build-profile
Skill1 starsChanged 5 months agoMITView on GitHub
Use when the user wants to create or refresh their candidate profile for Job Search HQ. Triggers: /build-profile, "build my profile", "set up my profile", "generate my candidate profile", "update my profile from my CV / LinkedIn". Produces profile/candidate.md (prose, read by the assessment skills) and profile/profile.json (structured) — either by parsing existing materials (CV, LinkedIn, an old profile) or by a short interview.
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- add-sourceSkill
- add-vacancySkill
- cover-letterSkill
- ingest-cvSkill
- interview-prepSkill
- recheck-statusesSkill
- refresh-listingsSkill
- update-statusSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 23
Mode A — parse existing materials (preferred): If the user has a CV (run /ingest-cv first or point at profile/cv/), a LinkedIn export/URL, …
- Very specific: line 39
Keep candidate.md skimmable: bullet lists, no fluff.
- Very specific: line 44
Write both files (never overwrite without confirming if they already exist — offer to merge).
≈ “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
build-profile
Two outputs, gitignored, mirroring the committed examples:
profile/candidate.md— prose, the shape ofprofile/candidate.example.md(Strengths · Gaps · Languages · CV variants). Assessment skillsReadthis at scoring time.profile/profile.json— structured, the shape ofprofile/profile.example.json(name, title, experienceYears, education, targetRole, targetComp, location, strengths, gaps, languages, cvVariants).
Pick a mode
Mode A — parse existing materials (preferred). If the user has a CV (run /ingest-cv
first or point at profile/cv/), a LinkedIn export/URL, or an old profile, read those and
synthesize. Don't interrogate them for facts already on the page.
Mode B — interview. Otherwise ask a short set of questions (don't exhaust them):
- Target role(s) and seniority.
- Core strengths — the 4–6 things they're genuinely strong at.
- Honest gaps — what they'd be stretched or rejected on.
- Comp expectations (currency, monthly band) and location/timezone/relocation.
- Languages + levels.
- CV variants they keep (e.g. a backend/LLM CV vs a voice CV).
Synthesize
- Be concise and honest — gaps are as useful as strengths (they drive accurate
level/techscoring and gap-defense in interview prep). Don't inflate. - Keep
candidate.mdskimmable: bullet lists, no fluff. cvVariants[]entries reference files underprofile/cv/(see/ingest-cv).
Finish
Write both files (never overwrite without confirming if they already exist — offer to merge).
Then tell the user they're ready to score roles (/add-vacancy) and that the files are local
(gitignored). No bake needed — the profile isn't part of the board.
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.

