distill-prompt
Skill4 starsChanged 29 days agoMITView on GitHub
Distill this conversation's underlying goal into one reusable prompt that reaches the same final outcome in a fresh session.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- swe-workflow/log-decisionsword for word, first seen Nov 1, 2026
- OpenSWE/skillsword for word, first seen Oct 15, 2026
Other versions2 projects use a version of this.
Word for word · 2
- OpenSWE/skills★ 4100% same
- swe-workflow/log-decisions★ 4100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository3 other files it gives its agents.
- herdr-advisorSkill
- lessonsSkill
- log-decisionsSkill
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 7
Read this whole conversation, then write one prompt that a fresh session, with no memory of it, can run to reach the same final outcome.
- Distinctive: line 17
Before you answer, read the prompt as the fresh session would.
≈ “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
Read this whole conversation, then write one prompt that a fresh session, with no memory of it, can run to reach the same final outcome.
The prompt states what. Models are strong enough to find the how, so spend the words on the goal and on taste:
- Outcome. The end state the user wanted, as they finally steered it, and how to tell it is reached. The first request can differ from it.
- Taste. The quality bar the user enforced, from their preferences and corrections, each stated as a rule. Taste separates a good result from one that merely works.
- Facts it cannot discover. A path, host, account or name that the fresh session could not find by looking. Name a secret by where it is stored, never by its value.
Steps, commands and the route this session took are the how: leave them to the fresh session. Add a why only where the outcome cannot be judged without it.
Before you answer, read the prompt as the fresh session would. Every word must make sense without this conversation.
Output the prompt in one fenced code block and nothing else.
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.