formaltask

Guide CLAUDE.md updates based on doc-guard suggestions. This skill should be used when updating documentation, fixing docs, addressing doc-guard suggestions, or updating CLAUDE.md. Activates when user requests "update documentation", "fix docs", "doc-guard suggestions", or "update CLAUDE.md".

Monitor blocked workers and help respond to them. Loop checks ft inbox, shows blocked workers, lets you respond naturally.

Adds tasks to FormalTask with mandatory discovery and validated criteria. Use when "add task", "create task", or "/task-add". For batch creation, use /epic-decompose instead.

Groups uncommitted changes into logical commits, walks through each grouping for approval, then optionally syncs with remote. Resolves merge conflicts interactively with context from recent remote and local history. Use when "commit my changes", "group commits", "smart commit", "commit and sync", or "organize my changes". Never resolves conflicts without user confirmation.

Unified critique for plans, specs, OR task artifacts. Auto-detects target. Spawns auditors. Commits tasks to DB when READY. Use "critique", "review", "is this ready".

Systematic debugging with graded exploration and agent escalation. MUST BE USED when encountering errors, test failures, or unexpected behavior.

Decompose plan -> specs OR specs -> tasks. Auto-detects stage. Use when "decompose", "break down", or after /critique APPROVED. For initial planning, use /plan instead.

Guides error handling patterns in the FormalTask codebase. Use when writing exception handlers, debugging silent failures, or ensuring proper error visibility. Activates on "error handling", "exception", "try/except", or when reviewing error-related code.

Implements code review feedback systematically, then commits and pushes. Use when user provides reviewer comments, PR feedback, or code review notes. One item at a time, mark complete before moving on.

This skill should be used when working with the FormalTask review system. Provides guidance on review types, gates, storage, and the review-fix workflow. Activates when user requests "review workflow", "review gate", "review types", "store review", or when working with task_reviews database operations.

Unified planning with auto scope detection. Use when "plan", "design", "architect", or unclear if task/epic. Routes single tasks to /task. For manual critique, use /critique instead.

Shows planning status dashboard for all projects. Use when "plan status", "what's in flight", "planning dashboard", or checking which projects need attention.

Converts code review findings (P0/P1/P2/P3) into actionable FormalTask issues. Use when "create tasks from review", "fix review issues", "process review findings". Enforces antirez-style prioritization - delete before fix, value before effort.

Narrows exploration proposals into plannable scope. Extracts ideas from conversation, gets user selection, primes context, writes brief for /plan. Use after exploring options, before /planning.

Forces reflection before task completion. Prompts self-reflection FIRST, then shows sibling specs. Mandatory when CHECK_LEARNINGS enabled.

Unified code review router. Detects patterns, proposes reviewers, spawns in parallel. Use "review", "review my changes", "review PR

Thorough two-phase epic review: AC verification then quality review. Use when user requests "/epic-review", "review epic", "is this epic done", or when verifying completed epics. Phase 1 gates Phase 2.

Unified revise for plans OR specs. Auto-detects target from critique report. Use when "revise", "fix plan/specs", or after /critique returns FIX_AND_SHIP. For initial creation, use /plan instead.

Ships a worktree: reviews changes, commits in logical groups, creates PR, merges, cleans up worktree+branch. Use when "ship worktree", "land worktree", "ship-worktree", or finishing work in a git worktree. For commits only, use committing-changes instead.

Monitor blocked workers and help respond to them. Loop checks ft work inbox, shows blocked workers, lets you respond naturally.

Single task creation shortcut. Use when /plan routes here (scope=TASK) or for quick task capture. For 2+ tasks, use /plan instead.

Enforces Red-Green-Refactor cycle with automated tdd-guard validation. Failing test required before implementation. tdd-guard blocks Write/Edit without test coverage. Use for all features and bugfixes.

Validates spec claims match codebase reality during /epic-finalize. Verifies file paths, symbols, and library claims. Produces P0/P1/P2 findings.

This skill should be used when validating batches of task specifications before creation. Activates when processing task plans from review findings, epic decompositions, or any batch task generation. Use when user says "validate task plan", "check these tasks", "are these tasks well-specified", or when --validate flag is passed to pm-review-fix. Ensures expert-planning quality standards, complete coverage, proper grouping, and priority preservation.

Forces meticulous self-review of work just completed. Itemizes every change, creates verification todos, then hunts for gaps using structured uncertainty analysis. Use after finishing implementation work, before claiming done.