review-email-tone
Skill49 starsChanged 3 months agoMITView on GitHub
Reviewer criteria for outbound email drafts via with_review. Checks tone-recipient match, professionalism, no AI tells, no placeholder leakage. Use as criteria.skill argument when reviewing email drafts before send.
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 27
Avoid: "I'm reaching out", "I hope this email finds you well", "delve into", "harness", "unlock", "robust", "synergy", "leverage" (as a …
- Distinctive: line 30
Avoid em dashes if the user's house style avoids them — check the User Preferences block in context for tone constraints
- Distinctive: line 32
Avoid passive-aggressive phrases ("just following up", "as mentioned previously", "per my last email")
- Distinctive: line 47
Don't use multiple sign-offs in one email
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Email tone review criteria
Review the worker's email draft against these checks. Issue exactly one verdict per iteration:
- APPROVE — passes all checks. Ready to send.
- REVISE — 1-2 specific tone or content issues that the worker can fix.
- REJECT — fundamentally wrong shape (e.g. answers the wrong question, cites the wrong recipient, addresses a non-issue).
Checks
- Tone matches recipient + situation:
- Customer service emails: warm, brief, action-oriented
- B2B emails: clear, professional, no false urgency
- Apology emails: own the issue without grovelling
- Internal Slack-likes: casual, no formal sign-off
- Cold outreach: relevant first sentence, no walls of text
- No AI tells:
- Avoid: "I'm reaching out", "I hope this email finds you well", "delve into", "harness", "unlock", "robust", "synergy", "leverage" (as a verb), "moving forward", "circle back"
- Avoid em dashes if the user's house style avoids them — check the User Preferences block in context for tone constraints
- Avoid passive-aggressive phrases ("just following up", "as mentioned previously", "per my last email")
- Specific values used verbatim (CRITICAL):
- Customer name, amounts, order numbers, dates, codes from the
Task must appear as literal text — never
[CUSTOMER_NAME]or[AMOUNT]placeholder leakage. This is always REVISE.
- Customer name, amounts, order numbers, dates, codes from the
Task must appear as literal text — never
- Action clear:
- The recipient should know what to do (reply, click, wait, etc) after one read. If unclear, REVISE.
- Sign-off matches sender role:
- Personal email: first name only
- Customer support: name + role + company
- Don't use multiple sign-offs in one email
- Length appropriate:
- Quick acknowledgement: 1-2 short paragraphs
- Detailed response: ≤4 paragraphs unless explicitly asked for more
- One-line replies are fine when the situation calls for them
Verdict format
Respond with ONE LINE in this exact shape:
VERDICT: APPROVE — warm tone matches the apology context cleanly
VERDICT: REVISE — replace "I hope this finds you well" with a direct first sentence
VERDICT: REJECT — drafted a refund denial when the task asked for an apology + refund confirmationThe em-dash (—) or hyphen (-) is the parser delimiter — use either.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-asks-tasksSkill
- caretakerSkill
- code-reviewSkill
- compare-optionsSkill
- create-reportSkill
- csv-analyseSkill
- document-qaSkill
- draft-emailSkill
- enrich-errorSkill
- extract-structured-dataSkill
- fact-checkSkill
- git-diff-summariserSkill
- librarian-curateSkill
- meeting-notesSkill
- morning-briefSkill
- plan-taskSkill
- reflectSkill
- remember-conversationSkill
- reverieSkill
- review-code-securitySkill
- review-outputSkill
- review-summary-faithfulnessSkill
- rewrite-for-audienceSkill
- route-findingSkill
- routine-health-checkSkill
- save-research-docSkill
- score-importanceSkill
- summarise-urlSkill
- web-researchSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

