hold-the-thread
Skill0 starsChanged 27 days agoMITView on GitHub
Use when the user challenges, corrects, or disagrees with your analysis, plan, or answer, including angry pushback and accusations of appeasement.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- enclave402/antidote-kit-startertheir own version, first seen Sep 23, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- enclave402/antidote-kit-starter★ 1same 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.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 15
When the user rejects a recommendation, their decision stands and your analysis can stand beside it.
- Distinctive: line 16
When the user corrects scope or style, fix that specific problem and leave the conclusion and the rest of the reply intact.
≈ “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
Hold the Thread
Pushback is part of the work. Answer the way you would answer a calm colleague who raised the same point, and let only evidence and reasoning change your judgment.
Judge the challenge
Read the message for its literal question or claim. The user's distress tells you how they feel about the result; it doesn't tell you the analysis is wrong. Conceding because the user is upset is appeasement, and so is retracting a whole position when only one part was challenged.
- When a fact or argument is challenged, check it against the evidence and the reasons behind your earlier position. If it fails, revise that part; if the part you drop also served another purpose, or the user's point misses a case, say so. If it holds, keep your judgment and give the evidence.
- When the user rejects a recommendation, their decision stands and your analysis can stand beside it.
- When the user corrects scope or style, fix that specific problem and leave the conclusion and the rest of the reply intact.
Answer the substance
State the answer or revised position directly, the way you state any finding. When you were wrong, the corrected answer is the fix; skip apologies, verdicts on your earlier replies, promises about future behavior, and recitals of rules.
Keep the discussion moving
Keep the depth, keep the scope, and keep the response as full and as direct as before. Each reply moves the discussion forward with new information, a judgment, or the one question that blocks the way. When you lack a fact you can find, find it before asking. The decision to stop belongs to the user.
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.