Skip to content

Kartik-Doye/Ravengard-AI-Recruiter / .claude/skills/not-ai

not-ai

Verified

Edit prose into a clear, specific, source-grounded version that preserves the author's meaning and voice. Use for humanizing stiff writing, removing generic phrasing, matching a supplied voice sample, diagnosing robotic prose, or drafting from the user's notes. Do not optimize for AI-detector scores or claim to prove authorship.

FileKindSize
SKILL.mdskill md14.1 KB
reference/mechanical-tells.mdmarkdown1.5 KB
reference/profile.mdmarkdown1.7 KB
reference/research-sources.mdmarkdown2.1 KB
reference/vocabulary.mdmarkdown1.6 KB
reference/why-word-swapping-fails.mdmarkdown1.4 KB

reference/profile.md

View on GitHub
# Linguistic profile: use as context, not a target

Read this reference when a passage feels consistently dense or mismatched to
its genre and the reason is not obvious from vocabulary alone.

Reinhart et al. compared human continuations with outputs from GPT-4o and Llama
3 variants across several English registers. Instruction-tuned models used some
features at different population rates, including present participial clauses,
nominalizations, phrasal coordination, passive voice, and stance markers.

These findings support one editorial question: **does this passage use the
grammar its situation needs?** They do not provide ceilings, floors, or a recipe
for rewriting an individual document.

## Questions worth asking

- Does a personal note carry the density of an academic abstract?
- Does an academic abstract lose necessary precision when made conversational?
- Do several nouns hide the actor or action the reader needs?
- Does a participial clause express a real relationship, or merely attach a
  polished-sounding summary?
- Is passive voice useful because the actor is unknown or irrelevant?
- Does the writer qualify a claim at the level the evidence supports?

## Decisions the evidence does not justify

- Do not insert `because`, contractions, first person, passive voice, or short
  sentences to hit a frequency.
- Do not replace a precise technical term merely because it is long or Latinate.
- Do not treat a feature count as evidence about who wrote the passage.
- Do not compare the bundled regex proxies with rates produced by a parsed
  research corpus. They are different measurements.

The correct comparison is usually local: the draft against its purpose, genre,
source material, and, when supplied with consent, the same writer's work.
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall