d-o-hub/github-template-ai-agents · Archived
Audit and rewrite content to remove AI writing patterns ("AI-isms").
npx skills add d-o-hub/github-template-ai-agents --skill avoid-ai-writing
This repository is archived — consider an actively maintained alternative.
Execute multiple independent tasks simultaneously using parallel agent coordination to maximize…
1 installsBreak down complex tasks into atomic, actionable goals with clear dependencies and success crit…
1 installsApply this skill to avoid generic "AI slop" in UI, UX, and copy. Triggers: "make this feel less…
1 installsTemplate for creating portable domain-specific verification skills.
1 installsRelated neighbors and high-traction skills in the same topics — useful to compare before installing.
Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…
3.3M installsBrowser automation CLI for AI agents. Use when the user needs to interact with websites, includ…
810.4K installsReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…
617.3K installsBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …
576.5K installsPrepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…
568.3K installsOther skills from d-o-hub/github-template-ai-agents · top by installs.
npx skills add d-o-hub/github-template-ai-agents
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Parsed from SKILL.md frontmatter.
Files included with this skill beyond the listing page.
SKILL.md
3,995 B
AGENTS.md
762 B
SUMMARY.md
368 B
You are editing content to remove AI writing patterns ("AI-isms") that make text sound machine-generated.
rewrite (default): Flag AI-isms and rewrite text to fix them. Returns Issues, Rewritten text, What changed, and a Second-pass audit.detect: Flag AI-isms only. No rewriting. Useful for CI/CD gates or audits.edit: Edit a file in-place with minimal, targeted changes using the Edit tool.Independent of audience context; sets the persona.
casual: Contractions, short sentences (≤14 words), low jargon.professional: Active voice, concrete claims, low hedging.technical: Plain copulatives (is/has), one idea per sentence, imperative mood.warm: Direct address ("you"), strong verbs, medium cadence (15-20 words).blunt: Short declaratives, no padding, no hedges.Adjusts rule strictness for specific audiences.
linkedin: Social-first; relaxed on formatting, strict on P0 credibility killers.blog: Default; all rules full strength.technical-blog: Technical terms (robust, leverage, etc.) exempt; strict prose rules.investor-email: Extra strict on promotional language and significance inflation.docs: Clarity over voice; relaxed on hedging and copula avoidance.casual: Slack/DM style; P0 credibility killers only.references/patterns.md catalog.- rewrite: Return audit, full rewrite, change summary, and second-pass audit. - detect: Return severity-grouped issues (P0/P1/P2) and assessment. - edit: Apply minimal Edit tool changes to target file; return edit report.
--iterate 2 is passed, repeat until no patterns remain (max 2 passes).| Rationalization | Reality |
|---|---|
| "AI writing is grammatically perfect, so it's fine." | Perfection is a tell; natural human writing has varied rhythm and personality. |
| "I can just ask the LLM to 'sound human'." | One-shot "sound human" prompts are vibes-based; this skill uses a structured audit. |
| "This will flag non-native speakers." | Patterns are signals, not proof. Use judgment and pair with context. |
references/patterns.md — Exhaustive catalog of AI patterns and vocabulary.ui-ux-optimize — For optimizing UI/UX specific copy and layouts.readme-best-practices — For documentation structure and discovery.professional + blogvoice-profiles skill for definitions and auto-detection.