ds-humanize
Skill20 starsChanged 46 days agoMITView on GitHub
Remove the AI tells from prose — the patterns that read as machine-written. Not `/ds-deslop` (code slop) or `/ds-comment-review` (whether a comment earns its place), and not `/ds-clarity-review` (whether a reader understands) or `/ds-doc-quality-review` (the document as artifact — bloat, redundancy, structure): this judges only whether the text sounds machine-written.
In this repository52 other files it gives its agents.
- ds-dev-skill-benchSkill
- ds-agent-reviewSkill
- ds-architecture-planSkill
- ds-arenaSkill
- ds-blast-radiusSkill
- ds-blueprintSkill
- ds-bug-reviewSkill
- ds-clarity-reviewSkill
- ds-code-quality-reviewSkill
- ds-comment-reviewSkill
- ds-data-modeSkill
- ds-data-reviewSkill
- ds-debugSkill
- ds-deslopSkill
- ds-doc-quality-reviewSkill
- ds-exploreSkill
- ds-git-modeSkill
- ds-go-reviewSkill
- ds-grill-meSkill
- ds-handoffSkill
- ds-howSkill
- ds-interaction-modeSkill
- ds-java-reviewSkill
- ds-notebook-reviewSkill
- ds-onboardingSkill
- ds-osvSkill
- ds-perf-planSkill
- ds-project-checkpointSkill
- ds-project-resumeSkill
- ds-python-reviewSkill
- ds-quality-gateSkill
- ds-reflectSkill
- ds-retroSkill
- ds-roadmapSkill
- ds-rust-reviewSkill
- ds-security-reviewSkill
- ds-semgrepSkill
- ds-shell-reviewSkill
- dsSkill
- ds-specSkill
- ds-step-modeSkill
- ds-tdd-modeSkill
- ds-test-modeSkill
- ds-test-quality-reviewSkill
- ds-tiger-style-modeSkill
- ds-tldtSkill
- ds-ts-reviewSkill
- ds-ui-modeSkill
- ds-ui-quality-reviewSkill
- ds-verify-thisSkill
- ds-zig-reviewSkill
- ds-zoom-outSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 7
When invoked, remove the AI tells from the prose in scope.
- Distinctive: line 13
Treat any argument as scope (files, directories, globs).
- Distinctive: line 33
Remove tells; don't add voice.
- Very specific: line 35
Don't enforce plainness or restructure for comprehension — that's /ds-clarity-review's lens.
- Very specific: line 36
Document structure stays. Never merge, split, or delete sections — a redundant section is /ds-doc-quality-review's bloat finding, not a …
≈ “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
When invoked, remove the AI tells from the prose in scope. Preserve meaning and the author's register — this removes patterns, it never injects new style, idiom, or figurative flourish. The test: a pattern an experienced writer of this document wouldn't produce.
This objective is distinct from clarity's: /ds-clarity-review optimizes for being understood; this skill optimizes for not reading as machine-written. The two overlap and then diverge — run both when you want both; never let one pass serve the other's goal.
Arguments
Treat any argument as scope (files, directories, globs). With no scope, work on the prose changed on the current branch.
What to remove
- Diff-anchored framing — prose describing its own edit history ("this was added to replace…", "now uses X instead") rather than what the thing is. Rewrite to the current state.
- Negative parallelism — "it's not just X, it's Y" as a reflex construction. State Y.
- Synonym cycling — rotating names for one thing to avoid repeating a word. One concept, one name.
- Inline-header bullets — a bolded label followed by a sentence restating the label.
- Title Case Headings where the document's convention is sentence case.
- Emoji decorating headings or bullets.
- Chatbot artifacts — conversation residue shipped as content: "Certainly!", "Here's the updated version", "as requested", "I hope this helps".
- Sycophancy — flattering the reader, the question, or the codebase.
- Filler phrases — "in order to", "it's important to note that", "as previously mentioned". Cut or compress.
- Stacked hedging — multiple qualifiers on one claim ("could potentially", "may possibly"). One hedge carrying real uncertainty stays; the stack goes.
- Signposting — announcing structure instead of having it: "let's dive in", "in this section we will".
- Rhetorical openers — self-answered questions and dramatic one-word leads.
Guardrails
- Meaning-preserving. Never change what the text claims, only how it sounds.
- Remove tells; don't add voice. Injected idiom or vivid phrasing is out of scope — and would fight the clarity pass.
- Fenced code, inline code, URLs, and quoted material stay byte-identical.
- Don't enforce plainness or restructure for comprehension — that's
/ds-clarity-review's lens. - Document structure stays. Never merge, split, or delete sections — a redundant section is
/ds-doc-quality-review's bloat finding, not a tell.
Output
Apply the edits, then give a concise 1–3 sentence summary of what was removed.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

