tasks
Skill4 starsChanged 9 months agoMITView on GitHub
Generate implementation tasks from design and delta specs. Use when creating a task list, breaking down work, or preparing to implement.
We split this skill into the rules it gives an agent
14 rules. 0 are common, 9 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 40 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Create actionable implementation tasks based on the design and delta specs.
- Very specific: line 10
Arguments: If $ARGUMENTS is provided, use it as the name parameter.
- Distinctive: line 22
When processing multiple changes:
- Very specific: line 24
Identify planned changes: - Only include changes with design.md AND specs/ directory
- Distinctive: line 27
Detect cycles: - If circular dependencies found:
- Distinctive: line 34
Process sequentially: - Create tasks for each change in order
- Distinctive: line 53
Read proposal, design, and delta specs
- Distinctive: line 59
If unsatisfied dependencies exist, warn user and ask to proceed or defer
- Distinctive: line 66
Check for test infrastructure (test directories, test configs, existing test patterns)
- Very specific: line 70
Create specs/.delta/<name>/tasks.md with specific, actionable tasks:
- Very specific: line 75
All tasks start with Status: pending and Owner: (unassigned)
- Distinctive: line 76
If the project has tests, include tasks for testing new or modified behavior
- Distinctive: line 78
Use the Write tool to create the task file.
- Very specific: line 86
When processing multiple changes, create a separate tasks.md for each change in its own directory.
“Common” is measured: kept by at least 6 in 10 of the 40 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
/ds:tasks [name] - Create implementation tasks
Create actionable implementation tasks based on the design and delta specs.
Arguments: If $ARGUMENTS is provided, use it as the name parameter. Otherwise, generate tasks for all planned changes.
Step 0: Version Check
See version-check.md for the standard version compatibility check procedure.
Step 1: Determine which change(s)
See determine-change.md for the standard change resolution procedure. For tasks, uses multi-change mode: if no name provided and multiple planned changes exist, process all in dependency order. Prerequisite: suggest /ds:plan.
Multi-Change Mode
When processing multiple changes:
- Identify planned changes - Only include changes with
design.mdANDspecs/directory - Build dependency graph - Parse Dependencies section from each proposal
- Topological sort - Independent changes first, then dependents in order
- Detect cycles - If circular dependencies found:
Do not proceed until cycle is resolved (hard block - task ordering is impossible with cycles)⚠️ Cycle detected: auth → permissions → admin → auth Cannot determine task order. Run /ds:new or /ds:batch to resolve the cycle first. - Process sequentially - Create tasks for each change in order
Output Format for Multi-Change
=== Tasks for: change-a (1 of 3) ===
[tasks 1-N]
=== Tasks for: change-b (2 of 3) ===
[tasks N+1-M]
=== Tasks for: change-c (3 of 3) ===
[tasks M+1-...]Tasks are numbered sequentially across all changes.
Step 2: Build context
- Read proposal, design, and delta specs
- Understand the full scope and approach
Step 3: Check dependencies
- Parse Dependencies from proposal
- If unsatisfied dependencies exist, warn user and ask to proceed or defer
Step 4: Explore the codebase
- Identify exact files and functions to modify
- Find where new code should be added
- Understand dependencies and integration points
- Check for test infrastructure (test directories, test configs, existing test patterns)
Step 5: Create tasks.md file
Create specs/.delta/<name>/tasks.md with specific, actionable tasks:
- Reference actual file paths from exploration
- Reference requirements being implemented
- Order tasks by dependency (what needs to happen first)
- All tasks start with
Status: pendingandOwner: (unassigned) - If the project has tests, include tasks for testing new or modified behavior
Use the Write tool to create the task file.
Task File Format
See task-format.md for the task file format, fields, and update instructions.
Multi-Change Mode
When processing multiple changes, create a separate tasks.md for each change in its own directory.
Other versions46 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 46
- jlia0/tinyclaw★ 3.6ksame name
- TinyAGI/tinyagi★ 3.6ksame name
- TinyAGI/tinyclaw★ 3.6ksame name
- snarktank/compound-product★ 542same name
- me2resh/apexyard★ 532same name
- ansvisor/ansvisor★ 220same name
- genkovich/sdd★ 187same name
- mp-web3/claude-starter-kit★ 108same name
- ArvorCo/Relentless★ 98same name
- ariffazil/arifOS★ 54same name
36 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.
Used alongsideProjects with it also use send-user-message, tinyagi-admin and 9 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
launchdarklySkillprojects
Guide for setting up LaunchDarkly projects in your codebase. Helps you assess your stack, choose the right approach, and integrate project management that makes sense for your architecture.
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
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.

