writing
Skill11 starsChanged 4 months agoCC0-1.0View on GitHub
Rewrite slop, or a reply that did not land, into text a person would write.
51 other projects use a version of this.
Adopted by
Most recently taken up by
- LarsLrn/orcaitheir own version, first seen Nov 8, 2026
- ryanportfolio/winuse-mcptheir own version, first seen Nov 8, 2026
- NilsHellwig/acl-paper-skillstheir own version, first seen Nov 8, 2026
- fracazo/design-systemtheir own version, first seen Nov 8, 2026
- zakirkun/slayerclawtheir own version, first seen Nov 8, 2026
- notque/vexjoy-agenttheir own version, first seen Nov 7, 2026
Used with
Projects with it also use addskill, apply-firmware 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.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
ryanportfolioSkillapply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions51 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 51
- wu-yc/LabClaw★ 1.1ksame name
- agentic-community/mcp-gateway-registry★ 1ksame name
- solana-foundation/explorer★ 856same name
- notque/claude-code-toolkit★ 448same name
- notque/vexjoy-agent★ 448same name
- zeuikli/claude-code-workspace★ 155same name
- joshuadavidthomas/agent-skills★ 49same name
- iliaal/ai-skills★ 45same name
- aws-samples/sample-agentic-coding-harness-benchmarks★ 20same name
- alxyrgin/secondbrain_ai★ 17same name
41 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 repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- auditSkill
- designSkill
- distillSkill
- git-workflowSkill
- intent-briefSkill
- judgeSkill
- query-refinerSkill
- sotaSkill
- timesheetSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 45 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Read all of references/cs-pairs.md, since its moves transfer across media.
- Distinctive: line 29
Write with ASD-STE100 clarity in any language: one name per thing, an explicit actor, unfamiliar terms explained.
- Distinctive: line 31
Keep strong original sentences.
“Common” is measured: kept by at least 6 in 10 of the 45 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
Writing
Rewrite the given text or passage as a person would write it. With no target, rewrite the last substantive agent response. Ask only when the target or intended meaning cannot be determined.
Slop is text that reads as generated: padded, generic, inflated, shaped by habits no person would choose. Each habit is a tell. references/tells.md catalogs tells for the reviewer. The writer works from the positive targets below, not the catalog.
1. Find the reader
Name the reader, what they already know, and what they must do or decide after reading. Find where the original loses them: a buried point, missing context, an unexplained term, slop. For project text, use the domain terms in the repo glossary (GLOSSARY.md, or CONTEXT.md in older repos).
Done when you can state the reader's need and the original's failure in one sentence each.
2. Study the pairs (Czech)
Read all of references/cs-pairs.md, since its moves transfer across media. Choose the pairs closest to your text's medium and register, and compare their sides on four axes: order, verbs, density, register.
Done when you can name, for each chosen pair, one move of the human side that your draft will copy.
3. Rewrite
- Lead with what the reader needs. Put the context a conclusion depends on before the conclusion.
- Write with ASD-STE100 clarity in any language: one name per thing, an explicit actor, unfamiliar terms explained.
- Carry over the author's stance. Every fact, number, and example comes from the original or the conversation. Uncertainty stays visible.
- Keep strong original sentences. Length follows content: add the context the reader lacks, and stop when the content ends.
- Match the original's language, register, and medium. Judge naturalness phrase by phrase, and draft from how a native speaker would explain the situation.
- Prose by default. Headings, bullets, and bold only where the reader navigates.
Done when every fact, qualification, link, and identifier from the original is in the draft, and the reader from step 1 could act on it.
4. Review
The writer cannot see its own tells. Spawn a reviewer subagent, withhold the conversation, and paste into its prompt:
- the original and the draft
- the reader from step 1
- the full text of
tells.md, plus the pairs chosen in step 2 for Czech
Brief the reviewer:
Read the draft cold, as this reader. Flag every passage that carries a tell from the catalog or leaves the reader unable to act. For each, quote it, name the tell, and give a one-line reason. Reply "clean" when nothing is left.
Fix each flagged passage, or keep it and record why. Send the revision to a fresh reviewer. Without subagents, check the draft against each tells.md entry in turn.
Done when a reviewer replies "clean", or two rounds have run.
5. Return
Return the rewrite alone. Add a note only for flags left after two rounds or a material uncertainty. When asked to edit a file, apply the rewrite there and report the change in one sentence.
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.

