planning-and-task-breakdown
Skill0 starsChanged 29 days agoMITView on GitHub
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.
81 other projects use a version of this, 59 of them edited.
Adopted by
Most recently taken up by
- Cody-Sims/agent-skillstheir own version, first seen Nov 16, 2026
- zademy/lu-queryedited, first seen Nov 16, 2026
- sirius-cc-wu/sirius-skillsedited, first seen Nov 16, 2026
- tkbk-online/skillsedited, first seen Nov 15, 2026
- addyosmani/agent-skillsedited, first seen Nov 14, 2026
- ishandutta2007/Awesome-Agent-Skillsedited, first seen Nov 8, 2026
Used with
Projects with it also use constraint-driven-development, deprecation-and-migration and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MrCipherSmithSkillconstraint-driven-development
Use when a project needs a persistent, measurable quality bar — starting a project without documented standards, 'set up constraints', or when coverage/perf/a11y thresholds get re-debated per-PR. Produces CONSTRAINTS.md with enforceable numbers, ratchets, and a guard against silent weakening. NOT for throwaway prototypes or a one-off CI setup.
Also in 14 projects that use this
HK-hubSkilldeprecation-and-migration
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.
Also in 34 projects that use this
HK-hubSkillobservability-and-instrumentation
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.
Also in 26 projects that use this
seikaikyoSkilldoubt-driven-development
對非平凡決策啟動新鮮 context 對抗審查(找碴不背書),在修正還便宜的時候抓出錯誤方向。適用:高風險改動(production、資安敏感邏輯、不可逆操作)、不熟的程式碼、要宣稱「這樣是安全的 / 可行的」之前。機械性操作與一行修改不適用。
Also in 30 projects that use this
seikaikyoSkillinterview-me
需求不明時的意圖萃取訪談:一次一題、每題附上自己的猜測、聽出「真正想要 vs 覺得應該要」,直到能預測使用者反應(約 95% 信心)才動工。適用:需求缺少對象 / 動機 / 成功標準 / 約束,或使用者點名「訪談我」「先確認一下」「我們確定嗎」。明確自足的指示、純資訊查詢、機械性操作不適用。
Also in 31 projects that use this
GSA-TTSSkillarchitecture-decision-records
Load when a user wants architecture decision records (ADRs) drafted from requirements or a design discussion, asks which decisions need an ADR, or wants an ADR draft reviewed for one-sided trade-offs, weak alternatives or missing requirement links. Not for setting up a project's whole documentation system (project-documentation-system).
Also in 3 projects that use this
- +1 more from HK-hub
Other versions81 projects use a version of this.
Word for word · 0
None found.
Edited · 59
- addyosmani/agent-skills★ 118k11% same
- ollaya-dev/ollaya★ 1.4k11% same
- shashankswe2020-ux/whoop-mcp★ 18118% same
- larchanka/skills★ 5014% same
- jmxt3/gitscape.ai★ 3322% same
- sampleXbro/agentsmesh★ 2718% same
- jaskirat1616/grok-skills★ 2211% same
- ishandutta2007/Awesome-Agent-Skills★ 2118% same
- HK-hub/AgentSkills★ 616% same
- lza6/claw-code-tingfeng★ 518% same
49 more not listed
Wrote their own version · 22
- tranhieutt/software_development_department★ 71same name
- vinvcn/addyosmani-agent-skills-zh★ 46same name
- LazyIsEfficient/agentic-os★ 17same name
- moberghr/mtk-agent-toolkit★ 8same name
- anotherben/claude-harness★ 7same name
- momentmaker/kaijutsu★ 3same name
- allanbian1017/skills★ 2same name
- bnalwalid/walidforge-skills★ 2same name
- codexskills/agent-forge★ 2same name
- GuillemRoca/agent-skills-android★ 2same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- .codex/AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- animate-expoSkill
- animateSkill
- break-uiSkill
- claritySkill
- code-reviewSkill
- code-simplificationSkill
- diagnoseSkill
- grill-with-docsSkill
- idea-refineSkill
- improve-codebase-architectureSkill
- incremental-implementationSkill
- interactive-test-planSkill
- manual-test-planSkill
- review-animationsSkill
- security-and-hardeningSkill
- spec-driven-developmentSkill
- tddSkill
- write-a-skillSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
6 rules. 4 are common, 2 are distinctive, and 0 are very specific to this project.
4
Common
Most of the 74 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 14
Before writing any code, operate in read-only mode:
- Common: line 15
Read the spec and relevant codebase sections
- Distinctive: line 58
After every 2-3 tasks, add a verification checkpoint:
- Distinctive: line 87
When a Repo Allocation is present, apply these rules to the task list:
- Common: line 114
All tasks are L/XL-sized
- Common: line 115
No checkpoints between tasks
“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Planning and Task Breakdown
Decompose work into small, verifiable tasks with explicit acceptance criteria. Every task should be small enough to implement, test, and verify in a single focused session.
The Planning Process
Step 1: Enter Plan Mode
Before writing any code, operate in read-only mode:
- Read the spec and relevant codebase sections
- Identify existing patterns and conventions
- Map dependencies between components
- Note risks and unknowns
Do NOT write code during planning. The output is a plan document.
Step 2: Map Dependencies
Implementation order follows the dependency graph bottom-up. Build foundations first.
Step 3: Slice Vertically
Build one complete feature path at a time, not all database then all API then all UI.
Each vertical slice delivers working, testable functionality:
Task 1: User can create an account (schema + API + UI)
Task 2: User can log in (auth + API + UI)
Task 3: User can create a task (schema + API + UI)Step 4: Write Tasks
Each task needs:
## Task [N]: [Short descriptive title]
**Acceptance criteria:**
- [ ] [Specific, testable condition]
- [ ] [Specific, testable condition]
**Verification:**
- [ ] Tests pass
- [ ] Build succeeds
**Dependencies:** [Task numbers or "None"]
**Estimated scope:** [S: 1-2 files | M: 3-5 files | L: 5+ files — break down further]Step 5: Add Checkpoints
After every 2-3 tasks, add a verification checkpoint:
## Checkpoint: After Tasks 1-3
- [ ] All tests pass
- [ ] Application builds
- [ ] Core flow works end-to-endTask Sizing
| Size | Files | Agent handles well? |
| S | 1-2 | Yes |
| M | 3-5 | Yes |
| L | 5-8 | Break it down further |
| XL | 8+ | Must break down |
Break a task down when: >3 acceptance criteria, touches 2+ independent subsystems, or "and" appears in the title.
Parallelization
- Safe: Independent feature slices, tests for implemented features, docs
- Sequential: Migrations, shared state, dependency chains
- Needs coordination: Features sharing an API contract (define contract first)
Cross-Repo Task Breakdown (optional)
Skip this section entirely when the spec has no Repo Allocation. Output is unchanged — single-repo task lists need none of this. This is the most important rule.
When a Repo Allocation is present, apply these rules to the task list:
- Tag every task with
[repo: <name>]identifying which repository it lands in, so placement is unambiguous without reading the acceptance criteria. - Order contract-first. A shared interface or contract must land before the code that consumes it. The consumer cannot be verified against an interface that does not yet exist, so the producing repo's tasks precede its consumers'.
- State merge-order dependencies explicitly. Record which repo's change must merge before another's. This cannot be inferred later from task metadata and is the most expensive cross-repo dependency to reconstruct mid-flight.
- Group by repo. Within the constraint of contract-first ordering, cluster each repo's tasks together so they can be executed as a unit.
Example:
## Task 1 [repo: api]: Expose /events endpoint
**Dependencies:** None
## Task 2 [repo: worker]: Consume /events endpoint
**Dependencies:** Task 1
**Merge-order:** api must merge before worker
## Task 3 [repo: web]: Display events list
**Dependencies:** Task 1
**Merge-order:** api must merge before webRed Flags
- Starting implementation without a written task list
- Tasks without acceptance criteria
- No verification steps
- All tasks are L/XL-sized
- No checkpoints between tasks
- Dependency order not considered
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

