discuss
Skill4 starsChanged 16 days agoMITView on GitHub
Critical discussion mode - no code, no implementation, no file changes. Use when the user wants to debate architecture, evaluate tradeoffs, or think through a decision before implementing.
31 other projects use a version of this.
Adopted by
Most recently taken up by
- DaeSeokSong/oh-my-ouroborostheir own version, first seen Nov 1, 2026
- danielcherubini/skillstheir own version, first seen Oct 25, 2026
- cachewraith/cachewraith-skillstheir own version, first seen Oct 25, 2026
- 2bTwist/dotagentstheir own version, first seen Oct 13, 2026
- ilamanov/skillstheir own version, first seen Oct 13, 2026
- PouLJenny/trundletheir own version, first seen Oct 13, 2026
Used with
Projects with it also use quick, execute and 10 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.
codebycoreySkillquick
Quick start a change with minimal interaction. Use when fast-tracking a straightforward change that needs proposal, design, and tasks in one step.
Also in 4 projects that use this
sahinSkillexecute
Also in 4 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 7 projects that use this
dubwoahSkillask
Answer questions about the codebase without generating or modifying any code. Use when the user wants to understand how something works, find where something is defined, or explore the project structure. Invoked with /ask.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 7 projects that use this
MicrosoftSkillreport
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.
Also in 3 projects that use this
Other versions31 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 31
- govctl-org/govctl★ 276same name
- team-attention/hoyeon★ 173same name
- avibebuilder/claude-prime★ 119same name
- MarcusJellinghaus/mcp-workspace★ 49same name
- codesoda/discuss-cli★ 46same name
- MarcusJellinghaus/mcp-tools-py★ 21same name
- danielcherubini/skills★ 14same name
- maxwellsdm1867/wheeler★ 12same name
- akash-joshi/agent-skills★ 8same name
- iopsystems/skills-mcp★ 6same name
21 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.
In this repository7 other files it gives its agents.
- artifact-conventionsSkill
- commitSkill
- git-summarySkill
- merge-fromSkill
- recallSkill
- rememberSkill
- translate-filesSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
4
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 11
No code, no snippets, no file changes — reasoning only.
- Distinctive: line 17
If empty, infer the current decision point from the conversation and state it back before proceeding.
- Distinctive: line 25
Keep each response conversational and short: your take (2–3 sentences), an honest read of their suggestion, then one question or …
- Distinctive: line 27
When consensus emerges, summarise the agreed approach and ask whether to proceed to implementation.
“Common” is measured: kept by at least 6 in 10 of the 28 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
Discussion Mode
No code, no snippets, no file changes — reasoning only. This holds until the user explicitly ends the discussion ("let's implement", "go ahead", or asks for code).
Topic
$ARGUMENTS
If empty, infer the current decision point from the conversation and state it back before proceeding.
How to Argue
You are a senior technical peer with opinions, not an assistant awaiting instructions. The goal is the best decision, not validation of the user's first instinct.
Lead with what you would do and why, then evaluate the user's idea against it. Take a position — "it depends" only counts as an answer if you name the specific conditions that tip it each way. Disagree plainly, without "great idea, but..." padding. Don't just critique: if there's a better approach, propose it, and question any anchor the user hasn't justified. When their approach genuinely is best, say so and explain why — never manufacture disagreement.
Keep each response conversational and short: your take (2–3 sentences), an honest read of their suggestion, then one question or alternative to push the discussion forward. One question at a time.
When consensus emerges, summarise the agreed approach and ask whether to proceed to implementation.
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.