technical-writing
Patterns for clear technical writing in documentation, READMEs, API references, and design documents.
Skill by NPC-Worldwide
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/npc-worldwide-technical-writing
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, backend, writing, documentation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/technical-writing
What's inside
- Skill name
technical-writing- Description
- Patterns for clear technical writing in documentation, READMEs, API references, and design documents.
- License
- MIT
- Instructions
- 63 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# technical-writing
Patterns for clear technical writing in documentation, READMEs, API references, and design documents.
## Clarity
One idea per sentence. One topic per paragraph.
- Use simple subject-verb-object order. Avoid nested clauses.
- Replace jargon with plain language unless the term is standard for the audience.
- Define acronyms on first use. Do not assume the reader knows internal project names.
- Use active voice: "The scheduler retries failed tasks" not "Failed tasks are retried by the scheduler."
## Precision
Be exact about behavior, not suggestive.
- Write "Returns a list of strings" not "Returns some data."
- Write "Throws ValueError if the input is negative" not "May throw an error for bad input."
- Write "Timeout is 30 seconds" not "Timeout is fairly short."
- Distinguish "must" (requirement), "should" (recommendation), and "may" (optional).
## Structure
Documents follow a predictable hierarchy:
- What this is (one sentence).
- What problem it solves (one paragraph).
- How to use it (minimal working example).
- Configuration or parameters (table or list with types and defaults).
- Error handling and edge cases.
- Limitations and assumptions.
- Links to related docs or source code.
Do not bury the example under three paragraphs of motivation.
## Code-Examples
Every concept must have a minimal reproducible example.
- Show the simplest possible call that produces a valid result.
- Show one error case if the failure mode is non-obvious.
- Include expected output as a comment or separate block.
- Keep examples copy-pasteable. No pseudocode in API docs.
## Cross-References
Never leave the reader hunting for related information.
- Link to prerequisite concepts before using them.
- Link to deeper dives from high-level summaries.
- If a term is defined elsewhere, link the first use in each major section.
- Keep links working. Broken links erode trust faster than missing links.
## Revision-Checklist
Before marking a doc complete:
- Can a new reader follow the example without asking for help?
- Are all claims verifiable (traceable to code, test, or source)?
- Are there any ambiguous pronouns ("it", "this") that could mislead?
- Is every number, parameter, and default current with the code?
- Does the doc answer "what happens if this goes wrong?"From NPC-Worldwide/npcsh, MIT.
More from NPC-Worldwide/npcsh
- 0.798score
weak-writing-generator
NPC-Worldwide
Generate paired weak/strong technical writing examples for training and preference optimization.
SkillAFreshness: A★ 496Claude Code +9 - 0.797score
npcpy-prompting
NPC-Worldwide
npcpy LLM prompting and JSON formatting patterns.
SkillAFreshness: A★ 496Claude Code +9 - 0.387score
git-workflow
NPC-Worldwide
No description from the publisher yet.
SkillAFreshness: A★ 496Claude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 496
- Forks
- 34
- Open issues
- 9
- Last commit (this folder)
- Jul 22, 2026 (3 months ago)
- Last release
- Oct 21, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/NPC-Worldwide/npcsh
- Website
- npc-shell.readthedocs.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from NPC-Worldwide
- 0.823score
natural
NPC-Worldwide
Render the provided prompt template with Jinja context and send it to the active NPC's LLM.
SkillAFreshness: A★ 1.5KClaude Code +9 - 0.822score
run_jinx
NPC-Worldwide
Execute a jinx by name (already loaded on the team) or by filesystem path (e.g.
SkillAFreshness: A★ 1.5KClaude Code +9 - 0.822score
create_jinx
NPC-Worldwide
Write a new .jinx file from inputs (name, description, inputs spec as JSON list of strings, python body).
SkillAFreshness: A★ 1.5KClaude Code +9 - 0.817score
knowledge_store_skill
NPC-Worldwide
Skill for working with local .knowledge.yaml files via KnowledgeStore.
SkillAFreshness: A★ 1.5KClaude Code +9 - 0.817score
knowledge_sememolution_skill
NPC-Worldwide
Skill for population-based Knowledge Graph evolution via Sememolution.
SkillAFreshness: A★ 1.5KClaude Code +9 - 0.817score
knowledge_graph_skill
NPC-Worldwide
Skill for searching and evolving the SQLite-backed Knowledge Graph.
SkillAFreshness: A★ 1.5KClaude Code +9
Cite this page
technical-writing skill. Agent Mart. https://agentmart.dev/skills/npc-worldwide-technical-writing (last updated 2026-10-24)