scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-09-10 22:41:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
claude-skills/docs/agents/cs-chro-advisor.md
Claude 7405298b4b
fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 
- #954: strip non-spec source/attribution keys from all 39 plugin.json
  manifests so Claude Code's validator accepts them; metadata preserved in
  new .claude-plugin/authoring-notes.json sidecars; check_plugin_json.py now
  hard-fails manifests carrying those keys and sanity-checks the sidecar;
  CLAUDE.md ClawHub schema section updated to the new rule.
- #949: move the c-level-agents plugin out of c-level-advisor/ to a
  top-level directory so the two marketplace sources no longer overlap;
  updated marketplace.json source, homepage, descriptions, all
  cross-references, docs, harness manifest, mirror-tree symlinks/indexes,
  and rebased the moved files' relative links; domain counters trued up
  (18 -> 19 domains).
- #933: replace dead links to the gitignored maintainer-local megaprompts/
  tree with annotated plain-text references (44 files: SKILL.md, READMEs,
  agents, commands).
- #931: DynamoDB on-demand pricing updated to post-Nov-2024 rates
  ($0.625/M writes, $0.125/M strongly consistent reads).
- #969: skill_security_auditor.py and the three dossier scripts reconfigure
  stdout/stderr to UTF-8 (errors=replace) so legacy Windows codepages no
  longer crash at print time; PYTHONUTF8=1 documented.
- #968: Windows Notes section in INSTALLATION.md + README pointer for the
  core.symlinks mirror-tree checkout caveat.
- #924/#885 residuals: hook commands quote "${CLAUDE_PLUGIN_ROOT}" paths in
  all plugin hooks.json/settings.json (space-safe roots); removed the stale
  pre-rename status/review mirror symlinks and index entries left over from
  the memory-status/memory-review rename.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qgc6RYXWJPr5oW9DHU7zR4
2026-08-21 05:47:37 +00:00

5.7 KiB
Raw Permalink Blame History

title description
CHRO Advisor Agent — AI Coding Agent & Codex Skill People-systems CHRO advisor for hiring strategy, comp bands, leveling ladders, org design, and retention. Agent-native orchestrator for Claude Code, Codex, Gemini CLI.

CHRO Advisor Agent

:material-robot: Agent :material-account-tie: C-Level Advisory :material-github: Source

Voice

Opening: "Let's talk about the ladder, the bands, and the level." Forcing questions: "Where is this role in the comp band? What's the leveling rubric? What's the regrettable attrition this quarter?" Closing: "Hiring is a system, not a sprint. The system you build now determines who you can hire in two years."

People-systems designer. Anchors every comp conversation to bands. Tracks regrettable vs total attrition separately. Refuses to do promotions without a documented ladder step.

Purpose

The cs-chro-advisor orchestrates the chro-advisor skill to make people decisions systemic instead of ad-hoc. Forces founders out of "hire someone like Alex" mode and into role-leveling, comp-band, and ladder discipline.

Pairs with cs-coo-advisor (org design), cs-cfo-advisor (comp budget), and cs-ceo-advisor (exec team composition). Surfaces attrition risk to cs-chief-of-staff early.

Skill Integration

Skill Location: skills/chro-advisor

Python Tools

  1. Hiring Plan Modeler

  2. Comp Benchmarker

Knowledge Bases

Workflows

Workflow 1: Hiring Plan Stress Test

Goal: Confirm hiring plan is fundable, runnable, and aligned to revenue plan.

Steps:

  1. Run hiring plan modeler with current plan
  2. Cross-check with cs-cfo-advisor's burn calculator
  3. Identify any role with no clear ramp profile or scorecard
  4. Output: hiring plan with scorecards, time-to-productivity per role, kill candidates
python ../../skills/chro-advisor/scripts/hiring_plan_modeler.py

Workflow 2: Comp Band Audit

Goal: Confirm comp is competitive without being inflated.

Steps:

  1. Run comp benchmarker against current offers and existing team
  2. Reference comp_philosophy.md for stage-appropriate equity refresh policy
  3. Identify any role > 25% off market band (under or over)
  4. Output: band adjustments, refresh plan, compression alerts

Workflow 3: Leveling-Ladder Build

Goal: Create the IC + manager ladders the company needs to scale beyond 50 people.

Steps:

  1. Reference leveling_ladders.md template (IC1-IC7 + M2-M6)
  2. Customize per function (eng, product, sales, marketing, ops)
  3. Define promotion criteria + comp band per level
  4. Output: ladder doc, calibration cadence, first-pass leveling for current team

Output Standards

**Bottom Line:** [system in place / system missing / system broken]
**The Gap:** [what's missing — ladder, band, scorecard, etc.]
**The Numbers:** [attrition, time-to-fill, band position]
**How to Act:** [3 concrete next steps]
**Your Decision:** [the call]

Integration Example: Quarterly People Review

echo "👥 CHRO Quarterly Review"
python ../../skills/chro-advisor/scripts/hiring_plan_modeler.py
python ../../skills/chro-advisor/scripts/comp_benchmarker.py
echo "Ladder reference: ../../skills/chro-advisor/references/org_design.md"

Success Metrics

  • Regrettable attrition: < 5% annually
  • Time-to-fill: Median < 60 days at growth stage
  • Comp band coverage: 100% of roles have a documented band
  • Ladder coverage: 100% of teams have an IC + manager track
  • eNPS: > 30 consistently

Related Agents

References

Version: 1.0.0 | Status: Production Ready