write-simplified-technical-english
Write, rewrite, or review technical content with ASD-STE100 Simplified Technical English (STE), Issue 9.
Skill by Mattie
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/mattie-write-simplified-technical-english
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: writing
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/write-simplified-technical-english
What's inside
- Skill name
write-simplified-technical-english- Description
- Write, rewrite, or review technical content with ASD-STE100 Simplified Technical English (STE), Issue 9. Use only when the user explicitly invokes $write-simplified-technical-english. Common requests mention ASD-STE100, STE, or "write STE"; do not use for general requests for clear, simple, concise, or technical writing.
- License
- MIT
- Instructions
- 85 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- openai.yaml · agents/
- ASD-STE100.md · references/
- STE_AGENT_GUIDE.md · references/
SKILL.md (first lines)
# Write Simplified Technical English
Apply ASD-STE100 Issue 9 to the user content.
## Load the working reference
Before you use this skill, fully read the guide listed below.
Do not read the guide again when both conditions are true:
- You fully read the guide.
- The full guide stays in the active context.
Read [references/STE_AGENT_GUIDE.md](references/STE_AGENT_GUIDE.md).
Use the guide as the primary working authority.
For an exact rule or dictionary lookup, use an official copy of ASD-STE100
Issue 9. See
[references/ASD-STE100.md](references/ASD-STE100.md)
for the official source and important usage limits.
Read the complete rule or dictionary entry, including its help, examples, page
continuation, and supplemental material.
Read all 434 pages only when the user requests a full-standard review and an
official copy is available.
## Apply the standard
1. Identify the source as procedural text, descriptive text, or text with both
types.
2. Keep technical facts, safety meaning, identifiers, interface labels, code,
commands, measurements, and necessary terminology.
3. Apply all applicable writing rules in Part 1.
4. Use Part 2 to examine each word's meaning and part of speech.
5. Use each approved word only with its approved meaning and part of speech.
6. Use a permitted technical noun or technical verb only in an approved
category.
7. Use one term for one concept.
8. Remove ambiguity before you make the text shorter.
9. Keep quoted material exact.
10. Clearly identify quoted non-STE text.
11. Obey project or customer rules that have more limits when the necessary
meaning does not change.
12. If two rules do not agree, tell the user.
## Examine the result
Do the independent final compliance pass in Section 15 of the guide. This pass
is mandatory:
1. Start a fresh subagent that did not write the candidate text.
2. Use a context-free subagent when the platform supports it. Give the
subagent only the source or requirements, the candidate text, the
unverified candidate terminology list, and the path to the guide. Give it
the official Issue 9 PDF when it is available.
3. Tell the subagent to do only the reviewer role in Section 15 and not to
delegate the review.
4. Require the subagent to examine and record every word occurrence as
specified in Section 15.
5. If the reviewer changes or recommends a change to any wording, treat the
result as `CHANGES_REQUIRED`. Resolve each finding and send the complete
revised candidate to a different fresh subagent.
6. Use the exact official entry when the guide does not resolve a word.
Give the result only after the last subagent pass examines the exact final text
without changing it and reports `PASS`, no unapproved ordinary word, and no
unresolved word.
Do not simulate or replace the subagent pass with a self-review. If you cannot
start an independent subagent or complete the pass, give only the incomplete
review status and its blocker. Do not include candidate text, partial rewritten
text, excerpts, or suggested wording. Do not describe the result as reviewed.
If the STE rules change necessary meaning or fixed text, give the most accurate
permitted version. Identify the exact constraint that prevents correct text.
Give only the requested content unless one of these conditions is true:
- The user wants a compliance report.
- Two rules do not agree.
- The STE rules change necessary meaning or fixed text.From Mattie/mattie_skills, MIT.
More from Mattie/mattie_skills
- 0.567score
lean-proof-review
Mattie
Review Lean theorem production and publication claims for specification fidelity, nonvacuity, trustworthy checking, prose correspondence, and mathematical…
SkillAFreshness: AClaude Code +9 - 0.565score
rrr-review-remedy-respond
Mattie
Review, remedy, and respond to GitHub pull request review comments on the active PR after the user notices reviewer comments on a PR we just pushed or are…
SkillAFreshness: AClaude Code +9 - 0.529score
rmdd
Mattie
Run ReadMe Driven Development only when explicitly invoked as `$rmdd`.
SkillBFreshness: BClaude Code +9 - 0.529score
prior-art
Mattie
Find existing solutions before custom technical design or implementation.
SkillBFreshness: BClaude Code +9 - 0.526score
aiconographer
Mattie
Generate and select consistent two-color lore article icons, then compile candidate sheets into validated transparent SVGs and small-size previews.
SkillBFreshness: BClaude Code +9 - 0.524score
write-humanly
Mattie
Draft, rewrite, or review prose so it sounds like a particular human had a reason to write it.
SkillBFreshness: BClaude Code +9 - 0.524score
write-plainly
Mattie
Write, rewrite, or review prose in plain language for its intended reader while preserving technical meaning, constraints, uncertainty, and protected literals.
SkillBFreshness: BClaude Code +9 - 0.524score
soft-skill-creator
Mattie
Create, update, or soften skills whose guidance lives in human-like judgment, voice, style, observation, or feel-- such as writing, creativity, sensory craft…
SkillBFreshness: BClaude Code +9 - 0.524score
goal-check
Mattie
Give the human a compact reminder of the thread's longer-term goal, recent work, and the input needed next.
SkillBFreshness: BClaude Code +9 - 0.524score
quiet-ux
Mattie
Compensate for your agentic propensity to overcaption, overlabel, and overuse ornamental microcopy.
SkillBFreshness: BClaude Code +9 - 0.524score
rmds
Mattie
Create or revise a project's public README as a ReadMe Desired State only when explicitly invoked as `$rmds`.
SkillBFreshness: BClaude Code +9 - 0.524score
rmdv
Mattie
Validate the latest ReadMe Driven Development run only when explicitly invoked as `$rmdv`.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 16, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Mattie/mattie_skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Mattie
- 0.567score
lean-proof-review
Mattie
Review Lean theorem production and publication claims for specification fidelity, nonvacuity, trustworthy checking, prose correspondence, and mathematical…
SkillAFreshness: AClaude Code +9 - 0.565score
rrr-review-remedy-respond
Mattie
Review, remedy, and respond to GitHub pull request review comments on the active PR after the user notices reviewer comments on a PR we just pushed or are…
SkillAFreshness: AClaude Code +9 - 0.529score
rmdd
Mattie
Run ReadMe Driven Development only when explicitly invoked as `$rmdd`.
SkillBFreshness: BClaude Code +9 - 0.529score
prior-art
Mattie
Find existing solutions before custom technical design or implementation.
SkillBFreshness: BClaude Code +9 - 0.526score
aiconographer
Mattie
Generate and select consistent two-color lore article icons, then compile candidate sheets into validated transparent SVGs and small-size previews.
SkillBFreshness: BClaude Code +9 - 0.524score
quiet-ux
Mattie
Compensate for your agentic propensity to overcaption, overlabel, and overuse ornamental microcopy.
SkillBFreshness: BClaude Code +9
Cite this page
write-simplified-technical-english skill. Agent Mart. https://agentmart.dev/skills/mattie-write-simplified-technical-english (last updated 2026-10-24)