until the failure is resolved.
- If tracking files are missing, stop and report the missing path before marking completion.
More from compozy/kb
kb
Comprehensive skill for the `kb` CLI and the Karpathy Knowledge Base pattern. Covers the full KB lifecycle — topic scaffolding, multi-source ingestion (URLs, files, YouTube, bookmarks, codebases), wiki article compilation, cross-article querying with file-back, lint-and-heal passes, QMD indexing, and hybrid search. Also covers codebase-specific analysis via inspect commands for complexity, coupling, blast radius, dead code, circular dependencies, symbol/file lookups, backlinks, and code smells. Use when working with kb CLI commands, knowledge base workflows, code vault generation, code graph analysis, code metrics inspection, wiki compilation, or the ingest-compile-query-lint cycle. Do not use for general code review, linting, formatting, building Go projects, or writing application code.
14systematic-qa
Executes full-project QA like a real user by discovering the repository verification contract, running build, lint, test, and startup commands, exercising core workflows end-to-end, creating realistic fixtures when needed, fixing root-cause regressions, and rerunning the full gate. Use when validating a branch, release candidate, migration, refactor, or risky commit. Do not use for static code review only, one-off unit test edits, or architecture brainstorming without execution.
1cy-create-tasks
Decomposes PRDs and TechSpecs into detailed, independently implementable task files with enrichment from codebase exploration. Use when a PRD or TechSpec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for PRD creation, TechSpec generation, or direct task execution.
1find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
1lesson-learned
Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.
1git-rebase
Intelligently handle git rebase operations and resolve merge conflicts while preserving features and maintaining code quality. Use when rebasing feature branches, resolving conflicts across commits, and ensuring clean linear history without losing changes.
1