hoavdc/CodexKit / skills/codexkit-talent-review-calibrator
codexkit-talent-review-calibrator
UnverifiedFacilitate talent review and people decisions with a structured view of performance, potential, readiness, risks, and development actions using talent calibration and 9-box logic. Use when preparing talent review, succession planning, promotion readiness, or performance calibration sessions. Do not use for payroll administration, HRIS updates, or generic praise notes.
Talent Review Calibrator
Purpose
Support fairer and more actionable talent discussions by structuring evidence, risk, and development actions.
When to use
- Leaders are preparing a talent review or succession discussion.
- Managers need calibration before promotion or performance decisions.
- HR wants consistent talent cards and action plans.
When not to use
- The task is a transactional HR operation.
- There is no evidence beyond vague opinion or hearsay.
Inputs
- employee or talent pool list
- recent performance evidence and outcomes
- potential indicators, readiness signals, and role criticality
- retention risk, succession context, or capability gaps
Procedure
- Define the evaluation lens and remove criteria drift before rating people.
- Separate evidence, interpretation, and bias risks.
- Place talent using performance, potential, and readiness signals.
- Identify critical-role coverage, succession gaps, and flight risk.
- Recommend development, retention, promotion, or watch actions.
- Flag where calibration evidence is weak or inconsistent.
Output
- talent calibration summary
- per-person talent cards
- 9-box or equivalent placement rationale
- succession and retention risk view
- action plan with owners and timing
Definition of done
- Each recommendation ties back to evidence.
- Critical talent risks and succession gaps are visible.
- The output is usable in an actual calibration session.
Examples
- "Prepare a talent review pack for our engineering and operations managers."
- "Calibrate promotion readiness for these six employees and identify development actions."
Quality Criteria
- Feedback is specific and references exact locations in the reviewed material
- Each critique includes a concrete improvement suggestion
- Severity is categorized (critical / important / nice-to-have)
- Positive aspects are acknowledged alongside areas for improvement
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Is the feedback technically accurate and properly contextualized? |
| Completeness | Were all major sections of the reviewed material addressed? |
| Context-fit | Is the review granularity appropriate for the material's maturity level? |
| Consequence | If the author implemented all feedback literally, what could go wrong? |
Edge Cases
- Material is too early-stage for detailed review — Provide structural feedback only. Note that content review is deferred until it matures.
- Reviewer lacks domain expertise — Focus on structure, clarity, and consistency. Flag domain-specific claims as 'Needs SME verification'.
- Author is defensive or resistant to feedback — Lead with what works well. Frame changes as questions rather than mandates.
Changelog
- v1.0.0 — Initial release
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |