skills-catalog/ln-403-task-rework/SKILL.md
Fixes tasks in To Rework by applying reviewer feedback, then returns to To Review. Use when task was rejected during review.
npx skillsauth add levnikolaevich/claude-code-skills ln-403-task-reworkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Paths: File paths (
shared/,references/,../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Ifshared/is missing, fetch files via WebFetch fromhttps://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.
Type: L3 Worker
Executes rework for a single task marked To Rework and hands it back for review.
Hex-line acceleration (if available): Use outline(file_path) before reading large code files. Use read_file() for discovery and read_file(edit_ready=true, verbosity="full") before any edit that needs revision and checksums. After edits: edit_file(base_revision=rev) → verify(checksums). Use changes() to show what was fixed.
Use read_file() and edit_file() as the primary path for code/config/script/test files during rework. Keep read_file() discovery-first by default; request edit_ready=true, verbosity="full" only when you are about to reuse its revision/checksum protocol. Built-in Read/Edit are fallback only when hex-line is unavailable.
| Input | Required | Source | Description |
|-------|----------|--------|-------------|
| taskId | Yes | args, parent Story, kanban, user | Task to rework |
Resolution: Task Resolution Chain. Status filter: To Rework
MANDATORY READ: Load shared/references/environment_state_contract.md, shared/references/storage_mode_detection.md, and shared/references/input_resolution_pattern.md
Extract: task_provider = Task Management → Provider (linear | file).
| Aspect | Linear Mode | File Mode |
|--------|-------------|-----------|
| Load task | get_issue(task_id) | Read("docs/tasks/epics/.../tasks/T{NNN}-*.md") |
| Load review notes | Linear comments | Review section in task file or kanban |
| Update status | save_issue(id, state) | Edit the **Status:** line in file |
File Mode transitions: To Rework → In Progress → To Review
MANDATORY READ: Load shared/references/mcp_tool_preferences.md — ALWAYS use hex-line MCP for code files when available. No fallback to standard Read/Edit unless hex-line is down.
shared/references/goal_articulation_gate.md — State REAL GOAL of this rework (what was actually broken, not "apply feedback"). Combine with 5 Whys (shared/references/problem_solving.md) to ensure root cause is articulated alongside the rework goal. NOT THE GOAL: a superficial patch that addresses the symptom, not the cause.shared/references/code_efficiency_criterion.md — Follow task plan/checkboxes; address config/hardcoded issues; update docs/tests noted in Affected Components and Existing Code Impact. Before handoff, verify 3 efficiency self-checks.MANDATORY READ: Load shared/references/coordinator_summary_contract.md, shared/references/worker_runtime_contract.md, shared/references/task_worker_runtime_contract.md
Shared contract:
summary_kind=task-statusrunId and summaryArtifactPathrunId and exact summaryArtifactPath before the worker writes its validated summaryMonitor (2.1.98+): When verification commands expected >30s, use Monitor. Fallback: Bash(run_in_background=true).
shared/references/environment_state_contract.mdshared/references/storage_mode_detection.mdshared/references/problem_solving.mddocs/tasks/kanban_board.mdVersion: 3.0.0 Last Updated: 2025-12-23
testing
Checks runtime lifecycle and config validation: bootstrap, shutdown, probes, cleanup, env sync, and fail-fast startup. Use for runtime readiness.
testing
Checks races, deadlocks, async hazards, TOCTOU, blocking I/O, and shared resource contention. Use when auditing concurrency correctness.
testing
Checks diagnosability through structured logs, metrics, traces, correlation IDs, and useful log levels. Use when auditing incident visibility.
development
Finds code that can be safely deleted: unreachable, unused, obsolete compatibility, and commented-out code. Use when pruning dead code.