engineering-writing
Skill1 starsChanged 4 days agoMITView on GitHub
Use for software docs, READMEs, commits, PR bodies, runbooks, error text, release notes and thesis LaTeX invariants, written for readers who will not review closely. Not for general or academic prose (natural-writing), Australian legal drafting (legal-writing), or durable-doc placement and ADRs (engineering-docs).
1 other project uses a version of this.
Adopted by
Most recently taken up by
- 169884902hzl/engineering-paper-skillstheir own version, first seen Oct 5, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- 169884902hzl/engineering-paper-skills★ 3same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- code-reviewSkill
- deliverSkill
- diagnoseSkill
- engineering-docsSkill
- evaluateSkill
- implementSkill
- legal-writingSkill
- natural-writingSkill
- orchestrateSkill
- refactorSkill
- releaseSkill
- retrospectSkill
- scopeSkill
- sessionSkill
- setup-repoSkill
- skill-craftSkill
- test-designSkill
- trackerSkill
- ui-ux-designSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 50
Never style-pass gates, credential custody, decision records or literal runbooks.
≈ “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
Engineering writing
The engineering overlay on natural-writing: that hub owns Australian
English, the mechanism catalogue, the condense pass and claim classes. This
skill adds what a reader of agent-written engineering text needs when they
will not check every line.
Reader contract
- Decision first. Open with what changed, what was decided, or what the reader must do. Background follows only if it changes their action.
- Every claim traces to code, a command, a test result or a link. Verify
each package, API, version, flag and URL against the source; otherwise mark
[FLAG: verify]. Never invent a specific to fill a shape. - Say what was not done or verified.
Not load-tested above 500 usersandretry is out of scope hereare the most valuable lines in a PR. - Observed vs inferred.
CPU sat at 100% for 4 minutesis observed;the regex likely backtracksis inferred, and marked as such. - One term per concept. Repeat the precise noun; do not cycle
endpoint,routeandURLfor variety. - A command or path beats a paragraph that describes it.
Workflow
- Name the reader, what they already know and what they must do. If the job is unclear, say so before drafting.
- Lock identifiers, commands, flags, error text, versions, numbers, dates, obligations and honest negatives. They survive any edit.
- Pick the artefact shape from artefacts.md: README, PR, commit, error, bug report, runbook, postmortem, migration note. For release notes and fragments use release-notes.md. For thesis and paper LaTeX use academic-artefacts.md.
- Draft structure before sentences, then apply the hub's mechanisms and engineer-voice.md for the internal-process leaks agents add to deliverables.
- Audit fidelity independently when a style pass touched facts: give a read-only reviewer the before and after, on fixed axes (dropped facts, promoted hedges, weakened warnings, invented content). Adopt only on an explicit verdict.
Bounds
- Living docs, placement and ADR scope belong to
engineering-docs. - Never style-pass gates, credential custody, decision records or literal runbooks; edit them by hand, and check first whether a test matches their exact wording.
- Agent-authored commits keep the repository's trailer convention. This skill returns a message; staging or committing needs its own authority.
- Specs, issue bodies and plans belong to
scopeandtracker, not here. - Flag what you cannot settle:
[FLAG: verify source],[FLAG: define audience],[FLAG: shortening drops obligation].
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.