Menu

#246 by GitHub stars

danyuchn/asd-ste100-skill

Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite,

Claude CodeEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

8da6b6340aa2 → a610dbdfb273

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 8da6b6340aa2

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit a610dbdfb27366653798bcdd4cebe745c92e1ac5

git clone --filter=blob:none --no-checkout https://github.com/danyuchn/asd-ste100-skill.git .hotskills/danyuchn-asd-ste100-skill && git -C .hotskills/danyuchn-asd-ste100-skill checkout --detach a610dbdfb27366653798bcdd4cebe745c92e1ac5 # Copy each selected skill directory from .hotskills/danyuchn-asd-ste100-skill into .claude/skills/<skill-name>/
6.2kGitHub stars
282stars in 7 days
1skill in this repository
43commits in 30 days

Heat

7.9
  • Star growth, last 7 daysAhead of 96% of tracked repositories
  • Star growth, last 24 hoursAhead of 97% of tracked repositories
  • Rank movement, last 7 daysAhead of 73% of tracked repositories
  • Commits, last 30 daysAhead of 89% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 7, 20266,166

Individual skills in this repository

How it works

asd-ste100

When your agent uses it

Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite, apply Simplified Technical English, plain-language rewrite, controlled-language rewrite, rewrite so an agent cannot misread this. Not for creative or marketing copy.

What it loads into context

Frontmatter

113 tokens

Always available to the agent

SKILL.md

3,598 tokens

When the skill is activated

Reference documents

5,128 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. When to Use This Skill
  2. Two Modes
  3. Source and Scope
  4. Core Rewrite Rules
  5. Scan Checklist
  6. Process
  7. Output Format
  8. Boundaries
  9. Additional Resources

Scripts executed separately

  • scripts/ste-lint.py

Files

  • .claude-plugin/marketplace.jsonasset214 bytes
  • .claude-plugin/plugin.jsonasset238 bytes
  • LICENSEasset1,075 bytes
  • README.mddoc10,995 bytes
  • SKILL.mdcore16,418 bytes
  • SKILL.mdcore16,418 bytes
  • SKILL.mdcore16,418 bytes
  • SKILL.mdcore16,418 bytes
  • SKILL.mdcore16,418 bytes
  • examples/before-after.mddoc7,649 bytes
  • examples/linter-edge-cases.mddoc223 bytes
  • references/writing-rules.mddoc4,891 bytes
  • scripts/ste-lint.pyruns96,247 bytes
Read SKILL.md

# Simplified Technical English (ASD-STE100)

ASD-STE100 is a controlled-language standard built by the aerospace and defense industry (ASD, the AeroSpace and Defense Industries Association of Europe) to stop maintenance technicians from misreading English instructions. The standard removes the two biggest sources of misreading: words with more than one meaning, and sentences with more than one possible structure.

This skill borrows that same discipline for a different reader: an **AI agent or a downstream system** that has to parse an English string — an error message, a tool description, an inter-agent instruction, a status report — without a human in the loop to resolve ambiguity. If a maintenance technician can misread "close the valve" as an adjective ("the valve that is near") instead of a command, so can a language model.

## When to Use This Skill

- An agent's output (explanation, instruction, log message, tool description) reads as dense, jargon-heavy, or ambiguous.
- Text will be consumed by another agent, a translation pipeline, or a non-native English reader, and misparsing has a real cost.
- You are writing a prompt, system message, or tool description and want to remove ambiguity before a model ever sees it.
- You want a **before/after** comparison showing exactly which rule was violated and how the rewrite fixes it. Ask for it — the default output is the rewritten text alone (see Output Format).

This skill is not for creative or marketing copy — STE is deliberately flat and literal. Do not apply it to text where voice, nuance, or persuasion is the point.
View the complete source on GitHub

Skills included

  • asd-ste100

Repository facts

License
MIT
Created
Jul 20, 2026
Last pushed
Nov 7, 2026
Forks
361
Open issues
3
Project activity
Active

Rank over the last 12 weeks

Now #246 · best #241 · up 23 in 30 days

  1. #245 from Oct 30 to Nov 1
  2. #243 on Nov 2
  3. #242 on Nov 3
  4. #241 from Nov 4 to Nov 5
  5. #243 on Nov 6
  6. #246 since Nov 7
75 earlier periods
  1. #852 on Aug 2
  2. #765 on Aug 8
  3. #727 on Aug 9
  4. #715 on Aug 10
  5. #702 on Aug 11
  6. #648 on Aug 12
  7. #571 on Aug 13
  8. #552 on Aug 14
  9. #519 from Aug 15 to Aug 16
  10. #508 on Aug 17
  11. #515 on Aug 18
  12. #502 on Aug 19
  13. #497 on Aug 20
  14. #486 on Aug 21
  15. #468 on Aug 22
  16. #485 on Aug 23
  17. #479 on Aug 24
  18. #482 on Aug 25
  19. #469 on Aug 26
  20. #473 on Aug 27
  21. #468 on Aug 28
  22. #459 on Aug 29
  23. #447 on Aug 30
  24. #459 on Aug 31
  25. #451 on Sep 1
  26. #437 on Sep 2
  27. #440 on Sep 3
  28. #427 on Sep 4
  29. #431 on Sep 5
  30. #432 on Sep 6
  31. #436 on Sep 7
  32. #437 on Sep 8
  33. #429 on Sep 9
  34. #426 on Sep 10
  35. #422 on Sep 11
  36. #418 on Sep 12
  37. #415 on Sep 13
  38. #423 from Sep 14 to Sep 15
  39. #425 on Sep 16
  40. #413 on Sep 17
  41. #418 on Sep 18
  42. #407 on Sep 19
  43. #416 on Sep 20
  44. #411 on Sep 21
  45. #421 on Sep 22
  46. #411 on Sep 23
  47. #405 on Sep 24
  48. #404 on Sep 25
  49. #401 on Sep 26
  50. #410 on Sep 27
  51. #411 on Sep 28
  52. #421 on Sep 29
  53. #409 on Sep 30
  54. #406 on Oct 1
  55. #345 on Oct 2
  56. #303 on Oct 3
  57. #285 on Oct 4
  58. #283 on Oct 5
  59. #278 on Oct 6
  60. #272 on Oct 7
  61. #269 on Oct 8
  62. #268 on Oct 9
  63. #264 on Oct 10
  64. #259 on Oct 11
  65. #258 from Oct 12 to Oct 13
  66. #255 on Oct 14
  67. #252 on Oct 15
  68. #248 on Oct 16
  69. #250 on Oct 17
  70. #249 on Oct 18
  71. #248 from Oct 19 to Oct 21
  72. #245 on Oct 22
  73. #244 from Oct 23 to Oct 25
  74. #241 on Oct 28
  75. #243 on Oct 29

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 37 signals by file

.claude-plugin/plugin.json

  • Network accessline 3
    "description": "Rewrite ambiguous English into ASD-STE100 Simplified Technical English",   "author": { "name": "danyuchn" },   "repository": "https://github.com/danyuchn/asd-ste100-skill",
  • Network accessline 4
    "author": { "name": "danyuchn" },   "repository": "https://github.com/danyuchn/asd-ste100-skill",   "license": "MIT"
  • Network accessline 5
    "repository": "https://github.com/danyuchn/asd-ste100-skill",

README.md

  • Network accessline 3
    A Claude Code skill that rewrites dense, ambiguous English into [ASD-STE100 Simplified Technical English](https://www.asd-ste100.org/) (STE) — the controlled-language standard the aerospace and defense industry built so aircraft maintenance
  • Network accessline 54
    The fastest way to install this skill is the [skills CLI](https://skills.sh/) — no clone, no path setup. Run it from your project root:
  • Network accessline 67
    git clone https://github.com/danyuchn/asd-ste100-skill ~/.claude/skills/asd-ste100
  • Network accessline 96
    - **Hebrew:** [g4lb/asd-ste100-hebrew-skill](https://github.com/g4lb/asd-ste100-hebrew-skill) is a Hebrew port of this skill. It includes a Hebrew linter. ASD-STE100 defines English only, so the Hebrew rules are an adaptation, not an offici
  • Network accessline 97
    - **Indonesian:** [jshsinaga/asd-ste100-indonesian-skill](https://github.com/jshsinaga/asd-ste100-indonesian-skill) adapts this skill for Indonesian technical text. Its Indonesian rules are an adaptation, not an official ASD-STE100 standard
  • Network accessline 101
    - [meiluosi/rewrite-fidelity-skill](https://github.com/meiluosi/rewrite-fidelity-skill) compares the original text with the rewrite. It flags changes in meaning and modality. It uses pattern matching, so check each flag yourself.
  • Network accessline 105
    - [ASD-STE100 official site](https://www.asd-ste100.org/)
  • Network accessline 106
    - [ASD-STE100 — About STE](https://www.asd-ste100.org/about_STE.html)
  • Network accessline 107
    - [ASD Europe — Simplified Technical English](https://www.asd-europe.org/standards-specifications/simplified-technical-english/)
  • Network accessline 108
    - [Simplified Technical English — Wikipedia](https://en.wikipedia.org/wiki/Simplified_Technical_English)
  • Network accessline 109
    - [TechScribe — ASD-STE100 Simplified Technical English](https://www.techscribe.co.uk/techw/asd-simplified-technical-english.htm)

SKILL.md

  • Network accessline 38
    Instead, this skill applies the *underlying principle* (pick the plainest, most common word available and use it the same way every time) rather than checking against a fixed word list. When exact ASD-approved wording matters (e.g. actual a

references/writing-rules.md

  • Network accessline 54
    - [ASD-STE100 official site](https://www.asd-ste100.org/)
  • Network accessline 55
    - [ASD-STE100 — About STE](https://www.asd-ste100.org/about_STE.html)
  • Network accessline 56
    - [ASD Europe — Simplified Technical English](https://www.asd-europe.org/standards-specifications/simplified-technical-english/)
  • Network accessline 57
    - [Simplified Technical English — Wikipedia](https://en.wikipedia.org/wiki/Simplified_Technical_English)
  • Network accessline 58
    - [TechScribe — ASD-STE100 Simplified Technical English](https://www.techscribe.co.uk/techw/asd-simplified-technical-english.htm)
  • Network accessline 59
    - [SKYbrary — Simplified Technical English (STE)](https://skybrary.aero/articles/simplified-technical-english-ste)

scripts/ste-lint.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 93
    # Markup that is not prose: character references (&nbsp; &#39; &#x2192;) and # autolinks (<https://...>). Inline link destinations ("](url") are found by
  • Network accessline 94
    # autolinks (<https://...>). Inline link destinations ("](url") are found by
  • Network accessline 1402
    findings, _ = lint("Press Ctrl&nbsp;C to stop &rarr; &#8594; &#x2192; now. "                        "See [the docs](https://x.io/a;b) or <https://x.io/a;b>.")
  • Network accessline 1403
    "See [the docs](https://x.io/a;b) or <https://x.io/a;b>.")
  • Network accessline 1404
    assert not any(f["rule"] == "semicolon" for f in findings), findings     findings, _ = lint('See [a](https://x.io/a;b "Title") and [b](<a b;c>) and [c](a(b;c)).')     assert not any(f["rule"] == "semicolon" for f in findings), findings
  • Network accessline 1405
    findings, _ = lint('See [a](https://x.io/a;b "Title") and [b](<a b;c>) and [c](a(b;c)).')
  • Network accessline 1419
    for text, cols in (("See [docs](https://x.io/a;b\n).", []),
  • Network accessline 1421
    ("See [a](b;c\n\"title\") now.", []),                        ("See [a](b;c (paren\ntitle)) now.", []),                        ("> See [docs](https://x.io/a;b\n> ).", []),
  • Network accessline 1422
    ("See [a](b;c (paren\ntitle)) now.", []),                        ("> See [docs](https://x.io/a;b\n> ).", []),                        ("See [docs](https://x.io/a;b\n\n).", [(1, 26)]),
  • Network accessline 1423
    ("> See [docs](https://x.io/a;b\n> ).", []),
  • Network accessline 1424
    ("See [docs](https://x.io/a;b\n\n).", [(1, 26)]),
  • Network accessline 1439
    ("See [a](https://x.io/a;b`c`tail).", []),
  • Network accessline 1457
    findings, _ = lint(text)         assert [(f["line"], f["col"]) for f in findings if f["rule"] == "semicolon"] == cols, (text, findings)     findings, _ = lint("Press [stop](https://x.io); then wait. Use & ; here.")
  • Network accessline 1458
    assert [(f["line"], f["col"]) for f in findings if f["rule"] == "semicolon"] == cols, (text, findings)     findings, _ = lint("Press [stop](https://x.io); then wait. Use & ; here.")     assert [f["col"] for f in findings if f["rule"] == "se
  • Network accessline 1459
    findings, _ = lint("Press [stop](https://x.io); then wait. Use & ; here.")

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 1 fact
Signal confidence: 34 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

316.9kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.7kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.3kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230.4kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.3kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

186kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

danyuchn/asd-ste100-skill: #246 on hotskills, 6.2k stars

[![danyuchn/asd-ste100-skill on hotskills](https://hotskills.dev/badge/danyuchn-asd-ste100-skill.svg)](https://hotskills.dev/skill/danyuchn-asd-ste100-skill/)