meaning-preserving-editor
Skill0 starsChanged 2 months agoMITView on GitHub
Edits and refines text for clarity, grammar, and brevity while preserving 100% of technical meaning and code integrity.
In this repository49 other files it gives its agents.
- bug-reproducerSkill
- claim-checkerSkill
- command-failure-diagnoserSkill
- config-risk-reviewerSkill
- csv-validatorSkill
- deployment-checklist-makerSkill
- diff-reviewerSkill
- factual-summarizerSkill
- field-extractorSkill
- api-contract-testerSkill
- database-migration-helperSkill
- security-vulnerability-fixerSkill
- git-commit-stagerSkill
- git-conflict-resolverSkill
- github-actions-debuggerSkill
- github-issue-triagerSkill
- github-pr-creatorSkill
- github-pr-reviewerSkill
- go-code-qualitySkill
- go-lint-and-vetSkill
- go-testingSkill
- json-schema-converterSkill
- lint-and-typecheckSkill
- meeting-notes-to-actionsSkill
- minimal-bug-fixSkill
- option-comparatorSkill
- py-code-qualitySkill
- py-lint-and-typecheckSkill
- py-testingSkill
- readme-writerSkill
- regression-test-writerSkill
- release-notes-drafterSkill
- repo-inspectorSkill
- research-briefSkill
- reversible-cleanup-plannerSkill
- rust-clippy-checkSkill
- rust-code-qualitySkill
- rust-testingSkill
- small-refactorSkill
- status-updateSkill
- step-by-step-tutorialSkill
- step-decomposerSkill
- tabular-analyzerSkill
- task-briefSkill
- test-runner-debuggerSkill
- ts-code-qualitySkill
- ts-lint-and-typecheckSkill
- ts-testingSkill
- skill-templateSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 9 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use this skill when:
- Very specific: line 20
Do not use to compress or summarize text into fewer bullet points.
- Very specific: line 21
Do not use to invent new documentation sections.
- Very specific: line 28
If draft_text is empty: stop and ask: "Please provide the text you would like edited."
- Distinctive: line 29
Never rename technical identifiers (function names, variables, CLI flags, URLs).
- Distinctive: line 30
Do not add unsubstantiated claims or marketing fluff.
- Distinctive: line 33
Follow these numbered actions:
- Distinctive: line 40
Remove filler words ("in order to" -> "to", "at this point in time" -> "now").
- Distinctive: line 42
Read original and edited versions side by side to ensure no semantic shift.
- Distinctive: line 47
If an ambiguous sentence in original could mean two different things: preserve both meanings or flag the ambiguity in the change log.
- Distinctive: line 48
Never convert a cautious statement ("may cause latency") into an absolute ("causes latency").
- Distinctive: line 77
Stop and ask the user when:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Meaning-Preserving Editor
Edits technical documentation, emails, or specifications to eliminate grammatical errors, passive voice, and wordiness. Strictly preserves technical terminology, code names, and semantics.
1. Purpose
Polish writing without changing what it says. "Meaning-preserving" means every factual premise, command line argument, code symbol, and technical claim remains untouched.
2. When to Use
Use this skill when:
- Polishing technical documentation, comments, or pull request descriptions.
- Refining non-native English drafts into idiomatic technical writing.
- User requests: "Edit this text for grammar and clarity without changing meaning."
3. When Not to Use
- Do not use to compress or summarize text into fewer bullet points; use
factual-summarizer. - Do not use to invent new documentation sections; use
readme-writer.
4. Required Inputs
draft_text: The text to edit (string).style_preference: Optional tone guidelines (e.g., concise, formal, friendly). Default: concise technical.
5. Missing-Input Behavior
- If
draft_textis empty: stop and ask: "Please provide the text you would like edited." - Never rename technical identifiers (function names, variables, CLI flags, URLs).
- Do not add unsubstantiated claims or marketing fluff.
6. Procedure
Follow these numbered actions:
- Action 1: Identify Invariable Elements
- Mark all code blocks, backtick symbols, URLs, and numbers as invariant.
- Action 2: Fix Grammar, Punctuation & Typos
- Correct subject-verb agreement, misspellings, and comma splices.
- Action 3: Simplify Sentence Structure
- Replace passive constructions with active voice where appropriate.
- Remove filler words ("in order to" -> "to", "at this point in time" -> "now").
- Action 4: Audit Meaning Preservation
- Read original and edited versions side by side to ensure no semantic shift.
- Action 5: Emit Edited Output with Change Log
- Format per Section 8.
7. Decision Rules
- If an ambiguous sentence in original could mean two different things: preserve both meanings or flag the ambiguity in the change log.
- Never convert a cautious statement ("may cause latency") into an absolute ("causes latency").
8. Output Format
Emit the edited text using this template:
### Edited Text
[Full edited text here]
---
#### Change Log & Rationale
- **[Edit 1]**: [What was changed and why, e.g. Replaced passive voice]
- **[Edit 2]**: [Corrected typo or punctuation]9. Verification Checklist
- 100% of technical identifiers and code symbols remain identical.
- No factual claims were added, altered, or deleted.
- Grammar and spelling errors are resolved.
- Change log documents all significant edits.
10. Common Failures and Recovery
| Failure Symptom | Cause | Recovery Action |
| Accidental code renaming | Editor treating symbol as prose | Revert symbol back to exact original casing. |
| Tone becomes marketing hype | Over-enthusiastic rephrasing | Strip buzzwords; maintain objective technical voice. |
11. Stop or Escalation Conditions
Stop and ask the user when:
- The draft text is unintelligible to the extent that intended meaning cannot be inferred.
12. Examples
Example 1: Successful Execution
Input:
Draft: In order to successfully run the unit test suite, it is required that the user executes the npm test command at this point in time.Output:
### Edited Text
To run the unit test suite, execute `npm test`.
---
#### Change Log & Rationale
- **Wordiness**: Replaced "In order to successfully run" with "To run".
- **Passive Voice**: Converted "it is required that the user executes" to active imperative "execute".
- **Redundant Phrasing**: Removed filler "at this point in time".
- **Formatting**: Wrapped `npm test` in code backticks for readability.Example 2: Ambiguous or Missing Input
Input:
Edit this:Output:
### Edited Text: Halted - No Text Provided
- **Status**: Halted
Please provide the draft text you would like edited.Example 3: Expected Final Output
Output:
### Edited Text
The database client caches query results for five minutes to reduce round-trip latency.
---
#### Change Log & Rationale
- **Conciseness**: Condensed "is functioning by caching query results for a duration of five minutes" into "caches query results for five minutes".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
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.

