Import AITURK IDE 1.0.0-beta.1 from Hermes 63279301; preserve MIT license

optional-skills/creative/simple-english/references/checklist.md

@@ -0,0 +1,43 @@
+# Verification checklist
+
+Run this pass on every draft before you deliver it. The checks are ordered from mechanical to judgment.
+
+## Mechanical checks (searchable)
+
+Search the draft for each pattern. Every hit outside code blocks and quoted text is a violation.
+
+| Search for | Violation | Fix |
+|---|---|---|
+| `'ll`, `'re`, `'ve`, `n't`, `it's` | Contraction (Rule 4.2) | Expand it. |
+| `has been`, `have been`, `had been` | Present/past perfect (Rule 3.4) | Simple past or simple present. |
+| `has` / `have` + past participle | Present perfect (Rule 3.4) | Simple past. |
+| `should`, `would`, `may`, `might`, `could` | Unapproved modal (Rule 3.2) | See the modal ladder in SKILL.md. |
+| `is being`, `are being`, `was being` | Progressive passive (Rules 3.4, 3.5) | Active, simple tense. |
+| `, making`, `, allowing`, `, enabling`, `, ensuring` | "-ing" clause as verb (Rule 3.5) | New sentence with a real subject. |
+| `;` | Semicolon (Rule 8.1) | Two sentences. |
+| `e.g.`, `i.e.`, `etc.` | Latin abbreviation (GR-6) | "for example", "that is", name the items. |
+| `simply`, `easily`, `seamlessly`, `robust` | Filler (no fact) | Delete. |
+| ` if `, ` when ` (mid-sentence) | Trailing condition (Rule 5.4) | Move the condition to the start of the sentence, add a comma. |
+
+## Countable checks
+
+1. **Sentence length.** Count words in each sentence. Procedural limit: 20. Descriptive limit: 25. Notes: 25.
+   Backticked commands, numbers with units, and identifiers count as one word each (Rule 8.6).
+2. **Paragraph size.** Maximum six sentences per paragraph (Rule 6.6).
+3. **Multi-word nouns.** Any noun chain over three words → break it with prepositions (Rule 2.1).
+4. **Instructions per sentence.** One, unless the actions are simultaneous (Rule 5.2).
+
+## Judgment checks
+
+5. **Classification.** Is each passage cleanly procedural or descriptive? Procedures in imperative, descriptions never in imperative.
+6. **Voice.** Any passive sentence: is the agent truly unknown, and is the passage descriptive? Otherwise make it active (Rule 3.6).
+7. **Condition placement.** Every "if/when" stands before its command, with a comma (Rule 5.4).
+8. **Synonym rotation.** One term per concept across the whole document (Rules 1.11, 9.4). Scan for check/verify/confirm, config/settings, run/execute.
+9. **Warnings.** Command or condition first, risk second (Rules 7.2, 7.3).
+10. **Completeness.** Articles present, "that" present after "make sure", no telegraph style (Rule 4.2).
+11. **Untouchables intact.** Code, identifiers, quoted errors, and proper nouns are unchanged.
+
+## When reporting violations (check mode)
+
+For each violation give: the rule number, the offending text, and a compliant rewrite. Cite only rule numbers that appear in SKILL.md.
+End the report with this statement when the user asked for STE compliance: "No tool can guarantee ASD-STE100 compliance. Final approval rests with the writer. The official standard is a free download at asd-ste100.org."

optional-skills/creative/simple-english/references/use-cases.md

@@ -0,0 +1,64 @@
+# Use cases beyond documentation
+
+STE was built for aircraft maintenance manuals. The same properties — one meaning per word, short sentences, condition-first commands — transfer to any text where misreading has a cost. By the end of Issue 8, 64% of registered STE users were outside aerospace and defense.
+
+Each case below names the mode and the adaptations.
+
+## Error messages and CLI output
+
+Mode: procedural. This is the highest-value target: an error message is a 2 a.m. instruction to a stressed reader.
+
+Pattern: state what happened (past simple), state the cause if known, give the command or condition to fix it.
+
+> **Before:** Oops! Something went wrong while attempting to establish a connection. Please ensure your credentials are properly configured and try again.
+> **After:** Connection to the database failed. The password for user `app` was not correct. Set `DB_PASSWORD` and connect again.
+
+## Runbooks and standard operating procedures
+
+Mode: strict-leaning procedural. This is STE's home turf — an on-call runbook is a maintenance manual.
+
+- Every step imperative, one instruction per step, conditions first.
+- Warnings before the step, command first, risk second.
+- 20-word limit enforced hard: an operator under pager stress reads each sentence once.
+
+## Incident reports and postmortems
+
+Mode: descriptive. Simple past only — a timeline in present perfect ("we have identified...") hides when things happened.
+
+> **Before:** We have identified an issue that may have impacted some users' ability to access the service.
+> **After:** Between 14:02 and 14:31 UTC, 12% of requests failed. A deploy at 14:00 removed the cache warmup step.
+
+STE bans hedges ("may have impacted") — the report states what is known and says "unknown" for the rest. This reads more honest because it is.
+
+## Commit messages and PR descriptions
+
+Mode: descriptive body, imperative subject. Convention already matches STE: imperative subject line, plain past facts in the body. Apply the substitution table and the 25-word limit to the body. Delete "this PR aims to".
+
+## API changelogs and release notes
+
+Mode: descriptive. One entry, one change, one sentence where possible. "Breaking:" entries follow the warning pattern — command first: "Update your calls to `v2/users`. The `name` field split into `first_name` and `last_name`."
+
+## Instructions for AI agents (prompts, AGENTS.md, skills)
+
+Mode: procedural. A system prompt is a procedure executed by a reader with no ability to ask questions — the exact reader STE was designed for.
+
+- One instruction per sentence keeps rules independently quotable and hard to half-follow.
+- One word, one meaning prevents the model from treating "check", "verify", and "validate" as three different operations.
+- Condition-first ("If the build fails, stop") beats trailing conditions, which models drop.
+- No "should" — a model reads "should" as optional. Write "must" or delete the rule.
+
+## Support macros and status-page updates
+
+Mode: descriptive, 25-word limit. Non-native readers are the majority of many user bases. No "we sincerely apologize for any inconvenience this may have caused" — "The API was down for 18 minutes. Uploads made during this time were saved and will process today."
+
+## Translation and localization prep
+
+Mode: strict. STE's original purpose was making English readable for non-native maintenance crews, and it doubles as pre-editing for machine translation. One meaning per word plus complete grammar (articles, "that") removes most translation ambiguity. If your docs get localized, STE cuts the error rate and the cost.
+
+## UI copy and empty states
+
+Mode: procedural, hard length limits. Buttons and labels are technical names (exempt). Body copy follows the rules: "No projects yet. Create a project to start." Nothing else survives at this length anyway.
+
+## Where STE does not fit
+
+Marketing pages, launch posts, blog voice, brand writing. STE deletes persuasion on purpose. Write those in your own voice — then use STE for the docs the landing page links to.