discussion
Skill89 starsChanged 13 days agoMITView on GitHub
Open a structured multi-round discussion that converges - research, explore options, decide together - and persist it as a .scratch work item ending in DESIGN.md and tracer-bullet tickets. For topics too big or contested for a one-shot chat answer.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- wowyuarm/dsh-agent-teamword for word, first seen Nov 8, 2026
- samchon/nestiatheir own version, first seen Oct 9, 2026
- samchon/typiatheir own version, first seen Oct 8, 2026
Other versions3 projects use a version of this.
Word for word · 1
- wowyuarm/dsh-agent-team★ 89100% same
Edited · 0
None found.
Wrote their own version · 2
- samchon/typia★ 6ksame name
- samchon/nestia★ 2.2ksame 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- .scratch/AGENTS.mdAGENTS.md
- ax-initSkill
- ax-reviewSkill
- codebase-ablationSkill
- codebase-designSkill
- diagnosing-bugsSkill
- grillingSkill
- researchSkill
- scratch-reviewSkill
- tddSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Follow .scratch/AGENTS.md: active/<work>/ with the five-item README.md (status, last-checked date, current frontier, completion conditions, …
- Very specific: line 21
If the repository has no .scratch work area, offer to run ax-init first.
- Very specific: line 37
When the shape is agreed, break the work into tracer-bullet tickets per .scratch/AGENTS.md (vertical slices, blocking edges, frontier.
- Distinctive: line 41
Update the README's five items as the frontier moves.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Discussion
A conductor for converging work: a topic that needs multiple rounds — research, exploring alternatives, decisions — and deserves persistence as a .scratch/active/<work>/ work item instead of chat that evaporates at compaction.
The flow internalizes to-spec and to-tickets for the local .scratch world: the discussion is the interview; its durable output is the work item's DESIGN.md and, once the shape is agreed, its issues/ tickets — all under the repo's own .scratch/AGENTS.md rules, which own the structures and stay the single source for them.
1. Gate
Discussion-worthy means: multiple rounds needed, real decisions to make, and the outcome will be built or referenced later. A question with a one-pass answer gets answered, not a work item.
2. Open the work item
Follow .scratch/AGENTS.md: active/<work>/ with the five-item README.md (status, last-checked date, current frontier, completion conditions, formal-doc exit) and a materials/ directory. Work in the conversation; persist what matters as it crystallizes, not at the end.
If the repository has no .scratch work area, offer to run ax-init first. Without one, keep the discussion in-conversation and say that nothing is being persisted.
3. Research
Pull in facts with the research skill — primary sources, each claim cited, findings saved into materials/. Facts are the agent's job: never ask the user for something that can be looked up.
4. Discuss in rounds
Run the questioning with the grilling discipline: map the topic as a design tree, work it in frontier rounds, numbered questions each carrying a recommended answer; one round, then wait. Settled answers reshape the tree and unlock the next frontier. The questioning is done when the frontier is empty — nothing left silently assumed.
5. Converge
Synthesize — do not transcript. DESIGN.md holds: the problem in the user's terms, the chosen shape, key decisions with their reasons, the agreed testing seams, and open questions. No file paths or code snippets (they go stale); the exception is decision-dense fragments (state machines, type shapes) inlined with their source noted.
6. Ticket
When the shape is agreed, break the work into tracer-bullet tickets per .scratch/AGENTS.md (vertical slices, blocking edges, frontier; wide refactors as expand–contract). Present the breakdown — title, blocked-by, what it delivers — and settle granularity with the user before writing any ticket file.
7. Keep the entry alive
Update the README's five items as the frontier moves; set last-checked at the start of each session that touches the item. Implementation proceeds per ticket (tdd at the agreed seams).
Before closing a work item with code changes, offer /scratch-review <work-item> to review the implementation against its design and tickets and save the report under reviews/. Resolve confirmed findings first; human acceptance evidence belongs separately under validation/. Closing follows the .scratch/AGENTS.md lifecycle — durable conclusions graduate into maintained docs, the item archives.
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.

