{"id":"ccb474b2-7e29-43b7-bed1-c2a337f27673","shortId":"G2gVmT","kind":"skill","title":"planning-and-task-breakdown","tagline":"Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.","description":"# Planning and Task Breakdown\n\n## Overview\n\nDecompose work into small, verifiable tasks with explicit acceptance criteria. Good task breakdown is the difference between an agent that completes work reliably and one that produces a tangled mess. Every task should be small enough to implement, test, and verify in a single focused session.\n\n## When to Use\n\n- You have a spec and need to break it into implementable units\n- A task feels too large or vague to start\n- Work needs to be parallelized across multiple agents or sessions\n- You need to communicate scope to a human\n- The implementation order isn't obvious\n\n**When NOT to use:** Single-file changes with obvious scope, or when the spec already contains well-defined tasks.\n\n## The Planning Process\n\n### Step 1: Enter Plan Mode\n\nBefore writing any code, operate in read-only mode:\n\n- Read the spec and relevant codebase sections\n- Identify existing patterns and conventions\n- Map dependencies between components\n- Note risks and unknowns\n\n**Do NOT write code during planning.** The output is a plan document, not implementation.\n\n### Step 2: Identify the Dependency Graph\n\nMap what depends on what:\n\n```\nDatabase schema\n    │\n    ├── API models/types\n    │       │\n    │       ├── API endpoints\n    │       │       │\n    │       │       └── Frontend API client\n    │       │               │\n    │       │               └── UI components\n    │       │\n    │       └── Validation logic\n    │\n    └── Seed data / migrations\n```\n\nImplementation order follows the dependency graph bottom-up: build foundations first.\n\n### Step 3: Slice Vertically\n\nInstead of building all the database, then all the API, then all the UI — build one complete feature path at a time:\n\n**Bad (horizontal slicing):**\n```\nTask 1: Build entire database schema\nTask 2: Build all API endpoints\nTask 3: Build all UI components\nTask 4: Connect everything\n```\n\n**Good (vertical slicing):**\n```\nTask 1: User can create an account (schema + API + UI for registration)\nTask 2: User can log in (auth schema + API + UI for login)\nTask 3: User can create a task (task schema + API + UI for creation)\nTask 4: User can view task list (query + API + UI for list view)\n```\n\nEach vertical slice delivers working, testable functionality.\n\n### Step 4: Write Tasks\n\nEach task follows this structure:\n\n```markdown\n## Task [N]: [Short descriptive title]\n\n**Description:** One paragraph explaining what this task accomplishes.\n\n**Acceptance criteria:**\n- [ ] [Specific, testable condition]\n- [ ] [Specific, testable condition]\n\n**Verification:**\n- [ ] Tests pass: `npm test -- --grep \"feature-name\"`\n- [ ] Build succeeds: `npm run build`\n- [ ] Manual check: [description of what to verify]\n\n**Dependencies:** [Task numbers this depends on, or \"None\"]\n\n**Files likely touched:**\n- `src/path/to/file.ts`\n- `tests/path/to/test.ts`\n\n**Estimated scope:** [Small: 1-2 files | Medium: 3-5 files | Large: 5+ files]\n```\n\n### Step 5: Order and Checkpoint\n\nArrange tasks so that:\n\n1. Dependencies are satisfied (build foundation first)\n2. Each task leaves the system in a working state\n3. Verification checkpoints occur after every 2-3 tasks\n4. High-risk tasks are early (fail fast)\n\nAdd explicit checkpoints:\n\n```markdown\n## Checkpoint: After Tasks 1-3\n- [ ] All tests pass\n- [ ] Application builds without errors\n- [ ] Core user flow works end-to-end\n- [ ] Review with human before proceeding\n```\n\n## Task Sizing Guidelines\n\n| Size | Files | Scope | Example |\n|------|-------|-------|---------|\n| **XS** | 1 | Single function or config change | Add a validation rule |\n| **S** | 1-2 | One component or endpoint | Add a new API endpoint |\n| **M** | 3-5 | One feature slice | User registration flow |\n| **L** | 5-8 | Multi-component feature | Search with filtering and pagination |\n| **XL** | 8+ | **Too large — break it down further** | — |\n\nIf a task is L or larger, it should be broken into smaller tasks. An agent performs best on S and M tasks.\n\n**When to break a task down further:**\n- It would take more than one focused session (roughly 2+ hours of agent work)\n- You cannot describe the acceptance criteria in 3 or fewer bullet points\n- It touches two or more independent subsystems (e.g., auth and billing)\n- You find yourself writing \"and\" in the task title (a sign it is two tasks)\n\n## Plan Document Template\n\n```markdown\n# Implementation Plan: [Feature/Project Name]\n\n## Overview\n[One paragraph summary of what we're building]\n\n## Architecture Decisions\n- [Key decision 1 and rationale]\n- [Key decision 2 and rationale]\n\n## Task List\n\n### Phase 1: Foundation\n- [ ] Task 1: ...\n- [ ] Task 2: ...\n\n### Checkpoint: Foundation\n- [ ] Tests pass, builds clean\n\n### Phase 2: Core Features\n- [ ] Task 3: ...\n- [ ] Task 4: ...\n\n### Checkpoint: Core Features\n- [ ] End-to-end flow works\n\n### Phase 3: Polish\n- [ ] Task 5: ...\n- [ ] Task 6: ...\n\n### Checkpoint: Complete\n- [ ] All acceptance criteria met\n- [ ] Ready for review\n\n## Risks and Mitigations\n| Risk | Impact | Mitigation |\n|------|--------|------------|\n| [Risk] | [High/Med/Low] | [Strategy] |\n\n## Open Questions\n- [Question needing human input]\n```\n\n## Parallelization Opportunities\n\nWhen multiple agents or sessions are available:\n\n- **Safe to parallelize:** Independent feature slices, tests for already-implemented features, documentation\n- **Must be sequential:** Database migrations, shared state changes, dependency chains\n- **Needs coordination:** Features that share an API contract (define the contract first, then parallelize)\n\n## Common Rationalizations\n\n| Rationalization | Reality |\n|---|---|\n| \"I'll figure it out as I go\" | That's how you end up with a tangled mess and rework. 10 minutes of planning saves hours. |\n| \"The tasks are obvious\" | Write them down anyway. Explicit tasks surface hidden dependencies and forgotten edge cases. |\n| \"Planning is overhead\" | Planning is the task. Implementation without a plan is just typing. |\n| \"I can hold it all in my head\" | Context windows are finite. Written plans survive session boundaries and compaction. |\n\n## Red Flags\n\n- Starting implementation without a written task list\n- Tasks that say \"implement the feature\" without acceptance criteria\n- No verification steps in the plan\n- All tasks are XL-sized\n- No checkpoints between tasks\n- Dependency order isn't considered\n\n## Verification\n\nBefore starting implementation, confirm:\n\n- [ ] Every task has acceptance criteria\n- [ ] Every task has a verification step\n- [ ] Task dependencies are identified and ordered correctly\n- [ ] No task touches more than ~5 files\n- [ ] Checkpoints exist between major phases\n- [ ] The human has reviewed and approved the plan","tags":["planning","and","task","breakdown","agent","skills","addyosmani","agent-skills","antigravity","antigravity-ide","claude-code","cursor"],"capabilities":["skill","source-addyosmani","skill-planning-and-task-breakdown","topic-agent-skills","topic-antigravity","topic-antigravity-ide","topic-claude-code","topic-cursor","topic-skills"],"categories":["agent-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/addyosmani/agent-skills/planning-and-task-breakdown","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add addyosmani/agent-skills","source_repo":"https://github.com/addyosmani/agent-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 43270 github stars · SKILL.md body (6,638 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":"2026-05-18T18:50:22.042Z","embedding":null,"createdAt":"2026-04-18T20:31:19.807Z","updatedAt":"2026-05-18T18:50:22.042Z","lastSeenAt":"2026-05-18T18:50:22.042Z","tsv":"'-2':440,542 '-3':482,501 '-5':444,554 '-8':563 '1':173,290,315,439,458,500,530,541,684,695,698 '10':825 '2':222,296,327,465,481,620,689,700,708 '3':261,302,339,443,475,553,632,712,725 '4':308,352,372,484,714 '5':447,450,562,728,948 '6':730 '8':574 'accept':62,394,629,734,897,928 'accomplish':393 'account':320 'across':129 'add':493,536,547 'agent':72,131,596,623,759 'alreadi':163,773 'already-impl':772 'anyway':838 'api':234,236,239,273,299,322,334,347,359,550,793 'applic':505 'approv':960 'architectur':680 'arrang':454 'auth':332,645 'avail':763 'bad':286 'best':598 'bill':647 'bottom':255 'bottom-up':254 'boundari':878 'break':6,23,110,577,606 'breakdown':5,52,66 'broken':591 'build':257,266,278,291,297,303,411,415,462,506,679,705 'bullet':635 'cannot':626 'case':847 'chain':786 'chang':155,535,784 'check':417 'checkpoint':453,477,495,497,701,715,731,912,950 'clean':706 'clear':18 'client':240 'code':180,210 'codebas':192 'common':801 'communic':137 'compact':880 'complet':74,280,732 'compon':202,242,306,544,566 'condit':398,401 'config':534 'confirm':924 'connect':309 'consid':919 'contain':164 'context':870 'contract':794,797 'convent':198 'coordin':788 'core':509,709,716 'correct':942 'creat':318,342 'creation':350 'criteria':63,395,630,735,898,929 'data':246 'databas':232,269,293,780 'decis':681,683,688 'decompos':54 'defin':167,795 'deliv':367 'depend':200,225,229,252,423,427,459,785,843,915,937 'describ':627 'descript':384,386,418 'differ':69 'document':218,664,776 'e.g':644 'earli':490 'edg':846 'end':514,516,719,721,817 'end-to-end':513,718 'endpoint':237,300,546,551 'enough':89 'enter':174 'entir':292 'error':508 'estim':41,436 'everi':84,480,925,930 'everyth':310 'exampl':528 'exist':195,951 'explain':389 'explicit':61,494,839 'fail':491 'fast':492 'featur':281,409,556,567,710,717,768,775,789,895 'feature-nam':408 'feature/project':669 'feel':32,117 'fewer':634 'figur':807 'file':154,431,441,445,448,526,949 'filter':570 'find':649 'finit':873 'first':259,464,798 'flag':882 'flow':511,560,722 'focus':98,617 'follow':250,377 'forgotten':845 'foundat':258,463,696,702 'frontend':238 'function':370,532 'go':812 'good':64,311 'graph':226,253 'grep':407 'guidelin':524 'head':869 'hidden':842 'high':486 'high-risk':485 'high/med/low':747 'hold':864 'horizont':287 'hour':621,830 'human':141,519,753,956 'identifi':194,223,939 'impact':744 'implement':26,91,113,143,220,248,667,774,855,884,893,923 'independ':642,767 'input':754 'instead':264 'isn':145,917 'key':682,687 'l':561,585 'larg':34,119,446,576 'larger':587 'leav':468 'like':432 'list':357,362,693,889 'll':806 'log':330 'logic':244 'login':337 'm':552,602 'major':953 'manual':416 'map':199,227 'markdown':380,496,666 'medium':442 'mess':83,822 'met':736 'migrat':247,781 'minut':826 'mitig':742,745 'mode':176,186 'models/types':235 'multi':565 'multi-compon':564 'multipl':130,758 'must':777 'n':382 'name':410,670 'need':21,39,108,125,135,752,787 'new':549 'none':430 'note':203 'npm':405,413 'number':425 'obvious':147,157,834 'occur':478 'one':78,279,387,543,555,616,672 'open':749 'oper':181 'opportun':756 'order':9,144,249,451,916,941 'output':214 'overhead':850 'overview':53,671 'pagin':572 'paragraph':388,673 'parallel':45,128,755,766,800 'pass':404,504,704 'path':282 'pattern':196 'perform':597 'phase':694,707,724,954 'plan':2,49,170,175,212,217,663,668,828,848,851,858,875,904,962 'planning-and-task-breakdown':1 'point':636 'polish':726 'possibl':48 'proceed':521 'process':171 'produc':80 'queri':358 'question':750,751 'ration':802,803 'rational':686,691 're':678 'read':184,187 'read-on':183 'readi':737 'realiti':804 'red':881 'registr':325,559 'relev':191 'reliabl':76 'requir':19 'review':517,739,958 'rework':824 'risk':204,487,740,743,746 'rough':619 'rule':539 'run':414 'safe':764 'satisfi':461 'save':829 'say':892 'schema':233,294,321,333,346 'scope':42,138,158,437,527 'search':568 'section':193 'seed':245 'sequenti':779 'session':99,133,618,761,877 'share':782,791 'short':383 'sign':658 'singl':97,153,531 'single-fil':152 'size':523,525,910 'skill' 'skill-planning-and-task-breakdown' 'slice':262,288,313,366,557,769 'small':57,88,438 'smaller':593 'source-addyosmani' 'spec':16,106,162,189 'specif':396,399 'src/path/to/file.ts':434 'start':36,123,883,922 'state':474,783 'step':172,221,260,371,449,901,935 'strategi':748 'structur':379 'subsystem':643 'succeed':412 'summari':674 'surfac':841 'surviv':876 'system':470 'take':613 'tangl':82,821 'task':4,10,27,31,51,59,65,85,116,168,289,295,301,307,314,326,338,344,345,351,356,374,376,381,392,424,455,467,483,488,499,522,583,594,603,608,655,662,692,697,699,711,713,727,729,832,840,854,888,890,906,914,926,931,936,944 'templat':665 'test':92,403,406,503,703,770 'testabl':369,397,400 'tests/path/to/test.ts':435 'time':285 'titl':385,656 'topic-agent-skills' 'topic-antigravity' 'topic-antigravity-ide' 'topic-claude-code' 'topic-cursor' 'topic-skills' 'touch':433,638,945 'two':639,661 'type':861 'ui':241,277,305,323,335,348,360 'unit':114 'unknown':206 'use':11,28,102,151 'user':316,328,340,353,510,558 'vagu':121 'valid':243,538 'verif':402,476,900,920,934 'verifi':58,94,422 'vertic':263,312,365 'view':355,363 'well':166 'well-defin':165 'window':871 'without':507,856,885,896 'work':7,24,46,55,75,124,368,473,512,624,723 'would':612 'write':178,209,373,651,835 'written':874,887 'xl':573,909 'xl-size':908 'xs':529","prices":[{"id":"42845afa-43d9-4ee1-9ee1-efa9baccbdca","listingId":"ccb474b2-7e29-43b7-bed1-c2a337f27673","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"addyosmani","category":"agent-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T20:31:19.807Z"}],"sources":[{"listingId":"ccb474b2-7e29-43b7-bed1-c2a337f27673","source":"github","sourceId":"addyosmani/agent-skills/planning-and-task-breakdown","sourceUrl":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown","isPrimary":false,"firstSeenAt":"2026-04-18T21:53:03.200Z","lastSeenAt":"2026-05-18T18:50:22.042Z"},{"listingId":"ccb474b2-7e29-43b7-bed1-c2a337f27673","source":"skills_sh","sourceId":"addyosmani/agent-skills/planning-and-task-breakdown","sourceUrl":"https://skills.sh/addyosmani/agent-skills/planning-and-task-breakdown","isPrimary":true,"firstSeenAt":"2026-04-18T20:31:19.807Z","lastSeenAt":"2026-05-07T22:40:25.629Z"}],"details":{"listingId":"ccb474b2-7e29-43b7-bed1-c2a337f27673","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"addyosmani","slug":"planning-and-task-breakdown","github":{"repo":"addyosmani/agent-skills","stars":43270,"topics":["agent-skills","antigravity","antigravity-ide","claude-code","cursor","skills"],"license":"mit","html_url":"https://github.com/addyosmani/agent-skills","pushed_at":"2026-05-16T22:00:25Z","description":"Production-grade engineering skills for AI coding agents.","skill_md_sha":"2dd66850b52d775265699fdf1810273169d37a67","skill_md_path":"skills/planning-and-task-breakdown/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown"},"layout":"multi","source":"github","category":"agent-skills","frontmatter":{"name":"planning-and-task-breakdown","description":"Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible."},"skills_sh_url":"https://skills.sh/addyosmani/agent-skills/planning-and-task-breakdown"},"updatedAt":"2026-05-18T18:50:22.042Z"}}