breakdown
Skill31 starsChanged 32 days agoMITView on GitHub
Decomposes one tangled problem into a smallest next action and a compact plan. Use only for /breakdown, "break this down", "break it down", or "decompose this". For open-ended ideation use fanout; skip when the task is already one clear action.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- mrlemoos/galiciatheir own version, first seen Nov 8, 2026
- artemnovitckii/claude-animation-skillstheir own version, first seen Nov 8, 2026
- islandhopper81/claude-skillstheir own version, first seen Nov 1, 2026
- jantichy/claudetheir own version, first seen Oct 27, 2026
- humzabuilds/claude-skillstheir own version, first seen Oct 20, 2026
- LucasCooperBey/claude-skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use ship, implement and 1 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.
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 4 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- artemnovitckii/claude-animation-skills★ 500same name
- jantichy/claude★ 45same name
- mehrad-dm/mastermind★ 23same name
- gregwebs/skills-sdlc★ 20same name
- flurdy/agent-skills★ 9same name
- int2t05/engineering-skills★ 3same name
- tukka25/code-breakdown★ 3same name
- shiggydoodah/skills★ 2same name
- LucasCooperBey/claude-skills★ 1same name
- madeordinary/serel-memory★ 1same name
4 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.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
3
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 8
Run inline without agents.
- Distinctive: line 10
Read the supplied text or referenced artifact.
- Distinctive: line 18
Use plain language and one critical path.
“Common” is measured: kept by at least 6 in 10 of the 13 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
Breakdown
Run inline without agents. This is a planning request; execute only if the user also authorizes the work.
- Read the supplied text or referenced artifact. For project work, read the project's current state and instructions to EOF before choosing an action. Ask once if the problem is too vague to decompose.
- Respond with these five short blocks:
- Goal: what completion means. Identify any discrepancy with the stated goal as an interpretation, not a settled fact.
- Smallest next action: one concrete step that can be completed in one sitting.
- Blocking decision: the fork that unlocks the action, or "none".
- Full plan: a compact checklist, secondary to the next action.
- First trap: the likeliest failure and its earliest observable signal.
Use plain language and one critical path. Do not create a file unless requested or required by the project's state-recording conventions.
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.