agentleFS
freskhufreskhu/genesis/.claude/skills/hire/SKILL.md

hire

Skill5 starsChanged 6 months agoApache-2.0View on GitHub

Full hiring pipeline: identify skill gap -> Maria researches -> Sarah hires -> Lena syncs DB

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ship.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no match, proceed with hiring.

    line 18
  2. Very specific:

    Verify with grep -q "Voice rules (mandatory" .claude/agents/<name>.md.

    line 40
  3. Distinctive:

    Never skip steps. Always Maria -> Sarah -> Lena.

    line 66
  4. Distinctive:

    Every hire must have: agent definition, profile, roster entry, DB entry.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

Hiring Pipeline

Step 1 -- Identify the Gap

The orchestrator determines that no existing team member can handle the task. Check the roster:

SELECT id, name, role FROM team_members WHERE is_active = 1;

If no match, proceed with hiring.

Step 2 -- Maria Researches

Delegate to Maria (Senior Researcher):

  • "Maria, pesquisa o que um expert real em [AREA] sabe, faz, e prioriza."
  • Maria uses WebSearch and WebFetch to research real-world professionals
  • Maria delivers a research brief to outbox/Team Reports/research-brief-[role].md

Step 3 -- Sarah Hires

Delegate to Sarah (HR Manager) with Maria's research brief:

  • Sarah designs the new team member: name, persona, identity, skills
  • Sarah creates:
    1. Agent definition in .claude/agents/<name>.md
    2. Profile in Team/<name>.md
    3. Updates Team/roster.md
  • Sarah classifies the agent as text-producing or code-only (default: text-producing — anything emitting human-readable prose: emails, reports, briefs, slide content, posts, analyses).
  • If text-producing, Sarah APPENDS the canonical voice-rules block:
    cat .claude/rules/_agent-voice-block.md >> .claude/agents/<name>.md
    Verify with grep -q "Voice rules (mandatory" .claude/agents/<name>.md. Skip the whole step if you have not written a banlist yet — see .claude/rules/.
  • Code-only agents (pure infra, ops or code roles with no human-facing prose) skip the voice block.

Step 4 -- Lena Syncs DB

MANDATORY -- hire is NOT complete until DB is updated.

Delegate to Lena:

INSERT INTO team_members (name, role, profile_path, agent_path, joined_at)
VALUES (?, ?, 'Team/<name>.md', '.claude/agents/<name>.md', strftime('%Y-%m-%dT%H:%M:%SZ', 'now'));

Log the hire:

INSERT INTO activity_history (actor_id, action, entity_type, entity_id, summary, occurred_at)
VALUES (1, 'hire_completed', 'team_member', (SELECT id FROM team_members WHERE name = ?), 'Hired [name] as [role]', strftime('%Y-%m-%dT%H:%M:%SZ', 'now'));

Step 5 -- Delegate Original Task

Now delegate the original task to the new hire.

Rules

  • Never skip steps. Always Maria -> Sarah -> Lena.
  • Every hire must have: agent definition, profile, roster entry, DB entry.
  • Report to {{OWNER}} when complete: who was hired, why, and where to find them.

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.