take
Skill1 starsChanged 36 days agoMITView on GitHub
Take the next (or named) ticket from the issue tracker, move it to in progress, grill only its open decisions (max 8 questions), and write Decisions and Files into the ticket. No code. Part of the dev-flow lifecycle (take, implement, address, done).
1 other project uses a version of this.
Adopted by
Most recently taken up by
- tldraw/tldrawtheir own version, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- tldraw/tldraw★ 51ksame name
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 repository14 other files it gives its agents.
- skills/setup-project/templates/AGENTS.mdAGENTS.md
- grill-meSkill
- addressSkill
- conventional-commitsSkill
- design-packageSkill
- doneSkill
- implementSkill
- preview-prSkill
- researchSkill
- setup-projectSkill
- stop-previewSkill
- ticketsSkill
- ui-from-referenceSkill
- visual-notesSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Claim (do this before anything else): Run just task <n> in-progress and show its output line (#<n> -> in-progress).
- Very specific: line 20
Grill: Use the grilling skill on the decisions the ticket leaves open: at most 8 questions, one batch, each with your recommendation.
- Very specific: line 21
Write: Add ## Decisions and append any new paths to ## Files.
- Very specific: line 22
If the work needs more than ~5 files, propose a split in the tickets format and stop.
- Distinctive: line 23
Stop: Do not build.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
/take [#N]
Project facts (commands, tracker, git tool, base branch, models) live in AGENTS.md. Read it first. Read nothing else project-wide.
- Sync. Graphite:
gt sync -f. Plain git:git switch <base> && git pull --ff-only. - Pick. The named issue; otherwise the first open issue in the earliest open milestone with label
status:todowhoseDepends:issues are all closed:gh issue list --label status:todo --milestone "<milestone>" --json number,title --limit 10gh issue view <n> --json title,body,milestone- for each
Depends: #x:gh issue view <x> --json state -q .state
- Claim (do this before anything else). Run
just task <n> in-progressand show its output line (#<n> -> in-progress). If it fails, stop and report the error. Then check out the base:gt checkout <base>orgit switch <base>. - Read. The files under
## Files, nothing more. For gaps, search the code, then open extra files one at a time. - Grill. Use the
grillingskill on the decisions the ticket leaves open: at most 8 questions, one batch, each with your recommendation. Look up facts yourself; ask only for decisions. - Write. Add
## Decisionsand append any new paths to## Files. Write the whole body to a temp file, thengh issue edit <n> --body-file <tmp>. If the work needs more than ~5 files, propose a split in theticketsformat and stop. - Stop. Do not build.
Shortest complete answer. End with one line: Next: /implement on <model for implement in AGENTS.md>.
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.

