AuthorOps-Skills
AGENTS.md0 starsChanged 2 months agoMITView on GitHub
AuthorOps-Skills is a portable, standalone skill library. Treat every skills/**/SKILL.md as an independently invocable intellectual operation.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository101 other files it gives its agents.
- abstract-reviewSkill
- literature-gapSkill
- methodology-reviewSkill
- paper-structureSkill
- results-discussion-alignmentSkill
- reviewer-responseSkill
- book-outlineSkill
- chapter-purposeSkill
- character-consistencySkill
- narrative-arcSkill
- pacing-checkSkill
- timeline-consistencySkill
- citation-accuracySkill
- citation-checkSkill
- citation-completenessSkill
- citation-generationSkill
- citation-relevanceSkill
- citation-styleSkill
- duplicate-reference-checkSkill
- reference-list-checkSkill
- source-claim-mappingSkill
- source-to-claim-mapSkill
- active-voiceSkill
- ambiguity-checkSkill
- clarity-checkSkill
- coherence-checkSkill
- concision-checkSkill
- grammar-checkSkill
- jargon-checkSkill
- parallelism-checkSkill
- passive-voiceSkill
- proofreadingSkill
- punctuation-checkSkill
- readability-checkSkill
- redundancy-checkSkill
- repetition-checkSkill
- spelling-checkSkill
- terminology-consistencySkill
- tone-checkSkill
- attribution-auditSkill
- claim-auditSkill
- final-document-auditSkill
- overclaiming-checkSkill
- plagiarism-risk-reviewSkill
- quotation-integritySkill
- self-plagiarism-riskSkill
- source-provenanceSkill
- chapter-structureSkill
- manuscript-consistencySkill
- manuscript-readinessSkill
- manuscript-structureSkill
- title-page-checkSkill
- cover-letterSkill
- ethics-disclosure-checkSkill
- journal-fitSkill
- peer-review-readinessSkill
- submission-requirementsSkill
- coherence-checkSkill
- completeness-checkSkill
- consistency-checkSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
Do not add workflow orchestration, application code, vendor-specific agent implementations, or UI.
- Distinctive: line 8
Prefer small composable skills over giant all-purpose prompts.
- Distinctive: line 10
Never claim external verification, plagiarism detection, citation validation, or source access unless the required evidence/tool is …
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AuthorOps-Skills Agent Guidance
AuthorOps-Skills is a portable, standalone skill library. Treat every skills/**/SKILL.md as an independently invocable intellectual operation.
Boundaries
- This repository contains skills and the standards needed to make skills interoperable.
- Do not add workflow orchestration, application code, vendor-specific agent implementations, or UI.
- Prefer small composable skills over giant all-purpose prompts.
- Skills detect, explain, suggest, rewrite, verify, or audit; they should state which mode they support.
- Never claim external verification, plagiarism detection, citation validation, or source access unless the required evidence/tool is actually available.
- Preserve author intent and agency. Default to identifying and explaining problems before rewriting.
Skill quality
A skill must have: precise purpose, explicit applicability, inputs, procedure, constraints, output contract, failure modes, and quality gates.
Evolution
Improve skills from real use and observed failures. New behavior should be backed by examples or regression cases when practical.
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.