agent-optimize
Skill0 starsChanged 7 months agoUnlicenseView on GitHub
Optimize a document for AI agent consumption. Restructures prose into formats that agents parse efficiently while preserving meaning.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- skillberry-ai/cap-evolvetheir own version, first seen Jun 16, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- skillberry-ai/cap-evolve★ 69same 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.
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- dev-recordSkill
- flesh-outSkill
- generator-codingSkill
- light-v-structureSkill
- no-pre-existing-failuresSkill
- review-skillSkill
- review-stepsSkill
- sandboxSkill
- sdlc-cross-reviewSkill
- strong-editSkill
- my-skillSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 14
Read the target document and identify its current structure
- Distinctive: line 22
Use structured formats agents parse well (clear headers, consistent patterns)
- Distinctive: line 27
Prefer concise, direct language over verbose explanation
- Distinctive: line 31
Add hierarchy indicators to show parent/child relationships
- Distinctive: line 32
Prefer visual structure over narrative explanation
≈ “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
Optimize the target document(s) at $ARGUMENTS for agent consumption.
Stop after each stage and have changes reviewed with user.
Note: The goal is agent efficiency, not stripping all prose. Some content is genuinely better as narrative — context-setting introductions, nuanced trade-offs, philosophy notes. Optimize the structure agents need to parse; preserve the prose humans need to understand intent.
- Read and assess the document (developer confirms)
- Read the target document and identify its current structure
- What sections are prose-heavy and could benefit from structured formats?
- What relationships between concepts are buried in narrative?
- Confirm understanding and optimization targets before proceeding
- Replace verbose prose with structured formats (agent leads with approval)
- Are there narrative paragraphs that would be clearer as tables, diagrams, or bullet lists?
- Convert where meaning is preserved — don't force structure where prose is genuinely better
- Use structured formats agents parse well (clear headers, consistent patterns)
- Compress token usage (agent leads with approval)
- Is there redundant phrasing that can be removed without losing information?
- Are there verbose explanations that could be stated more directly?
- Prefer concise, direct language over verbose explanation
- Make relationships explicit (agent leads with approval)
- Are there implicit references between sections that should be explicit cross-references?
- Add hierarchy indicators to show parent/child relationships
- Prefer visual structure over narrative explanation
Pipeline Position
This skill sits at the end of the composition pipeline: flesh-out -> review-steps -> strong-edit -> agent-optimize. Run it after the content is complete and reviewed — it restructures for consumption, not correctness.
When to Use This vs Other Skills
| Goal | Use |
| Raw notes need structure and expansion | flesh-out |
| Draft needs polish and consistency | review-steps |
| Complete draft needs critical evaluation | strong-edit |
| Finalized document needs agent-friendly restructuring | agent-optimize |
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.