write-dev-tasks
Skill0 starsChanged 15 days agoMITView on GitHub
Break a PRD or technical design into ordered tasks with yes/no acceptance. Use when the user asks for tickets, a task breakdown, detailed dev tasks, or a work plan. Do not write product code. Do not invent a backlog for a one-file change.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- rpraharaj/ai-engineeredited, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- rpraharaj/ai-engineer★ 127% same
Wrote their own version · 0
None found.
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 repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Do not implement. Do not open tracker issues unless the user asked and a tracker CLI this repo already uses works.
- Very specific: line 30
If there is only one small task, stop and run shape-work.
- Very specific: line 38
If none exists and the work is large, stop and offer write-prd or write-design.
- Very specific: line 47
Read AGENTS.md, applicable requirements, and the named PRD/design.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write dev tasks
Turn an agreed what/how into ordered slices. This is not a PRD, not a design, and not shape-work.
Do not implement. Do not open tracker issues unless the user asked and a tracker CLI this repo already uses works.
Is this the right skill?
| Signal | Do this instead |
| Product why still open | write-prd |
| How still open | write-design |
| Exactly one small slice | shape-work |
| Start coding | implement-change |
If there is only one small task, stop and run shape-work.
Required inputs
- PRD and/or design the user pointed at
- Applicable requirements and approved design revision, or an explicitly shaped small-change baseline
AGENTS.md
If none exists and the work is large, stop and offer write-prd or write-design.
Human decisions (do not invent)
- Opening tracker issues
- Parallelism that shares a contract
Procedure
- Read
AGENTS.md, applicable requirements, and the named PRD/design. Check revision-bound prerequisite approvals fromcontext/decision-rights.md. Stop for unapproved design, unresolved blocking review findings, or missing applicable requirements; useshape-workfor an explicitly small change. - Find the home: first existing
docs/tasks/,docs/dev/, a pathAGENTS.mdnames, or a sibling of the design. Name:docs/tasks/<slug>.md. - Open references/dev-tasks-template.md. Copy every heading. Write
n/awhen unused. - Each task: one kind, one next skill, yes/no acceptance, real likely files or “could not find”, and traces to applicable requirement ids and design slice (or shaped-work id for a small change), qualified by artifact path and revision. No drive-by world refactor inside a feature task.
- Order is dependency-real (expand before readers). Parallel only with no shared contract.
Output
- Path:
docs/tasks/<slug>.md - Template:
references/dev-tasks-template.md
Quality bar
- Task 1 is the smallest slice that proves the approach
- Later tasks do not assume code Task 1 has not shipped
- Batch done would fail today
- Count is as small as the risks require
- Applicable Must coverage is complete across the batch, or gaps block handoff; approvals match the source revisions
Done
- Path
- Task count and first title
- Next skill for Task 1:
shape-workorimplement-change
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.