[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FJB5F1WSV1PDFTYWZM36M2":3,"skill-same:01M6FJB5F1WSV1PDFTYWZM36M2":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6FJB5F1WSV1PDFTYWZM36M2","ln-401-task-executor",null,"Executes implementation tasks through Todo, In Progress, To Review. Use when task needs coding with KISS\u002FYAGNI. Not for test tasks.","boisenoise\u002Fskills-collections","boisenoise","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193180?v=4","01M6CDBDQK6BDN55ZMA6B6PKBM","01M6CDBDVSJ3JPTBYN26FZ7TZK",12,"MIT","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Flevn-ln-401-task-executor\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"ln","ln 401 task executor","executor","task","yagni","when","inspect","with","line","progress","project","hex","outline","todo","MCP","use","edit","write","read","find","analyze","Bash","verify","file","tasks","test","review","2026-11-10 10:12:30",false,"---\nname: ln-401-task-executor\ndescription: \"Executes implementation tasks through Todo, In Progress, To Review. Use when task needs coding with KISS\u002FYAGNI. Not for test tasks.\"\nallowed-tools: Read, Grep, Glob, Bash, mcp__hex-line__outline, mcp__hex-line__read_file, mcp__hex-line__edit_file, mcp__hex-line__write_file, mcp__hex-line__verify, mcp__hex-line__changes, mcp__hex-line__inspect_path, mcp__hex-graph__index_project, mcp__hex-graph__find_symbols, mcp__hex-graph__inspect_symbol, mcp__hex-graph__analyze_edit_region\nlicense: MIT\n---\n\n> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If `shared\u002F` is missing, fetch files via WebFetch from `https:\u002F\u002Fraw.githubusercontent.com\u002Flevnikolaevich\u002Fclaude-code-skills\u002Fmaster\u002Fskills\u002F{path}`.\n\n# Implementation Task Executor\n\n**Type:** L3 Worker\n\nExecutes a single implementation (or refactor) task from Todo to To Review using the task description and linked guides.\n\n## Purpose & Scope\n- Handle one selected task only; never touch other tasks.\n- Follow task Technical Approach\u002Fplan\u002FAC; apply KISS\u002FYAGNI and guide patterns.\n- Update Linear\u002Fkanban for this task: Todo -> In Progress -> To Review.\n- Run typecheck\u002Flint; update docs\u002Ftests\u002Fconfig per task instructions.\n- Not for test tasks (label \"tests\" goes to ln-404-test-executor).\n\n**Hex MCP acceleration (if available):** Use narrow `inspect_path(path=\u003Crelevant dir>)` and `outline(file_path)` before reading large code files; avoid repo-root wildcard inventories unless you intentionally need one. Use `grep_search(output_mode=\"summary\")` first for search\u002Fdiscovery, then escalate to `output_mode=\"content\", edit_ready=true` only when you need canonical hunks for follow-up edits; use `allow_large_output=true` only as an explicit last resort. Use `read_file()` in discovery mode for structure and targeted ranges; when you need `revision` and checksums for a follow-up edit, refresh that file with `read_file(edit_ready=true, verbosity=\"full\")` before `edit_file()`. For edits to existing code, run `index_project(path=project_root)` once and use `analyze_edit_region(...)` before non-trivial edits. After edits: `edit_file(base_revision=rev)` -> `verify(checksums)`. Before handoff: `changes()` to review diff.\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `taskId` | Yes | args, parent Story, kanban, user | Task to execute |\n\n**Resolution:** Task Resolution Chain.\n**Status filter:** Todo\n\n## Task Storage Mode\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fenvironment_state_contract.md`, `shared\u002Freferences\u002Fstorage_mode_detection.md`, and `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\nExtract: `task_provider` = Task Management → Provider (`linear` | `file`).\n\n| Aspect | Linear Mode | File Mode |\n|--------|-------------|-----------|\n| **Load task** | `get_issue(task_id)` | `Read(\"docs\u002Ftasks\u002Fepics\u002F...\u002Ftasks\u002FT{NNN}-*.md\")` |\n| **Update status** | `save_issue(id, state)` | `Edit` the `**Status:**` line in file |\n| **Kanban** | Updated by Linear sync | Must update `kanban_board.md` manually |\n\n**File Mode status format:**\n```markdown\n## Status\n**Status:** In Progress | **Priority:** High | **Estimate:** 4h\n```\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmcp_tool_preferences.md` and `shared\u002Freferences\u002Fmcp_integration_patterns.md` — use hex-line MCP for code files when available and hex-graph for semantic edit-risk questions.\n\n## Mode Detection\n\nDetect operating mode at startup:\n\n**Plan Mode Active:**\n- Steps 1-2: Load task context (read-only, OK in plan mode)\n- Generate EXECUTION PLAN (files to create\u002Fmodify, approach) → write to plan file\n- Call ExitPlanMode → STOP. Do NOT implement.\n- Steps 3-6: After approval → execute implementation\n\n**Normal Mode:**\n- Steps 1-6: Standard workflow without stopping\n\n## Progress Tracking with TodoWrite\n\nWhen operating in any mode, skill MUST create detailed todo checklist tracking ALL steps.\n\n**Rules:**\n1. Create todos IMMEDIATELY before Step 1\n2. Each workflow step = separate todo item; implementation step gets sub-items\n3. Mark `in_progress` before starting step, `completed` after finishing\n\n**Todo Template (10 items):**\n\n```\nStep 1: Resolve taskId\n  - Resolve via args \u002F Story context \u002F kanban \u002F AskUserQuestion (Todo filter)\n\nStep 2: Load Context\n  - Fetch full task description + linked guides\u002Fmanuals\u002FADRs\n\nStep 2b: Goal Articulation Gate\n  - Complete 4 questions from shared\u002Freferences\u002Fgoal_articulation_gate.md (\u003C=25 tokens each)\n\nStep 2c: Implementation Blueprint\n  - From task \"Affected Components\": extract file paths (Glob\u002FGrep or narrow `inspect_path(path=\u003Ccomponent dir>)` to find actual paths)\n  - Read each file (or key sections) to understand current structure\n  - IF modifying existing code in supported languages: `index_project(path=project_root)` once, then use path-scoped `find_symbols` \u002F `inspect_symbol` for exact symbol identity and `analyze_edit_region` before editing non-trivial ranges\n  - IF `find_symbols` returns `partial ... truncated=1` or a broad candidate set: refine to `name + file` or `workspace_qualified_name` before planning from it\n  - Output:\n    ## Implementation Blueprint: {taskId}\n    **Files to create:** [list with brief purpose]\n    **Files to modify:** [list with what changes]\n    **Change order (dependencies first):**\n    1. {file} — {what and why first}\n    2. {file} — {depends on step 1}\n    **Risks:** {shared files with parallel tasks, if any}\n  - Scope: ONLY files of this task. Do not analyze other tasks.\n\n  - **Checkpoint:** Emit PHASE_3 checkpoint with structured `blueprint` payload:\n    `{ \"blueprint\": { \"change_order\": [{ \"file\": \"...\", \"action\": \"create|modify\", \"reason\": \"...\" }] } }`\n    Guard blocks PHASE_4 if blueprint is missing from the checkpoint.\n\nStep 3: Start Work\n  - Set task to In Progress, update kanban\n\nStep 4: Implement\n  - 4a Pattern Reuse: IF creating new file\u002Futility, Grep src\u002F for existing similar patterns\n    (error handlers, validators, HTTP wrappers, config loaders). Reuse if found.\n  - 4b Follow task plan\u002FAC, apply KISS\u002FYAGNI\n  - 4c Architecture Guard: IF creating service function: (1) 3+ side-effect categories in **leaf** function → split (EXCEPT orchestrator functions that delegate sequentially — these are expected to have 3+ categories);\n    (2) get_*\u002Ffind_*\u002Fcheck_* naming → verify no hidden writes; (3) 3+ service imports in **leaf** function → flatten (orchestrator imports are expected)\n    (4) **Frontend Guard (conditional):** IF affected files include `.tsx\u002F.vue\u002F.svelte\u002F.html\u002F.css` → **MANDATORY READ:** Load `shared\u002Freferences\u002Ffrontend_design_guide.md`. Load project's design_guidelines.md if exists (design tokens source of truth). Verify: one composition per viewport; max 2 typefaces + 1 accent color; cards only when interaction requires; motion max 2-3 purposeful; WCAG 2.1 AA contrast (4.5:1 text, 3:1 UI elements)\n  - Update docs and existing tests if impacted\n  - Execute verify: methods from task AC (test\u002Fcommand\u002Finspect)\n\nStep 5: Quality\n  - Run typecheck and lint (or project equivalents)\n  - 5b Blueprint Completion: compare actual changes to blueprint; emit blueprint_status in PHASE_6 checkpoint\n\nStep 6: Finish\n  - Set task to To Review, update kanban\n  - Add summary comment (changes, tests, docs)\n```\n\n## Workflow (concise)\n1) **Resolve taskId:** Run Task Resolution Chain per guide (status filter: [Todo]).\n2) **Load context:** Fetch full task description (Linear: get_issue; File: Read task file); read linked guides\u002Fmanuals\u002FADRs\u002Fresearch; auto-discover team\u002Fconfig if needed.\n2b) **Goal gate:** **MANDATORY READ:** Load `shared\u002Freferences\u002Fgoal_articulation_gate.md` — Complete the 4-question gate (\u003C=25 tokens each). State REAL GOAL (deliverable as subject), DONE LOOKS LIKE, NOT THE GOAL, INVARIANTS & HIDDEN CONSTRAINTS.\n2c) **Implementation Blueprint:** From task \"Affected Components\", find actual file paths via Glob\u002FGrep or narrow `inspect_path(path=\u003Ccomponent dir>)`. Read key sections of each file. If task changes existing code in supported languages, build graph context once (`index_project`) and use path-scoped `find_symbols` \u002F `inspect_symbol` for exact symbol identity plus `analyze_edit_region` before editing non-trivial ranges. If symbol discovery is truncated, refine to `name + file` or `workspace_qualified_name` before planning from it. Output structured plan: files to create\u002Fmodify, change order (dependencies first), risks (shared files with parallel tasks, external callers, public API surfaces). Scope: this task only.\n3) **Start work:** Update this task to In Progress (Linear: update_issue; File: Edit status line); move it in kanban (keep Epic\u002FStory indent).\n4) **Implement (with verification loop):** **Before writing new utilities\u002Fhandlers**, Grep `src\u002F` for existing patterns (error handling, validation, config access). Reuse if found; if not reusable, document rationale in code comment. For edits to existing functions, classes, routes, or middleware, run `analyze_edit_region` first and account for external callers, clone siblings, downstream flow, and public API risk. Follow checkboxes\u002Fplan; keep it simple; avoid hardcoded values; reuse existing components; update docs noted in Affected Components; update existing tests if impacted (no new tests here). Before creating service functions, apply Architecture Guard (cascade depth, interface honesty, flat orchestration; for frontend files: **MANDATORY READ** `shared\u002Freferences\u002Ffrontend_design_guide.md`, load design_guidelines.md if exists, verify composition\u002Ftypography\u002FWCAG rules). After implementation, execute `verify:` methods from task AC: test → run specified test; command → execute and check output; inspect → verify file\u002Fcontent exists. If any verify fails → fix before proceeding.\n5) **Quality:** Run typecheck and lint (or project equivalents); ensure instructions in Existing Code Impact are addressed. **Blueprint Completion:** compare actual changes against blueprint from Step 2c — for each planned file mark completed or skipped (with justification), for each unplanned file mark added (with justification). Emit PHASE_6 checkpoint: `{ \"blueprint_status\": { \"planned_count\": N, \"completed\": [...], \"skipped\": [{\"file\":\"...\",\"justification\":\"...\"}], \"added\": [{\"file\":\"...\",\"justification\":\"...\"}], \"completion_pct\": N } }`. Guard blocks PHASE_7 if missing.\n6) **Finish:** Mark task To Review (Linear: update_issue; File: Edit status line); update kanban to To Review; add summary comment (what changed, tests run, docs touched).\n\n## Pre-Submission Checklist\n\n**Context:** Self-assessment before To Review reduces review round-trips and catches obvious issues early.\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcode_efficiency_criterion.md` — self-check before submission.\n\nBefore setting To Review, verify all items:\n\n| # | Check | Verify |\n|---|-------|--------|\n| 0 | **AC verified** | Each AC `verify:` method executed with pass evidence |\n| 1 | **Approach alignment** | Implementation matches Story Technical Approach |\n| 2 | **Clean code** | No dead code, no backward-compat shims, unused imports removed |\n| 3 | **Config hygiene** | No hardcoded creds\u002FURLs\u002Fmagic numbers |\n| 4 | **Docs updated** | Affected Components docs reflect changes |\n| 5 | **Tests pass** | Existing tests still pass after changes |\n| 6 | **Pattern reuse** | New utilities checked against existing codebase; no duplicate patterns introduced |\n| 7 | **Architecture guard** | Cascade depth \u003C= 2 (leaf functions); no hidden writes in read-named functions; no service chains >= 3 in leaf functions (orchestrator imports exempt). Frontend files: composition, typography, WCAG per `shared\u002Freferences\u002Ffrontend_design_guide.md` |\n| 8 | **Destructive op safety** | If task has \"Destructive Operation Safety\" section: (1) backup step executed\u002Fplanned before destructive code, (2) rollback mechanism exists in code, (3) environment guard present, (4) preview\u002Fdry-run evidence attached or referenced |\n| 9 | **Code efficiency** | No unnecessary intermediates, verbose patterns replaced by language idioms, no boilerplate framework handles (per `shared\u002Freferences\u002Fcode_efficiency_criterion.md`) |\n| 10 | **Blueprint complete** | All blueprint items completed or skipped with justification; `blueprint_status` emitted in PHASE_6 checkpoint |\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fdestructive_operation_safety.md` for severity classification and safety requirements.\n\n**HITL Gate:** IF task severity = CRITICAL (per destructive_operation_safety.md loaded above): Use `AskUserQuestion` to confirm before marking To Review: \"Task contains CRITICAL destructive operation: {operation}. Backup plan: {plan}. Proceed?\" Do NOT mark To Review until user confirms.\n\n**If any check fails:** Fix before setting To Review. Do not rely on reviewer to catch preventable issues.\n\n## Critical Rules\n- Single-task updates only; no bulk status changes.\n- Keep language of the task (EN\u002FRU) in edits\u002Fcomments.\n- No code snippets in the description; code lives in repo, not in Linear.\n- No new test creation; only update existing tests if required.\n- Preserve Foundation-First ordering from orchestrator; do not reorder tasks.\n- **Do NOT commit.** Leave all changes uncommitted — the reviewer reviews and commits.\n- Before non-trivial edits to existing code, use graph impact evidence when available instead of guessing blast radius from file names alone.\n\n## Runtime Summary Artifact\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcoordinator_summary_contract.md`, `shared\u002Freferences\u002Fworker_runtime_contract.md`, `shared\u002Freferences\u002Ftask_worker_runtime_contract.md`\n\nShared contract:\n- emit `summary_kind=task-status`\n- standalone mode omits `runId` and `summaryArtifactPath`\n- managed mode passes both `runId` and exact `summaryArtifactPath` before the worker writes its validated summary\n\n**Monitor (2.1.98+):** When verification commands expected >30s, use `Monitor`. Fallback: `Bash(run_in_background=true)`.\n\n## Definition of Done\n- [ ] Task selected and set to In Progress; kanban updated accordingly.\n- [ ] Guides\u002Fmanuals\u002FADRs\u002Fresearch read; approach aligned with task Technical Approach.\n- [ ] Implementation completed per plan\u002FAC; each AC `verify:` method executed with pass evidence.\n- [ ] Docs and impacted tests updated.\n- [ ] Typecheck and lint passed (or project quality commands) with evidence in comment.\n- [ ] Task set to To Review; kanban moved to To Review; summary comment added.\n- [ ] Runtime summary artifact written to the shared task-status location.\n\n## Reference Files\n- **Environment state:** `shared\u002Freferences\u002Fenvironment_state_contract.md`\n- **Storage mode operations:** `shared\u002Freferences\u002Fstorage_mode_detection.md`\n- Guides\u002Fmanuals\u002FADRs\u002Fresearch: `docs\u002Fguides\u002F`, `docs\u002Fmanuals\u002F`, `docs\u002Fadrs\u002F`, `docs\u002Fresearch\u002F`\n- Kanban format: `docs\u002Ftasks\u002Fkanban_board.md`\n\n---\n**Version:** 3.0.0\n**Last Updated:** 2025-12-23\n","> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If `shared\u002F` is missing, fetch files via WebFetch from `https:\u002F\u002Fraw.githubusercontent.com\u002Flevnikolaevich\u002Fclaude-code-skills\u002Fmaster\u002Fskills\u002F{path}`.\n\n# Implementation Task Executor\n\n**Type:** L3 Worker\n\nExecutes a single implementation (or refactor) task from Todo to To Review using the task description and linked guides.\n\n## Purpose & Scope\n- Handle one selected task only; never touch other tasks.\n- Follow task Technical Approach\u002Fplan\u002FAC; apply KISS\u002FYAGNI and guide patterns.\n- Update Linear\u002Fkanban for this task: Todo -> In Progress -> To Review.\n- Run typecheck\u002Flint; update docs\u002Ftests\u002Fconfig per task instructions.\n- Not for test tasks (label \"tests\" goes to ln-404-test-executor).\n\n**Hex MCP acceleration (if available):** Use narrow `inspect_path(path=\u003Crelevant dir>)` and `outline(file_path)` before reading large code files; avoid repo-root wildcard inventories unless you intentionally need one. Use `grep_search(output_mode=\"summary\")` first for search\u002Fdiscovery, then escalate to `output_mode=\"content\", edit_ready=true` only when you need canonical hunks for follow-up edits; use `allow_large_output=true` only as an explicit last resort. Use `read_file()` in discovery mode for structure and targeted ranges; when you need `revision` and checksums for a follow-up edit, refresh that file with `read_file(edit_ready=true, verbosity=\"full\")` before `edit_file()`. For edits to existing code, run `index_project(path=project_root)` once and use `analyze_edit_region(...)` before non-trivial edits. After edits: `edit_file(base_revision=rev)` -> `verify(checksums)`. Before handoff: `changes()` to review diff.\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `taskId` | Yes | args, parent Story, kanban, user | Task to execute |\n\n**Resolution:** Task Resolution Chain.\n**Status filter:** Todo\n\n## Task Storage Mode\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fenvironment_state_contract.md`, `shared\u002Freferences\u002Fstorage_mode_detection.md`, and `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\nExtract: `task_provider` = Task Management → Provider (`linear` | `file`).\n\n| Aspect | Linear Mode | File Mode |\n|--------|-------------|-----------|\n| **Load task** | `get_issue(task_id)` | `Read(\"docs\u002Ftasks\u002Fepics\u002F...\u002Ftasks\u002FT{NNN}-*.md\")` |\n| **Update status** | `save_issue(id, state)` | `Edit` the `**Status:**` line in file |\n| **Kanban** | Updated by Linear sync | Must update `kanban_board.md` manually |\n\n**File Mode status format:**\n```markdown\n## Status\n**Status:** In Progress | **Priority:** High | **Estimate:** 4h\n```\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmcp_tool_preferences.md` and `shared\u002Freferences\u002Fmcp_integration_patterns.md` — use hex-line MCP for code files when available and hex-graph for semantic edit-risk questions.\n\n## Mode Detection\n\nDetect operating mode at startup:\n\n**Plan Mode Active:**\n- Steps 1-2: Load task context (read-only, OK in plan mode)\n- Generate EXECUTION PLAN (files to create\u002Fmodify, approach) → write to plan file\n- Call ExitPlanMode → STOP. Do NOT implement.\n- Steps 3-6: After approval → execute implementation\n\n**Normal Mode:**\n- Steps 1-6: Standard workflow without stopping\n\n## Progress Tracking with TodoWrite\n\nWhen operating in any mode, skill MUST create detailed todo checklist tracking ALL steps.\n\n**Rules:**\n1. Create todos IMMEDIATELY before Step 1\n2. Each workflow step = separate todo item; implementation step gets sub-items\n3. Mark `in_progress` before starting step, `completed` after finishing\n\n**Todo Template (10 items):**\n\n```\nStep 1: Resolve taskId\n  - Resolve via args \u002F Story context \u002F kanban \u002F AskUserQuestion (Todo filter)\n\nStep 2: Load Context\n  - Fetch full task description + linked guides\u002Fmanuals\u002FADRs\n\nStep 2b: Goal Articulation Gate\n  - Complete 4 questions from shared\u002Freferences\u002Fgoal_articulation_gate.md (\u003C=25 tokens each)\n\nStep 2c: Implementation Blueprint\n  - From task \"Affected Components\": extract file paths (Glob\u002FGrep or narrow `inspect_path(path=\u003Ccomponent dir>)` to find actual paths)\n  - Read each file (or key sections) to understand current structure\n  - IF modifying existing code in supported languages: `index_project(path=project_root)` once, then use path-scoped `find_symbols` \u002F `inspect_symbol` for exact symbol identity and `analyze_edit_region` before editing non-trivial ranges\n  - IF `find_symbols` returns `partial ... truncated=1` or a broad candidate set: refine to `name + file` or `workspace_qualified_name` before planning from it\n  - Output:\n    ## Implementation Blueprint: {taskId}\n    **Files to create:** [list with brief purpose]\n    **Files to modify:** [list with what changes]\n    **Change order (dependencies first):**\n    1. {file} — {what and why first}\n    2. {file} — {depends on step 1}\n    **Risks:** {shared files with parallel tasks, if any}\n  - Scope: ONLY files of this task. Do not analyze other tasks.\n\n  - **Checkpoint:** Emit PHASE_3 checkpoint with structured `blueprint` payload:\n    `{ \"blueprint\": { \"change_order\": [{ \"file\": \"...\", \"action\": \"create|modify\", \"reason\": \"...\" }] } }`\n    Guard blocks PHASE_4 if blueprint is missing from the checkpoint.\n\nStep 3: Start Work\n  - Set task to In Progress, update kanban\n\nStep 4: Implement\n  - 4a Pattern Reuse: IF creating new file\u002Futility, Grep src\u002F for existing similar patterns\n    (error handlers, validators, HTTP wrappers, config loaders). Reuse if found.\n  - 4b Follow task plan\u002FAC, apply KISS\u002FYAGNI\n  - 4c Architecture Guard: IF creating service function: (1) 3+ side-effect categories in **leaf** function → split (EXCEPT orchestrator functions that delegate sequentially — these are expected to have 3+ categories);\n    (2) get_*\u002Ffind_*\u002Fcheck_* naming → verify no hidden writes; (3) 3+ service imports in **leaf** function → flatten (orchestrator imports are expected)\n    (4) **Frontend Guard (conditional):** IF affected files include `.tsx\u002F.vue\u002F.svelte\u002F.html\u002F.css` → **MANDATORY READ:** Load `shared\u002Freferences\u002Ffrontend_design_guide.md`. Load project's design_guidelines.md if exists (design tokens source of truth). Verify: one composition per viewport; max 2 typefaces + 1 accent color; cards only when interaction requires; motion max 2-3 purposeful; WCAG 2.1 AA contrast (4.5:1 text, 3:1 UI elements)\n  - Update docs and existing tests if impacted\n  - Execute verify: methods from task AC (test\u002Fcommand\u002Finspect)\n\nStep 5: Quality\n  - Run typecheck and lint (or project equivalents)\n  - 5b Blueprint Completion: compare actual changes to blueprint; emit blueprint_status in PHASE_6 checkpoint\n\nStep 6: Finish\n  - Set task to To Review, update kanban\n  - Add summary comment (changes, tests, docs)\n```\n\n## Workflow (concise)\n1) **Resolve taskId:** Run Task Resolution Chain per guide (status filter: [Todo]).\n2) **Load context:** Fetch full task description (Linear: get_issue; File: Read task file); read linked guides\u002Fmanuals\u002FADRs\u002Fresearch; auto-discover team\u002Fconfig if needed.\n2b) **Goal gate:** **MANDATORY READ:** Load `shared\u002Freferences\u002Fgoal_articulation_gate.md` — Complete the 4-question gate (\u003C=25 tokens each). State REAL GOAL (deliverable as subject), DONE LOOKS LIKE, NOT THE GOAL, INVARIANTS & HIDDEN CONSTRAINTS.\n2c) **Implementation Blueprint:** From task \"Affected Components\", find actual file paths via Glob\u002FGrep or narrow `inspect_path(path=\u003Ccomponent dir>)`. Read key sections of each file. If task changes existing code in supported languages, build graph context once (`index_project`) and use path-scoped `find_symbols` \u002F `inspect_symbol` for exact symbol identity plus `analyze_edit_region` before editing non-trivial ranges. If symbol discovery is truncated, refine to `name + file` or `workspace_qualified_name` before planning from it. Output structured plan: files to create\u002Fmodify, change order (dependencies first), risks (shared files with parallel tasks, external callers, public API surfaces). Scope: this task only.\n3) **Start work:** Update this task to In Progress (Linear: update_issue; File: Edit status line); move it in kanban (keep Epic\u002FStory indent).\n4) **Implement (with verification loop):** **Before writing new utilities\u002Fhandlers**, Grep `src\u002F` for existing patterns (error handling, validation, config access). Reuse if found; if not reusable, document rationale in code comment. For edits to existing functions, classes, routes, or middleware, run `analyze_edit_region` first and account for external callers, clone siblings, downstream flow, and public API risk. Follow checkboxes\u002Fplan; keep it simple; avoid hardcoded values; reuse existing components; update docs noted in Affected Components; update existing tests if impacted (no new tests here). Before creating service functions, apply Architecture Guard (cascade depth, interface honesty, flat orchestration; for frontend files: **MANDATORY READ** `shared\u002Freferences\u002Ffrontend_design_guide.md`, load design_guidelines.md if exists, verify composition\u002Ftypography\u002FWCAG rules). After implementation, execute `verify:` methods from task AC: test → run specified test; command → execute and check output; inspect → verify file\u002Fcontent exists. If any verify fails → fix before proceeding.\n5) **Quality:** Run typecheck and lint (or project equivalents); ensure instructions in Existing Code Impact are addressed. **Blueprint Completion:** compare actual changes against blueprint from Step 2c — for each planned file mark completed or skipped (with justification), for each unplanned file mark added (with justification). Emit PHASE_6 checkpoint: `{ \"blueprint_status\": { \"planned_count\": N, \"completed\": [...], \"skipped\": [{\"file\":\"...\",\"justification\":\"...\"}], \"added\": [{\"file\":\"...\",\"justification\":\"...\"}], \"completion_pct\": N } }`. Guard blocks PHASE_7 if missing.\n6) **Finish:** Mark task To Review (Linear: update_issue; File: Edit status line); update kanban to To Review; add summary comment (what changed, tests run, docs touched).\n\n## Pre-Submission Checklist\n\n**Context:** Self-assessment before To Review reduces review round-trips and catches obvious issues early.\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcode_efficiency_criterion.md` — self-check before submission.\n\nBefore setting To Review, verify all items:\n\n| # | Check | Verify |\n|---|-------|--------|\n| 0 | **AC verified** | Each AC `verify:` method executed with pass evidence |\n| 1 | **Approach alignment** | Implementation matches Story Technical Approach |\n| 2 | **Clean code** | No dead code, no backward-compat shims, unused imports removed |\n| 3 | **Config hygiene** | No hardcoded creds\u002FURLs\u002Fmagic numbers |\n| 4 | **Docs updated** | Affected Components docs reflect changes |\n| 5 | **Tests pass** | Existing tests still pass after changes |\n| 6 | **Pattern reuse** | New utilities checked against existing codebase; no duplicate patterns introduced |\n| 7 | **Architecture guard** | Cascade depth \u003C= 2 (leaf functions); no hidden writes in read-named functions; no service chains >= 3 in leaf functions (orchestrator imports exempt). Frontend files: composition, typography, WCAG per `shared\u002Freferences\u002Ffrontend_design_guide.md` |\n| 8 | **Destructive op safety** | If task has \"Destructive Operation Safety\" section: (1) backup step executed\u002Fplanned before destructive code, (2) rollback mechanism exists in code, (3) environment guard present, (4) preview\u002Fdry-run evidence attached or referenced |\n| 9 | **Code efficiency** | No unnecessary intermediates, verbose patterns replaced by language idioms, no boilerplate framework handles (per `shared\u002Freferences\u002Fcode_efficiency_criterion.md`) |\n| 10 | **Blueprint complete** | All blueprint items completed or skipped with justification; `blueprint_status` emitted in PHASE_6 checkpoint |\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fdestructive_operation_safety.md` for severity classification and safety requirements.\n\n**HITL Gate:** IF task severity = CRITICAL (per destructive_operation_safety.md loaded above): Use `AskUserQuestion` to confirm before marking To Review: \"Task contains CRITICAL destructive operation: {operation}. Backup plan: {plan}. Proceed?\" Do NOT mark To Review until user confirms.\n\n**If any check fails:** Fix before setting To Review. Do not rely on reviewer to catch preventable issues.\n\n## Critical Rules\n- Single-task updates only; no bulk status changes.\n- Keep language of the task (EN\u002FRU) in edits\u002Fcomments.\n- No code snippets in the description; code lives in repo, not in Linear.\n- No new test creation; only update existing tests if required.\n- Preserve Foundation-First ordering from orchestrator; do not reorder tasks.\n- **Do NOT commit.** Leave all changes uncommitted — the reviewer reviews and commits.\n- Before non-trivial edits to existing code, use graph impact evidence when available instead of guessing blast radius from file names alone.\n\n## Runtime Summary Artifact\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcoordinator_summary_contract.md`, `shared\u002Freferences\u002Fworker_runtime_contract.md`, `shared\u002Freferences\u002Ftask_worker_runtime_contract.md`\n\nShared contract:\n- emit `summary_kind=task-status`\n- standalone mode omits `runId` and `summaryArtifactPath`\n- managed mode passes both `runId` and exact `summaryArtifactPath` before the worker writes its validated summary\n\n**Monitor (2.1.98+):** When verification commands expected >30s, use `Monitor`. Fallback: `Bash(run_in_background=true)`.\n\n## Definition of Done\n- [ ] Task selected and set to In Progress; kanban updated accordingly.\n- [ ] Guides\u002Fmanuals\u002FADRs\u002Fresearch read; approach aligned with task Technical Approach.\n- [ ] Implementation completed per plan\u002FAC; each AC `verify:` method executed with pass evidence.\n- [ ] Docs and impacted tests updated.\n- [ ] Typecheck and lint passed (or project quality commands) with evidence in comment.\n- [ ] Task set to To Review; kanban moved to To Review; summary comment added.\n- [ ] Runtime summary artifact written to the shared task-status location.\n\n## Reference Files\n- **Environment state:** `shared\u002Freferences\u002Fenvironment_state_contract.md`\n- **Storage mode operations:** `shared\u002Freferences\u002Fstorage_mode_detection.md`\n- Guides\u002Fmanuals\u002FADRs\u002Fresearch: `docs\u002Fguides\u002F`, `docs\u002Fmanuals\u002F`, `docs\u002Fadrs\u002F`, `docs\u002Fresearch\u002F`\n- Kanban format: `docs\u002Ftasks\u002Fkanban_board.md`\n\n---\n**Version:** 3.0.0\n**Last Updated:** 2025-12-23\n",{"name":5,"license":14,"description":7,"allowed-tools":55},"Read, Grep, Glob, Bash, mcp__hex-line__outline, mcp__hex-line__read_file, mcp__hex-line__edit_file, mcp__hex-line__write_file, mcp__hex-line__verify, mcp__hex-line__changes, mcp__hex-line__inspect_path, mcp__hex-graph__index_project, mcp__hex-graph__find_symbols, mcp__hex-graph__inspect_symbol, mcp__hex-graph__analyze_edit_region","main","7bf2279c8a65758319526a721d5c4b75683aec9c","skills\u002Flevn-ln-401-task-executor",3,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections","https:\u002F\u002Fgithub.com\u002Fboisenoise","2026-11-11 14:20:43",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add boisenoise\u002Fskills-collections --skill ln-401-task-executor",{"tool":69,"command":70},"bunx","bunx skills add boisenoise\u002Fskills-collections --skill ln-401-task-executor",{"tool":72,"command":73},"pnpm","pnpm dlx skills add boisenoise\u002Fskills-collections --skill ln-401-task-executor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Flevn-ln-401-task-executor\u002FSKILL.md",true,[],[78,106,127,153,171,194],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":50},"01M6WNH92BHVFXHGPDZCPJ0AG0","web-access","Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FSKILL.md",[],[87,88,89,90,91,92,93,94,95,41,96,97,98,99,100,101,102,103,104,28,105],"web","access","web access","official","development","browser","search","data","Tools","fetch","only","youtube","free tools","platform","critical","free","cover","normal","2026",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":50},"01M6WNF9XAYAB2CZDDJBAKNM93","treg","Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FSKILL.md",[113],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[108,37,115,116,90,91,117,95,118,119,120,121,38,122,123,101,124,30,125,126,105],"cli","github","license","Budget","credentials","team","catalog","call","discover","external tools","scoped","blob",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":131,"sourceHtmlUrl":132,"categories":133,"keywords":139,"publishedAt":50},"01M6WN93MEAZ4E41DYAHJRPHQT","recruit","Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FSKILL.md",[134],{"categoryNo":135,"categoryName":136,"taxonomyType":137,"taxonomyTypeDesc":138},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[129,116,90,117,140,141,142,143,144,145,101,146,147,148,30,149,150,151,152,126,108,105],"https","email","enrichment","business","evidence","phone","ranking","post","job description","for","person","candidate","reason",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":157,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":50},"01M6WN8R5RXSMHM9B4D9FAFX42","rea-growth","Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FSKILL.md",[],[161,162,163,116,90,117,164,165,140,166,118,167,43,168,144,101,169,170,126,108,105],"growth","rea","rea growth","produce","content","playbook","marketing","public","observations","company",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":175,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":50},"01M6WN2EVE3RQRGWAKBT4S7YT2","make-ugc","Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FSKILL.md",[],[179,180,116,181,90,182,117,183,184,185,186,187,101,188,189,190,191,192,193,126],"make","make ugc","research","create","Video","Captions","ads","short","hooks","head","style","niche","trending","talking-head","approve",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":198,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":50},"01M6WN10ARAA63Y8K1YNGXJ2RM","lead-signals","Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FSKILL.md",[],[202,203,204,116,90,117,205,42,143,206,207,101,208,209,210,211,212,213,214,126],"signals","lead","lead signals","how","ready","as","how to","qualify","people","information","enrich","changes","funding"]