jackson2w/claude-code-skills / clarity
clarity
VerifiedDraft, 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.
| File | Kind | Size |
|---|---|---|
| LICENSE | other | 1.0 KB |
| SKILL.md | skill md | 7.5 KB |
| references/edit.md | markdown | 7.1 KB |
| references/interview.md | markdown | 3.2 KB |
| references/longform.md | markdown | 4.9 KB |
| references/medium.md | markdown | 3.4 KB |
| references/review.md | markdown | 2.7 KB |
| scripts/prose_stats.pyexecutable | script | 14.1 KB |
| scripts/strip_markdown.pyexecutable | script | 2.4 KB |
references/interview.md
View on GitHub# Perspective interview
Use this only in co-write mode or when an authored draft has a real substance gap. The goal is
to collect language and material the author actually supplies, not to simulate a human voice.
## Start here
Ask the author for one untidied answer before drafting:
> Talk to me for three to five minutes, or stream-type one take. Do not organize it first. Tell
> me what happened, why you want to write this now, who you want to reach, what you believe,
> and the examples or doubts that make the idea yours. Use real names, numbers, and incidents
> only when you are comfortable publishing them. Skip private details instead of blurring them.
Offer these prompts as aids, not a questionnaire they must complete:
- What triggered the piece this week: a conversation, bug, meeting, result, or annoyance?
- Picture one reader. What do they already know, and what should change for them afterward?
- Who disagrees with you, and what is their strongest real argument?
- What do you say about this in conversation that you have never written down?
- Which example from your own work carries the point? What happened and what changed?
- Where are you uncertain, or what have you changed your mind about?
- What would you cut from the conventional version of this piece?
Also ask for prior writing on the topic: posts, notes, talks, definitions, or lists the author
already wrote. Treat those as source text and retain their attribution.
## If a draft already exists
Do not interview the author about the whole draft. Ask at most three questions about the parts
that lack support or authorship:
```txt
This paragraph says [claim]. What is your evidence, and how sure are you?
The example could belong to anyone. What is your version of it?
The ending restates the point. What should the reader actually do, notice, or reconsider?
```
One concrete follow-up usually yields more than five general questions. Prefer: “Tell me about
the last time this actually bit you. What broke, and what did you do?”
## Turn the answer into prose
1. Extract the point, useful phrases, examples, uncertainties, and order of discovery.
2. Build the spine from the author's supplied language. Cut true repetition and direct address
to the interviewer. Reorder when it clarifies development.
3. Lightly edit grammar when comprehension requires it. Protect coined language, trade slang,
genuine asides, mixed feelings, and unusual details. If a stronger edit changes the thought
or erases a distinctive phrase, preserve it or show the author both versions.
4. Add model-written material only for a clear job: sourced research, a definition, a factual
bridge, or compression. Never write a memory, preference, or experience for the author.
5. Leave `[TK: precise question]` where the piece needs material the interview did not provide.
6. Outside the publishable draft, report a provenance note in chat:
```txt
Author material: [which sections or kinds of language came from the interview/prior writing]
Model contribution: [research, organization, connective prose, or none]
Open items: [TK questions or none]
```
Do not report a detector score as proof of authorship. The provenance note describes the actual
process, which is the claim the workflow can support.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |