english-technical-message
Skill0 starsChanged 41 days agoMITView on GitHub
Use when improving a short English technical message such as a PR comment, GitHub issue, Slack message, or recruiter reply. Mention "improve my message", "fix my english", "polish this comment" as triggers.
In this repository45 other files it gives its agents.
- admission-policy-reviewSkill
- alert-rule-reviewSkill
- architecture-reviewSkill
- argocd-applicationsetSkill
- argocd-debugSkill
- argocdSkill
- cert-manager-debugSkill
- cicd-reviewSkill
- cilium-debugSkill
- ciliumSkill
- cluster-backupSkill
- dast-reviewSkill
- dockerfile-reviewSkill
- git-messageSkill
- gitops-reviewSkill
- go-bugfixSkill
- go-code-reviewSkill
- go-testing-reviewSkill
- grafana-dashboardsSkill
- helm-reviewSkill
- homelab-change-planSkill
- incident-analysisSkill
- ingressSkill
- interview-system-designSkill
- istio-debugSkill
- istioSkill
- kubernetes-autoscalingSkill
- kubernetes-debugSkill
- kubernetes-securitySkill
- kubernetes-yaml-reviewSkill
- migration-planSkill
- observability-reviewSkill
- observability-stackSkill
- production-readinessSkill
- pr-reviewSkill
- root-cause-analysisSkill
- runbook-writerSkill
- runtime-security-reviewSkill
- secrets-managementSkill
- storage-debugSkill
- supply-chain-securitySkill
- terraform-reviewSkill
- upgrade-readinessSkill
- vaultSkill
- vulnerability-triageSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
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 18
Read the exact draft and surrounding communication context supplied by the user.
- Distinctive: line 22
Do not turn a short operational message into an essay.
- Distinctive: line 26
Follow the Workflow, Safety rules, and Quality checklist below.
- Distinctive: line 36
Use when the user has drafted a short English technical message — a PR comment, GitHub issue, Slack message, or reply to a recruiter — and …
- Distinctive: line 47
Read the draft and identify the actual intent (report a bug, ask a question, push back politely, decline something, confirm a decision).
- Distinctive: line 50
Keep sentences short and direct — this is a technical message, not an essay.
- Distinctive: line 54
If the message could be read as ambiguous or accidentally blunt/rude in English, flag that specifically.
- Distinctive: line 62
Do not change the technical meaning of the message (e.g.
- Distinctive: line 64
Do not over-formalize casual messages (Slack messages don't need to read like a legal memo).
- Distinctive: line 65
Do not invent additional content the user didn't say.
≈ “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
English Technical Message
TL;DR checklist
- Identify the author's intent and audience.
- Correct grammar and phrasing without changing the technical facts.
- Return one ready-to-send version in the original tone.
Key read-only checks
- Read the exact draft and surrounding communication context supplied by the user.
Common pitfalls
- Do not turn a short operational message into an essay.
Agent procedure
Follow the Workflow, Safety rules, and Quality checklist below.
Quick references
- Workflow below.
Last verified: unverified
When to use
Use when the user has drafted a short English technical message — a PR comment, GitHub issue, Slack message, or reply to a recruiter — and wants it improved before sending.
Goal
Make the message natural, clear, and correctly worded at a B2-friendly level, while preserving the original technical meaning and the author's intent — not turning it into something overly formal or robotic.
Workflow
- Read the draft and identify the actual intent (report a bug, ask a question, push back politely, decline something, confirm a decision).
- Fix grammar, word choice, and phrasing errors without changing the technical content.
- Keep sentences short and direct — this is a technical message, not an essay; avoid over-formalizing wording that was already clear.
- Preserve the author's tone (casual Slack message stays casual; a formal recruiter reply stays professional) rather than flattening everything to the same register.
- If the message could be read as ambiguous or accidentally blunt/rude in English, flag that specifically.
- Offer one improved version, and — if the original was notably complex — a simpler alternative phrasing as well.
- Briefly explain the key corrections made, so the user learns the pattern for next time.
Safety rules
- Do not change the technical meaning of the message (e.g. don't soften a real blocker into a vague comment).
- Do not over-formalize casual messages (Slack messages don't need to read like a legal memo).
- Do not invent additional content the user didn't say.
Output format
## Improved version
<the corrected message>
## Simpler version (optional)
<only if useful — a more concise/simpler alternative>
## Key corrections
- <original phrase> → <correction> — <why>Quality checklist
- Technical meaning is unchanged from the original
- Tone/register matches the original context (Slack vs. formal reply)
- Corrections are explained briefly, not just silently applied
- No content was invented beyond what the user wrote
- Wording stays at a natural, B2-friendly level, not artificially advanced
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.

