job-search-writing
Skill0 starsChanged 2 months agoMITView on GitHub
Victoria's conventions for job-search correspondence — thank-you notes, follow-ups, cover letters, recruiter emails. Use whenever drafting any message sent to a recruiter, hiring manager, or interviewer.
In this repository3 other files it gives its agents.
- humanizeSkill
- resume-tailoringSkill
- social-trends-radarSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 14
Avoid AI tells generally. No em-dash overuse.
- Distinctive: line 30
Place the most memorable detail at the end of its paragraph so it lands.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Job Search Writing Conventions
Rules for drafting anything Victoria sends to a recruiter, hiring manager, or interviewer: thank-you notes, follow-ups, cover letters, outreach, and LinkedIn messages.
Hard rules
Never use the word "today" in a thank-you note. Notes are often sent the next morning, or read days later. "Thank you for the conversation today" is wrong by the time it lands. Use "thank you for the conversation," "thanks for the time," or reference the substance instead of the timing.
Avoid AI tells generally. No em-dash overuse. Never use these constructions:
- "But here's the thing:"
- "Then I realized:"
- "The result?"
- "Hot take:"
- "but here's what nobody's saying"
- "fluff" / "delve"
- "It's not just [X]. It's also [Y]"
- "No [X]. No [Y]. Just [Z]."
- "From X to Y:"
Thank-you notes
- Short. Three paragraphs maximum, roughly 150–200 words.
- Pick one thread from the conversation, not all of them. A note that revisits everything reads like a summary. A note that picks the single most important thread reads like someone who knows what matters.
- Lead the chosen thread with a specific, memorable proof point rather than a claim. A concrete story ("I found a bug in Sprinklr's reporting that was affecting the entire platform before they had") beats an assertion ("I'm a power user").
- Place the most memorable detail at the end of its paragraph so it lands.
- Close briefly. No elaborate sign-offs, no restating enthusiasm twice.
Voice
Direct, concrete, warm, lightly wry. Numbers attached to stories, stories attached to numbers. No corporate filler, no throat-clearing, no over-explaining. Short declaratives are fine. Read it aloud — if it sounds like a comms team wrote it, rewrite it.
Signs it's working: it sounds like a competent person talking, not like a candidate performing.
Reference details
- Sign-off: first name only
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.

