tasks
Skill1 starsChanged 3 months agoMIT-0View on GitHub
Expand a design doc's task map into a tasks/ folder — a README index plus one file per subtask
49 other projects use a version of this.
Adopted by
Most recently taken up by
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
- tandregbg/core-claude-skillstheir own version, first seen Nov 4, 2026
- kenbanks-peng/skillstheir own version, first seen Nov 1, 2026
- shakhruz/mila-coretheir own version, first seen Nov 1, 2026
- ananthanandanan/skillstheir own version, first seen Nov 1, 2026
- ansvisor/ansvisortheir own version, first seen Nov 1, 2026
Used with
Projects with it also use send-user-message, tinyagi-admin and 10 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.
Maliot100XSkillsend-user-message
Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp). Use when the agent needs to notify, alert, or send an unsolicited message to a user — especially during heartbeat invocations, scheduled tasks, or when the agent wants to reach out without a prior user message in the current conversation. Triggers: 'send message to user', 'notify user', 'alert user', 'message the user on discord/telegram/whatsapp', or any need to proactively communicate with a paired sender.
Also in 4 projects that use this
jlia0Skilltinyagi-admin
Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code. Use when the agent needs to: list/add/remove/update agents or teams, check queue status, view logs, start/stop/restart TinyAGI, change settings (provider, model, channels), send messages to the queue, manage tasks, retry dead-letter messages, view recent responses, modify TinyAGI source code or configuration, or perform any administrative operation on the TinyAGI platform. Triggers: 'manage tinyagi', 'add an agent', 'remove a team', 'check queue', 'view logs', 'restart tinyagi', 'change provider', 'update settings', 'create a task', 'modify tinyagi code'.
Also in 3 projects that use this
ArvorCoSkillconstitution
Create or update the project constitution - personalized governance and coding principles. Use when starting a project or updating project standards. Triggers on: create constitution, update principles, set project rules.
Also in 4 projects that use this
ArvorCoSkillspecify
Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.
Also in 6 projects that use this
GoogleSkillquality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
Also in 3 projects that use this
anyprotoSkillskills-manager
Context-aware routing to skills and hooks management. Use when troubleshooting skill activation, fine-tuning keywords, or managing the automated documentation system.
Also in 3 projects that use this
- +1 more from ArvorCo
Other versions49 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 49
- jlia0/tinyclaw★ 3.6ksame name
- TinyAGI/tinyagi★ 3.6ksame name
- TinyAGI/tinyclaw★ 3.6ksame name
- me2resh/apexyard★ 542same name
- snarktank/compound-product★ 542same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- ansvisor/ansvisor★ 233same name
- genkovich/sdd★ 187same name
- mp-web3/claude-starter-kit★ 108same name
- ArvorCo/Relentless★ 98same name
39 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 repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-dlcSkill
- commitSkill
- design-docSkill
- pr-draftSkill
- spec-designSkill
- story-newSkill
- story-refineSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 42 edited versions we read keep these.
1
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
- Distinctive: line 33
Don't re-derive architecture here.
“Common” is measured: kept by at least 6 in 10 of the 42 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
/tasks — decompose into subtasks
Step 4 of the AI-DLC pipeline. Expands the Task map from an approved design-doc.md into a tasks/ folder: a README.md index and one T<N>-<slug>.md file per task. Task files specify the API surface (interface + docs) for each unit — not full implementations. Writing the implementation is the building phase's job, which starts after inception is complete.
Input
The story slug, e.g. /tasks weather-tool. Reads .local/user-stories/<slug>/design-doc.md.
Steps
- Read the design doc, especially its Task map table (# / Task / Depends on / File) and the cross-cutting contract. If there is no task map, STOP and recommend
/design-doc <slug>first. - Read the templates in
references/(bundled):tasks-readme-template.mdandtask-template.md. - Generate the index
tasks/README.mdfrom the design doc's task map: a status table (#, Task, Status, Depends on) with every task starting atnot-started, the recommended order, and the status-progression note. - Generate one file per task,
tasks/T<N>-<slug>.md, each with: a metadata table (Status / Depends-on) followed by a Satisfies (story Definition of Done) bullet list (one verbatim-quoted DoD checkbox per bullet), then Objective, Files, an API surface for that unit, Notes/gotchas, an Acceptance checkbox list, and any task-local Decisions.- API surface, not implementation. Specify the interface the building phase will implement: public function signatures, classes, Pydantic/dataclass models, enums, protocols (TS: functions, interfaces, types; Rust:
struct/enum/trait/fnsignatures), key type signatures — each with a docstring describing intent, invariants, and error conditions. Leave bodies as.../raise NotImplementedError/throw new Error("todo")/ Rusttodo!()/unimplemented!()/ prose. The goal is to give the building-phase agent clear guidance on what to build without handing it a how to copy-paste. Do NOT write full implementations here — that is the building phase's job, which runs after inception is complete. - Glue and entrypoints are implementation too. A complete, runnable block — a
main/entrypoint that parses args and branches, module wiring with real control flow, a function that's short enough to "just write" — is still a body. Describe what it does in prose or a bulleted responsibilities list; leave the code to the build. Type/enum/struct/config definitions (e.g. aCargo.toml, a settings JSON, a clapArgsstruct) ARE the contract and belong here. - Doc comments are the contract, not narration. The signature already states types, ownership, and nullability — a doc comment that restates it is noise the builder will copy verbatim into source. Document what the signature can't: invariants, sentinel values, why an enum arm is explicit, error conditions, ordering guarantees. Skip
/// The session's UUID.onsession_id: String; keep/// 0 when no result was found.Leave a field bare when its name and type say everything. If the project has a documentation-style rule (e.g. inCLAUDE.md), follow it here — task files are where that style enters the codebase. - Where an exact SDK API shape is uncertain, include the intended signature and add a "confirm at build/type-check time" note pointing at the relevant docs/example.
- API surface, not implementation. Specify the interface the building phase will implement: public function signatures, classes, Pydantic/dataclass models, enums, protocols (TS: functions, interfaces, types; Rust:
- Keep task files consistent with the design doc — same file paths, same dependency edges, same DoD mapping. Every DoD checkbox in the story should be covered by at least one task's Acceptance; flag any gap.
- Show the proposed file list + the README index and confirm before writing all files.
- On confirmation, write
tasks/README.mdand eachtasks/T*.md. Tell the user the tasks are ready to build, and that status should progressnot-started → in-progress → done(in both the README table and each file's**Status:**) as work proceeds.
Principles
- One task = one coherent unit that, once implemented, ends green (Python:
ruff/black/pytest; TS:tsc/eslint/tests). If a task can't be verified in isolation, it's too big or wrongly cut — revisit the split. - Inception stops at the interface. If you're tempted to write function bodies, stop — that's the building phase.
- Docs earn their place. Every
///a task file ships gets copied into source, so restatement compounds: if a doc comment would be deleted in code review for saying what the type already says, don't write it here either. - Don't re-derive architecture here; if the decomposition reveals a structural problem, surface it and suggest editing the design doc rather than silently diverging.
- Task code must honor the design doc's cross-cutting contract (e.g. ARM64, FastAPI on
0.0.0.0:8080, stateless container).
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.

