humanizer-skills
AGENTS.md0 starsChanged 10 days agoMITView on GitHub
skills/ is the single canonical source of truth for all five Agent Skills (humanize, humanize-text, ai-writing-detector, anti-slop-coder, academic-humanizer).
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 32,671 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 repository15 other files it gives its agents.
- academic-humanizerSkill
- ai-writing-detectorSkill
- anti-slop-coderSkill
- humanizeSkill
- humanize-textSkill
- academic-humanizerSkill
- ai-writing-detectorSkill
- anti-slop-coderSkill
- humanizeSkill
- humanize-textSkill
- academic-humanizerSkill
- ai-writing-detectorSkill
- anti-slop-coderSkill
- humanizeSkill
- humanize-textSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Flat depth-1 discovery: Every skill directory must remain directly under <root>/<skill-name>/SKILL.md so @deepseek-ai/dsh-skill-filesystem …
- Very specific: line 9
Strict frontmatter: Keep description in YAML frontmatter as a single-line double-quoted string so strict parsers in OpenCode and DeepSeek …
- Very specific: line 10
Zero external dependencies: All scripts under skills/*/scripts/ must use Python 3.9+ standard library only.
- Very specific: line 11
Pre-commit check: Always run ./scripts/sync-platforms.sh --check && python3 scripts/validate.py before committing.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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
Repository Contract (AGENTS.md)
skills/ is the single canonical source of truth for all five Agent Skills (humanize, humanize-text, ai-writing-detector, anti-slop-coder, academic-humanizer).
Invariants
- Edit only inside
skills/<skill-name>/and then run./scripts/sync-platforms.shto mirror changes identically into.opencode/skills/,.claude/skills/,.agents/skills/, and.dsh/skills/. - Flat depth-1 discovery: Every skill directory must remain directly under
<root>/<skill-name>/SKILL.mdso@deepseek-ai/dsh-skill-filesystem(DeepSeek Harness) discovers all skills without silent category-folder skipping. - Strict frontmatter: Keep
descriptionin YAML frontmatter as a single-line double-quoted string so strict parsers in OpenCode and DeepSeek Harness never skip a skill on unquoted colons. - Zero external dependencies: All scripts under
skills/*/scripts/must use Python 3.9+ standard library only. - Pre-commit check: Always run
./scripts/sync-platforms.sh --check && python3 scripts/validate.pybefore committing.
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.

