BumpyClock/agent-templates / skills/pstack/technical-writing
technical-writing
UnverifiedWrite or review technical documents, PR descriptions, and commit messages.
Technical writing
Make the requested document accurate and useful to its intended reader. Preserve the requested format, scope, and repository conventions. This skill owns technical accuracy, terminology, and reader context. Unslop owns the prose cleanup pass.
Document structure
Use the reader's task to choose the structure. For document sets or an unclear document purpose, read Document types. A small edit does not require document reorganization.
Technical accuracy
- Preserve exact identifiers, commands, paths, quotations, and code semantics.
- Match code examples to the project's language and format conventions.
- Distinguish current behavior, proposed behavior, and unresolved facts.
- Support consequential claims with relevant source evidence.
- Preserve warnings, prerequisites, limitations, and necessary uncertainty.
- Report source defects without changes to product code unless authorized.
Prose
Follow repository prose rules. Where those rules leave a choice, prefer concrete verbs, explicit actors, and consistent technical terms. Keep conditions and negation close to the action they qualify. Use the same name for the same concept. Do not replace valid technical vocabulary with a less precise synonym.
For substantial style revision, use Unslop. Do not modify that skill or other shared instructions as a side effect. For STE-controlled documents, use the required edition and dictionary before a claim of formal compliance.
PR and commit text
Use this pass during pre-PR cleanup or a requested review of PR or commit text. Check claims against the proposed diff, user intent, and available verification evidence. Distinguish implemented behavior from plans and passing checks from unverified expectations. Give reviewers the reason for the change, its scope, and material risks or tradeoffs without repeating the diff. Preserve exact symbols and use consistent terms across the text and changed documentation. Follow the repository's template and the Git and releases conventions. PR and commit text do not require document-type analysis. Correct unsupported or misleading wording within the requested scope. Report unresolved factual questions or code defects rather than hiding them with more confident prose.
Completion
For review requests, return material findings with source locations and proposed corrections. For edit requests, deliver the revised text and report unresolved factual questions. For PR bodies, summarize reviewer-relevant changes and risks. Link detailed decision logs, commit lists, and measurement tables unless the requested format needs them inline. Check affected links, identifiers, and examples against their sources. Run executable examples only when their accuracy needs a check and execution is within scope.
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: 464k | 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: 196k | 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: 196k | 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: 196k | Updated | Claude CodeCodex | Verified | Install |