{"id":"88dfc76c-7e20-4244-a6de-8e5497a32d2d","shortId":"BFkv8A","kind":"skill","title":"parallel-task","tagline":"Coordinate plan files by launching multiple parallel subagents for unblocked tasks. Triggers on explicit \"/parallel-task\" commands.","description":"# Parallel Task Runner\n\nUse Orchestration Mode. Parse plan files and delegate tasks to parallel subagents.\n\n## Safety Boundaries\n\n- Do not launch subagents for tasks that share write scope until the dependency is resolved.\n- Do not continue past blockers silently; surface the blocked task and stop that branch of work.\n- Do not mark tasks complete until validation from the plan has actually been checked.\n- Do not run this skill unless the user explicitly invoked `/parallel-task` or clearly asked for parallel agent work.\n\n## Process\n\n### Step 1: Parse Request\n\nExtract from user request:\n1. **Plan file**: The markdown plan to read\n2. **Sprint/Phase** (optional): Which section to run\n\nIf sprint not provided, ask user which to run.\n\n### Step 2: Read & Parse Plan\n\n1. Find sprint/phase section (e.g., `## Sprint 1:`)\n2. Extract task subsections (e.g., `### Task 1.1:`)\n3. For each task, extract:\n   - Task ID and name\n   - Full content (description, location, acceptance criteria, validation)\n4. Build task list\n\n### Step 3: Launch Subagents\n\nFor each task, launch subagent with:\n- **description**: \"Implement task [ID]: [name]\"\n- **prompt**: Use template below\n\nIf there are multiple unblocked tasks, launch multiple subagents in parallel.\n\n### Task Prompt Template\n\n```\nYou are implementing a specific task from a development plan.\n\n## Context\n- Plan: [filename] - [sprint/phase]\n- Goals: [relevant overview from plan]\n- Dependencies: [prerequisites for this task]\n- Related tasks: [tasks in same sprint]\n- Constraints: [risks from plan]\n\n## Your Task\n**Task [ID]: [Name]**\n\nLocation: [File paths]\nDescription: [Full description]\n\nAcceptance Criteria:\n[List from plan]\n\nValidation:\n[Tests or verification from plan]\n\n## Instructions\n1. Examine and explore the plan, all relevant files & dependencies. Ensure ambiguities are cleared up.\n2. Implement changes for all acceptance criteria\n3. Keep work **atomic and committable**\n4. For each file: read first, edit carefully, preserve formatting\n5. Run validation if feasible\n6. Return summary of:\n   - Files modified/created\n   - Changes made\n   - How criteria are satisfied\n   - Validation performed or deferred\n\n## Important\n- Be careful with paths\n- Stop and describe blockers if encountered\n- Focus on this specific task\n```\n\n### Step 4: Monitor & Log\n\nAfter subagents complete:\n1. Collect results\n2. **ALWAYS mark completed tasks** and update with:\n   - Concise work log\n   - Files modified/created\n   - Errors or gotchas encountered\n\n### Step 5: Repeat\n\nNow, pause and read the whole plan again to see what new tasks are unblocked.\n\nStart back at step 3. Continue launching agents on unblocked tasks in parallel.\n\nRepeat this loop until the plan is done.\n\nDo not stop until the plan is fully completed or you encounter a blocker.\n\n## Step 6: Validate\n\nAfter completing all tasks, validate the plan's success by checking the final state against the original plan. Perform available tests and ensure success. If there are any issues, address them before marking the plan as complete.\n\nAfter validation, provide a summary of:\n- Files modified/created\n- Changes made\n- How criteria are satisfied\n- Validation performed or deferred\n\n## Error Handling\n\n- Sprint not found: List available sprints/phases\n- Parse failure: Show what was tried, ask for clarification\n\n## Example Usage\n\n```\n/parallel-task plan.md\n/parallel-task ./plans/auth-plan.md sprint 2\n/parallel-task user-profile-plan.md phase 1\n```\n\n## Run Summary Template\n\n```markdown\n# Sprint/Phase Run Summary\n\n## Tasks Assigned: [N]\n\n### Completed\n- Task [ID]: [Name] - [Brief summary]\n\n### Issues\n- Task [ID]: [Name]\n  - Issue: [What went wrong]\n  - Resolution: [How resolved or what's needed]\n\n### Blocked\n- Task [ID]: [Name]\n  - Blocker: [What's preventing completion]\n  - Next Steps: [What needs to happen]\n\n## Overall Status\n[Completion summary]\n\n## Files Modified\n[List of changed files]\n\n## Next Steps\n[Recommendations]\n```","tags":["parallel","task","agent","skills","jdrhyne","agent-skills","agentic-ai","ai-agents","automation","claude-code","clawdbot","codex"],"capabilities":["skill","source-jdrhyne","skill-parallel-task","topic-agent-skills","topic-agentic-ai","topic-ai-agents","topic-automation","topic-claude-code","topic-clawdbot","topic-codex","topic-cursor","topic-developer-tools","topic-gemini-cli","topic-github-copilot","topic-llm-agents"],"categories":["agent-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/jdrhyne/agent-skills/parallel-task","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add jdrhyne/agent-skills","source_repo":"https://github.com/jdrhyne/agent-skills","install_from":"skills.sh"}},"qualityScore":"0.565","qualityRationale":"deterministic score 0.56 from registry signals: · indexed on github topic:agent-skills · 230 github stars · SKILL.md body (3,940 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T00:54:19.716Z","embedding":null,"createdAt":"2026-04-18T22:05:02.970Z","updatedAt":"2026-04-22T00:54:19.716Z","lastSeenAt":"2026-04-22T00:54:19.716Z","tsv":"'/parallel-task':18,92,494,496,500 '/plans/auth-plan.md':497 '1':102,109,138,144,262,344,503 '1.1':151 '2':117,134,145,277,347,499 '3':152,173,284,386 '4':168,290,338 '5':300,365 '6':305,418 'accept':165,250,282 'actual':79 'address':449 'agent':98,389 'alway':348 'ambigu':273 'ask':95,128,489 'assign':512 'atom':287 'avail':439,481 'back':383 'block':60,535 'blocker':56,329,416,539 'boundari':36 'branch':65 'brief':518 'build':169 'care':297,323 'chang':279,311,465,558 'check':81,430 'clarif':491 'clear':94,275 'collect':345 'command':19 'committ':289 'complet':72,343,350,411,421,456,514,543,552 'concis':355 'constraint':235 'content':162 'context':215 'continu':54,387 'coordin':4 'criteria':166,251,283,314,468 'defer':320,474 'deleg':30 'depend':49,224,271 'describ':328 'descript':163,182,247,249 'develop':213 'done':402 'e.g':142,149 'edit':296 'encount':331,363,414 'ensur':272,442 'error':360,475 'examin':263 'exampl':492 'explicit':17,90 'explor':265 'extract':105,146,156 'failur':484 'feasibl':304 'file':6,28,111,245,270,293,309,358,463,554,559 'filenam':217 'final':432 'find':139 'first':295 'focus':332 'format':299 'found':479 'full':161,248 'fulli':410 'goal':219 'gotcha':362 'handl':476 'happen':549 'id':158,185,242,516,522,537 'implement':183,207,278 'import':321 'instruct':261 'invok':91 'issu':448,520,524 'keep':285 'launch':8,39,174,179,197,388 'list':171,252,480,556 'locat':164,244 'log':340,357 'loop':397 'made':312,466 'mark':70,349,452 'markdown':113,507 'mode':25 'modifi':555 'modified/created':310,359,464 'monitor':339 'multipl':9,194,198 'n':513 'name':160,186,243,517,523,538 'need':534,547 'new':378 'next':544,560 'option':119 'orchestr':24 'origin':436 'overal':550 'overview':221 'parallel':2,10,20,33,97,201,394 'parallel-task':1 'pars':26,103,136,483 'past':55 'path':246,325 'paus':368 'perform':318,438,472 'phase':502 'plan':5,27,77,110,114,137,214,216,223,238,254,260,267,373,400,408,426,437,454 'plan.md':495 'prerequisit':225 'preserv':298 'prevent':542 'process':100 'prompt':187,203 'provid':127,459 'read':116,135,294,370 'recommend':562 'relat':229 'relev':220,269 'repeat':366,395 'request':104,108 'resolut':528 'resolv':51,530 'result':346 'return':306 'risk':236 'run':84,123,132,301,504,509 'runner':22 'safeti':35 'satisfi':316,470 'scope':46 'section':121,141 'see':376 'share':44 'show':485 'silent':57 'skill':86 'skill-parallel-task' 'source-jdrhyne' 'specif':209,335 'sprint':125,143,234,477,498 'sprint/phase':118,140,218,508 'sprints/phases':482 'start':382 'state':433 'status':551 'step':101,133,172,337,364,385,417,545,561 'stop':63,326,405 'subag':11,34,40,175,180,199,342 'subsect':148 'success':428,443 'summari':307,461,505,510,519,553 'surfac':58 'task':3,14,21,31,42,61,71,147,150,155,157,170,178,184,196,202,210,228,230,231,240,241,336,351,379,392,423,511,515,521,536 'templat':189,204,506 'test':256,440 'topic-agent-skills' 'topic-agentic-ai' 'topic-ai-agents' 'topic-automation' 'topic-claude-code' 'topic-clawdbot' 'topic-codex' 'topic-cursor' 'topic-developer-tools' 'topic-gemini-cli' 'topic-github-copilot' 'topic-llm-agents' 'tri':488 'trigger':15 'unblock':13,195,381,391 'unless':87 'updat':353 'usag':493 'use':23,188 'user':89,107,129 'user-profile-plan.md':501 'valid':74,167,255,302,317,419,424,458,471 'verif':258 'went':526 'whole':372 'work':67,99,286,356 'write':45 'wrong':527","prices":[{"id":"d2bed494-ea24-4b41-9005-1c71a3728e57","listingId":"88dfc76c-7e20-4244-a6de-8e5497a32d2d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"jdrhyne","category":"agent-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T22:05:02.970Z"}],"sources":[{"listingId":"88dfc76c-7e20-4244-a6de-8e5497a32d2d","source":"github","sourceId":"jdrhyne/agent-skills/parallel-task","sourceUrl":"https://github.com/jdrhyne/agent-skills/tree/main/skills/parallel-task","isPrimary":false,"firstSeenAt":"2026-04-18T22:05:02.970Z","lastSeenAt":"2026-04-22T00:54:19.716Z"}],"details":{"listingId":"88dfc76c-7e20-4244-a6de-8e5497a32d2d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"jdrhyne","slug":"parallel-task","github":{"repo":"jdrhyne/agent-skills","stars":230,"topics":["agent-skills","agentic-ai","ai-agents","automation","claude-code","clawdbot","codex","cursor","developer-tools","gemini-cli","github-copilot","llm-agents","mcp","openclaw","prompt-engineering","prompts"],"license":null,"html_url":"https://github.com/jdrhyne/agent-skills","pushed_at":"2026-03-27T14:29:53Z","description":"A collection of AI agent skills for Clawdbot, Claude Code, Codex","skill_md_sha":"d54345f3c89c153c7c9a15d002e12801ad64ad85","skill_md_path":"skills/parallel-task/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/jdrhyne/agent-skills/tree/main/skills/parallel-task"},"layout":"multi","source":"github","category":"agent-skills","frontmatter":{"name":"parallel-task","description":"Coordinate plan files by launching multiple parallel subagents for unblocked tasks. Triggers on explicit \"/parallel-task\" commands."},"skills_sh_url":"https://skills.sh/jdrhyne/agent-skills/parallel-task"},"updatedAt":"2026-04-22T00:54:19.716Z"}}