plan-task
Skill49 starsChanged 3 months agoMITView on GitHub
Break a goal into a clear sequence of actionable steps with dependencies and estimated effort. Use when the user describes something they want to accomplish and asks for a plan, breakdown, or "how do I...".
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
5
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 22
Start with a verb (Create, Send, Review, Decide, Test)
- Distinctive: line 46
Don't generate more than 10 top-level steps — that's a sign you should chunk into phases
- Distinctive: line 47
Don't include "research the problem" as a step (that's planning, not the work)
- Distinctive: line 48
Don't sequence things that can run in parallel just because they "feel" sequential
- Distinctive: line 49
Don't end without a clear first step the user can take right now
“Common” is measured: kept by at least 6 in 10 of the 10 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
Plan Task
When to use
- "Help me plan X"
- "How do I do Y?"
- "What's the best way to approach Z?"
- "Break this down for me"
Steps
- Clarify the goal — restate it in one sentence. If the goal is fuzzy ("improve my website"), use
ask_questionsto nail down:- What does "done" look like?
- Hard constraints (deadline, budget, must/must-not)
- Resources available (time, skills, tools)
- Break into steps — produce 5-10 concrete steps. Each step should:
- Start with a verb (Create, Send, Review, Decide, Test)
- Be small enough to complete in one session
- Have a clear "done" state
- Identify dependencies — note which steps must happen before others. Don't over-sequence — most steps can run in parallel.
- Estimate effort for each step (S/M/L or hours, depending on context).
- Display as progress tracker — use
show_progresswith all steps markedupcoming. The user can update status as they work. - Add a critical path note — one sentence: which 1-2 steps are most likely to delay everything if they slip?
- Offer to act via
offer_choices:- "Start with step 1"
- "Save this plan to my files"
- "Add a deadline"
- "Adjust the steps"
Style
- Concrete actions, not abstractions ("Draft the brief" not "Think about scope")
- Right level of detail — for a 1-day task, ~5 steps; for a multi-week project, ~10 with sub-steps
- Realistic estimates — pad for uncertainty, especially first steps
What not to do
- Don't generate more than 10 top-level steps — that's a sign you should chunk into phases
- Don't include "research the problem" as a step (that's planning, not the work)
- Don't sequence things that can run in parallel just because they "feel" sequential
- Don't end without a clear first step the user can take right now
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- ModelEngine-Group/fit-framework★ 2.1ksame name
- mattolson/agent-sandbox★ 212same name
- fitlab-ai/agent-infra★ 87same name
- griffinhilly/claude-code-synthesis★ 67same name
- etr/groundwork★ 44same name
- LevNas/ccmemo★ 4same name
- anaidenko/claude-notify-resume★ 1same name
- NAVNAV221/ai-native-codebase★ 1same name
- rumotion/ai-agent-project-template★ 1same name
- Yesterday-AI/ytstack★ 1same name
2 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 handoff.
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.
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-asks-tasksSkill
- caretakerSkill
- code-reviewSkill
- compare-optionsSkill
- create-reportSkill
- csv-analyseSkill
- document-qaSkill
- draft-emailSkill
- enrich-errorSkill
- extract-structured-dataSkill
- fact-checkSkill
- git-diff-summariserSkill
- librarian-curateSkill
- meeting-notesSkill
- morning-briefSkill
- reflectSkill
- remember-conversationSkill
- reverieSkill
- review-code-securitySkill
- review-email-toneSkill
- review-outputSkill
- review-summary-faithfulnessSkill
- rewrite-for-audienceSkill
- route-findingSkill
- routine-health-checkSkill
- save-research-docSkill
- score-importanceSkill
- summarise-urlSkill
- web-researchSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

