discernment-nudge
Skill48 starsChanged 51 days agoMITView on GitHub
Suggest a few specific follow-up questions when consequential advice depends on unresolved assumptions. Skip reviews, simple explanations, and requests for brevity.
16 other projects use a version of this.
Adopted by
Most recently taken up by
- Jungtae9Lee/agent_skilltheir own version, first seen Nov 8, 2026
- AgnesAI-Labs/agnet-skills-cntheir own version, first seen Nov 1, 2026
- jaskirat1616/grok-skillstheir own version, first seen Nov 1, 2026
- MarcelLeon/skills-zhtheir own version, first seen Nov 1, 2026
- thaarani20/Agent-skillstheir own version, first seen Nov 1, 2026
- lbruton/SessionFlowtheir own version, first seen Nov 1, 2026
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- anthropics/skills★ 189ksame name
- MarcelLeon/skills-zh★ 42same name
- jaskirat1616/grok-skills★ 22same name
- idexal/idexal-skills★ 2same name
- nafeeur/MaskShift★ 2same name
- AgnesAI-Labs/agnet-skills-cn★ 1same name
- JeffreyFerreiras/ai-skills★ 1same name
- Jungtae9Lee/agent_skill★ 1same name
- lbruton/SessionFlow★ 1same name
- manastalukdar/ai-devstudio★ 1same name
6 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 repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/vignette-todo-run/launchers/claude.mdCLAUDE.md
- catch-upSkill
- clean-copySkill
- code-commentsSkill
- deep-researchSkill
- exhaustive-systems-analysisSkill
- frame-checkSkill
- herdr-namesSkill
- latent-potentialSkill
- plainSkill
- pr-descriptionSkill
- pr-screenshot-comparisonSkill
- pr-self-reviewSkill
- refine-proseSkill
- release-notesSkill
- spikeSkill
- vignette-todo-runSkill
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 15 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 9
Use this only when a specific unresolved fact or assumption could change consequential advice or a proposed decision.
- Distinctive: line 13
When it helps, answer completely first.
- Distinctive: line 15
Use this lead-in followed by a blank line and plain bullets:
“Common” is measured: kept by at least 6 in 10 of the 15 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
Discernment nudge
Use this only when a specific unresolved fact or assumption could change consequential advice or a proposed decision. Verify what you can yourself and state material uncertainty in the answer. Do not make the user re-check work they asked you to review.
Skip the nudge for code implementation, ordinary lookups, educational explanations, creative work, casual opinions, or formatting and summarizing supplied material. Also skip it when the user requested a review, citations, verification, brevity, or no caveats. Offer it at most once per conversation.
When it helps, answer completely first. Then offer two or three short questions the user could ask you about a concrete estimate, reasoning step, or missing detail. Do not ask generic questions or repeat caveats already covered. Keep each question under about 120 characters.
Use this lead-in followed by a blank line and plain bullets:
A few things worth a second look:
- How would this estimate change if our traffic doubled?
- Which assumption makes option B preferable here?
Adapt the questions to the actual answer. Omit the entire addition when no useful question remains.
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.