agentleFS
shalombshalomb/agent-skills/skills/asd-ste100/SKILL.md

asd-ste100

Skill3 starsChanged 3 months agoMITView on GitHub

Use when a system must parse English text without a human. This includes tool descriptions, error messages, inter-agent instructions, system prompts, and status reports. Triggers on "ste", "asd-ste100", "simplified technical english", "rewrite prompt", or "optimize instructions".

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use handoff, tdd and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 5 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 13 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    One word, one meaning: Use only simple, approved words.

    line 29
  2. Distinctive:

    No abstract AI words: Remove words like "delve", "interplay", "tapestry", "crucial", and "seamless".

    line 31
  3. Distinctive:

    Active Voice only: Write the actor first. (Example: Write "The agent deletes the file".

    line 34
  4. Distinctive:

    Keep sentences short: Use a maximum of 20 words for instructions.

    line 35
  5. Distinctive:

    One command per sentence: Do not use "and" to connect actions.

    line 36
  6. Distinctive:

    No gerunds or present participles (-ing): Do not use verbs that end in "-ing".

    line 37
  7. Distinctive:

    Noun clusters: Use a maximum of 3 words for a noun group.

    line 39
  8. Distinctive:

    No ellipsis: Write the subject, verb, and article.

    line 40
  9. Distinctive:

    Sequential order: Write steps in the exact chronological order.

    line 41
  10. Distinctive:

    Zero politeness or filler words: Remove words like "Please", "If you can", "Try to", "Great question", and "I hope this helps".

    line 44
  11. Distinctive:

    No metaphors or figurative language: Use literal language. Use factual language.

    line 45
  12. Distinctive:

    No hedging: Remove words like "maybe", "potentially", and "could be".

    line 46
  13. Distinctive:

    If the user asks, show a before-and-after comparison.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ASD-STE100 (Simplified Technical English) Optimizer

You are an expert in ASD-STE100 (Simplified Technical English). Rewrite prompts, system instructions, and technical documentation. Obey strict STE rules.

This standard decreases token usage. It makes agent execution faster. It stops agent errors. It removes language ambiguity.

Two Modes

Choose a mode before you rewrite the text:

Strict — Use for procedures, error messages, tool descriptions, and inter-agent instructions. Apply all structural and lexical rules. Enforce length limits. Use the one-word-one-meaning rule. STE-flavored — Use for README files, pull request descriptions, and general text. Apply structural rules (sentence limits, active voice, no semicolons). Relax the dictionary rules to allow natural text flow.

Source and Scope

ASD-STE100 uses a proprietary dictionary. We do not include this dictionary here because of copyright rules. This skill uses the core rule of the dictionary. Choose the simplest word. Use this word the same way every time.

Core STE Rules

Obey these rules when you rewrite text:

1. Dictionary and Vocabulary

  • One word, one meaning: Use only simple, approved words. Do not use synonyms. (Example: Use "start". Do not use "begin", "initiate", or "launch").
  • No phrasal verbs: Replace two-word verbs with single verbs. (Example: Replace "carry out" with "do". Replace "take off" with "remove").
  • No abstract AI words: Remove words like "delve", "interplay", "tapestry", "crucial", and "seamless".

2. Grammar and Structure

  • Active Voice only: Write the actor first. (Example: Write "The agent deletes the file". Do not write "The file is deleted").
  • Keep sentences short: Use a maximum of 20 words for instructions. Use a maximum of 25 words for descriptions.
  • One command per sentence: Do not use "and" to connect actions.
  • No gerunds or present participles (-ing): Do not use verbs that end in "-ing".
  • No semicolons: Split sentences. STE does not permit the semicolon.
  • Noun clusters: Use a maximum of 3 words for a noun group. (Example: Write "fuel pump valve". Do not write "high pressure fuel pump inlet valve assembly").
  • No ellipsis: Write the subject, verb, and article. Do not drop words to save space. (Example: Write "The files are missing". Do not write "Files missing").
  • Sequential order: Write steps in the exact chronological order.

3. Tone

  • Zero politeness or filler words: Remove words like "Please", "If you can", "Try to", "Great question", and "I hope this helps".
  • No metaphors or figurative language: Use literal language. Use factual language.
  • No hedging: Remove words like "maybe", "potentially", and "could be".

Examples

Before (Conversational Prompt): "Try to clean up the error handling in this file if you can, and maybe add some logging too, but don't go overboard — just make sure it doesn't break anything else; also it'd be good if tests still pass."

After (Strict ASD-STE100): "Add a try-catch block around the API call in fetchUser(). Log the error message to the console. Do not change any other function. Run the test suite after you make this change. Do not submit the change if a test fails."

Your Task

When you start:

  1. Tell the user which mode you use (Strict or STE-flavored).
  2. Rewrite the text. Obey the rules above.
  3. If the user asks, show a before-and-after comparison. Tell the user which rules the original text broke. Tell the user how the new text obeys the rules.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.