Skip to content

jackson2w/claude-code-skills / clarity

clarity

Verified

Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write, rewrite, review, and lint modes.

FileKindSize
LICENSEother1.0 KB
SKILL.mdskill md7.5 KB
references/edit.mdmarkdown7.1 KB
references/interview.mdmarkdown3.2 KB
references/longform.mdmarkdown4.9 KB
references/medium.mdmarkdown3.4 KB
references/review.mdmarkdown2.7 KB
scripts/prose_stats.pyexecutablescript14.1 KB
scripts/strip_markdown.pyexecutablescript2.4 KB

references/review.md

View on GitHub
# Review format

Review the piece the user supplied. Do not create a replacement draft or change files unless
asked. Lead with the largest material issue; line edits come second.

## Piece-level diagnosis

Use these fields when relevant, omitting fields that would add ceremony rather than information:

```txt
Job:          the medium, reader, and intended outcome
Substance:    what the piece specifically contributes, or what is missing
Trust:        factual support, attribution, uncertainty, and any preservation risk
Development:  how the material progresses and where it becomes list-like or repetitive
Voice:        what reads as the author's and where generic model register takes over
Ending:       whether it stops on the last useful thought
Top fixes:    the two or three changes with the largest expected gain, ranked
```

For reference, procedural, academic, legal, or message-oriented prose, do not demand an
authorial thesis. Evaluate whether the text performs its actual job.

If the substance is too thin to support a useful rewrite, say so plainly and offer the
interview. Continue with requested line feedback, but explain that surface edits cannot supply
missing evidence or experience.

## Passage-level finding

Use one block per material issue:

```txt
Passage:      the shortest quote that locates the issue
Verdict:      keep / revise / ask-author / cut
Pattern:      a concise name from edit.md
Why:          what the passage does instead of its intended job
Suggestion:   a supported replacement, a precise author question, or the reason to cut
Safety check: whether the suggestion preserves facts, attribution, scope, and voice
```

Verdicts:

- `keep`: a pattern is present but earned, required by the medium, or preferable to the
  proposed alternatives. State what earns it.
- `revise`: the source already contains enough material for an honest improvement.
- `ask-author`: improvement needs a fact, mechanism, example, opinion, or experience the source
  does not supply. Ask exactly for that information and offer a cut or plain fallback.
- `cut`: the passage adds only repetition, ceremony, unsupported emphasis, or closure.

Do not invent the missing material in a suggested rewrite. Check your own replacement for the
same formula, inflated claim, meaning drift, or fabricated detail you identified in the source.

## Review discipline

- Distinguish errors from likely improvements and both from taste.
- Quote the previous sentence when context determines whether a contrast, adjective, passive,
  list, or closing beat is earned.
- Prefer a few high-impact findings to an exhaustive word watchlist.
- Report no finding when the prose already performs its job.
- Do not use a detector verdict as evidence that a passage is good, bad, human, or generated.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall