agentleFS
Sign inStart free
QaliAIQaliAI/ai-job-agent/skills/refresh-candidate-brand/SKILL.md

refresh-candidate-brand

Skill0 starsChanged 3 months agoMITView on GitHub

Rebuild the candidate's base resume, LinkedIn positioning, project portfolio, and lane-specific professional narrative from verified profile evidence.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  1. Distinctive:

    Use this when the candidate's recent projects, consulting work, AI builds, or career direction have changed enough that the base résumé / …

    line 10
  2. Distinctive:

    Never use an unverified memory or inference as a résumé fact.

    line 22
  3. Distinctive:

    When a current LinkedIn export or public profile is available:

    line 54
  4. Distinctive:

    do not claim that a profile change was made unless it was actually made.

    line 58
  5. Distinctive:

    Avoid long inventories of experiments.

    line 72
  6. Distinctive:

    Before releasing any base résumé or LinkedIn copy:

    line 76
  7. Distinctive:

    never convert system-wide scope into a personal outcome claim without evidence.

    line 79

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

refresh-candidate-brand

Use this when the candidate's recent projects, consulting work, AI builds, or career direction have changed enough that the base résumé / LinkedIn positioning is stale.

Source hierarchy

  1. candidate/MASTER_PROFILE.md
  2. candidate/VERIFIED_ACHIEVEMENTS.md
  3. candidate/CAREER_STORIES.md
  4. candidate/skills.json
  5. candidate-provided source documents, including a LinkedIn export or prior résumé
  6. candidate-provided portfolio / GitHub URLs
  7. public evidence that can be independently verified

Never use an unverified memory or inference as a résumé fact.

Required outputs

Write to output/profile/:

  • base_resume.md — the strongest general résumé, not tied to one posting;
  • linkedin_headline.md — one recommended headline plus 2 materially different alternatives;
  • linkedin_about.md — concise first-person About section;
  • project_portfolio.md — selected builds with problem, action, stack, and result/evidence;
  • positioning_by_track.md — how the same verified experience should be emphasized for each configured opportunity track;
  • profile_gaps.md — missing dates, metrics, credentials, or chronology that must be verified before submission.

Positioning rules

For hybrid candidates, do not flatten the profile into one overloaded identity such as "software engineer / marketer / consultant / everything."

Instead:

  1. define a durable umbrella narrative;
  2. preserve 3–5 opportunity lanes from OPPORTUNITY_TRACKS.json;
  3. map the strongest verified evidence to each lane;
  4. let application tailoring change emphasis, not history.

Examples of distinct lanes:

  • AI transformation / enablement;
  • AI product / solutions builder;
  • growth + CRM / automation systems;
  • fractional advisory / coaching;
  • domain-specialist roles such as coworking / PropTech.

LinkedIn review

When a current LinkedIn export or public profile is available:

  • identify stale titles, About copy, services, Featured items, and skills;
  • recommend additions from verified recent work;
  • recommend Featured links for the strongest working products, talks, publications, demos, and case studies;
  • do not claim that a profile change was made unless it was actually made.

Project evidence

A project is résumé-worthy when it demonstrates at least one of:

  • shipped user-facing software;
  • AI/agent/automation implementation;
  • revenue or operating workflow;
  • technical integration;
  • measurable business outcome;
  • domain expertise;
  • client adoption;
  • meaningful leadership or decision-making.

Avoid long inventories of experiments. Select the projects that prove the target narrative.

QA

Before releasing any base résumé or LinkedIn copy:

  • run claim-check;
  • surface every unresolved chronology/metric issue in profile_gaps.md;
  • never convert system-wide scope into a personal outcome claim without evidence.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free