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/medium.md
View on GitHub# Medium routing
Read only the row relevant to the task. Explicit user requirements and binding house or venue
rules outrank these defaults.
| Medium | Optimize for | Preserve | Avoid |
|---|---|---|---|
| Essay, article, newsletter | Development, authorial judgment, examples, readable momentum | Voice, uncertainty, earned digressions | A comprehensive survey when one through-line will do |
| Documentation, guide | Correct completion, scanning, prerequisites, examples, failure states | Headings, lists, code, warnings, exact terms | Restructuring for novelty or hiding conditions in prose |
| Reference, API, policy | Retrieval, precision, consistency | Repeated schemas, definitions, tables, normative language | Anti-template edits that make entries inconsistent |
| Academic paper | Claim-evidence fit, venue conventions, calibrated verbs | Citations, numbers, equations, `we`, evidence-bound hedging, useful passive voice | Casualizing, invented evidence, or removing qualification for punch |
| Legal, medical, safety | Accuracy, scope, traceable authority, risk communication | Required notices, definitions, uncertainty, escalation paths | Voice experiments or brevity that drops protections |
| Marketing, launch copy | A specific audience, demonstrated value, credible proof | Product names, constraints, calls to action, required claims | Unsupported superlatives, generic excitement, fabricated customers or metrics |
| Email, memo, Slack | The request, decision, update, owner, and next action | Social context, salutations where expected, useful bullets | Turning a short message into an essay or inserting fake casual mess |
| UI text | Task completion, brevity, accessibility, consistent terminology | Labels, error recovery, localization constraints | Personality that obscures the action or changes product semantics |
| Speech, talk, slides | Listening comprehension, oral rhythm, memorable evidence | Repetition that helps an audience follow, stage directions when requested | Applying page-prose density or removing every rhetorical beat |
| Fiction, narrative | Perspective, causality, scene, character choice, genre expectations | Deliberate ambiguity, voice, nonlinear structure when earned | Adding disorder or open threads solely to evade a model pattern |
## Medium-specific checks
### Documentation and reference
Predictability is a feature. Keep repeated entry structures, numbered procedures, tables, and
explicit transitions when they help retrieval or prevent mistakes. Test whether a reader can
complete the task, not whether each paragraph looks different.
### Academic and high-stakes prose
Never invent or alter evidence. `Suggests`, `is consistent with`, and `may indicate` can be the
most accurate verbs. Flag an unsupported claim for the author instead of manufacturing a figure,
citation, sample size, or stronger conclusion.
For current legal, medical, policy, grant, or venue requirements, consult the governing source;
this writing skill is not authority for changing them.
### Messages
Lead with the concrete request, decision, or update when the relationship permits it. Preserve
real politeness. Cut service-desk filler, but do not make a sensitive message artificially blunt.
### Authored long-form and narrative
This is where Clarity's authorship questions matter most. Look for supplied experience,
judgment, images, and boundaries. Structural asymmetry should follow importance or events, not a
rule that “human writing must be messy.”
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 |