How do I install the Performance Review skill?

Run npx skillmds@latest add knuckles-team/performance-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Performance Review safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Performance Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Performance Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Performance Review?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Performance Review by knuckles-team

Name: Performance Review
Author: Knuckles-Team

Performance Review

Run an employee performance review: gather OKRs and metrics, analyze performance against targets, and generate a review report. Use for periodic or annual performance evaluations and OKR tracking.

Knuckles-Team dd8270f 2 files · 2.8 KB Updated Sep 17, 2026

File contents

Performance Review Workflow

CONCEPT:KG-2.12 — Company Operations Domain

Periodic performance evaluation leveraging KG OKR cascading for transparent, data-driven reviews.

Steps

Step 0: Gather OKR Progress

Agent: hr-coordinator Tools: graph_query

Query KG for employee's OKR hierarchy using cascadesTo traversal:

Organization-level OKRs → Department OKRs → Individual OKRs
okrProgress (0.0–1.0) for each objective
Key result completion rates
Cross-functional contributions (edges to other team's goals)

Step 1: Compute Metrics & Trends

Agent: analytics-agent Tools: graph_query, data_science_mcp

Analyze performance data:

OKR completion rate vs. targets
Competency growth (proficiencyLevel changes)
Peer review scores (if available)
Sprint velocity / throughput metrics
Comparison to role-level benchmarks

Step 2: Generate Review Document

Agent: report-generator Tools: graph_write, document_tools

Generate structured performance review:

Strengths and achievements
Areas for improvement
OKR scorecard with evidence links
Development plan recommendations
Compensation review recommendation (if applicable)

Step 3: KG Persistence

Agent: graph-os

Create PerformanceReview node linked to:

Employee via reviewedIn edge
OKR nodes via measuresGoal edges
Next review cycle via scheduledFor

Output

Performance review document (PDF/MD)
PerformanceReview node in KG with reviewRating
Development plan recommendations
Compensation adjustment recommendation (for human review)

Human Oversight Required

✅ Final performance ratings and compensation changes require manager approval.

Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet depends_on run in parallel; dependents run after their prerequisites complete.

Run first (in parallel): Step 0 — Gather OKR Progress; Step 1 — Compute Metrics & Trends; Step 2 — Generate Review Document; Step 3 — KG Persistence

Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

---name: performance-reviewdescription: Run an employee performance review: gather OKRs and metrics, analyze performance against targets, and generate a review report. Use for periodic or annual performance evaluations and OKR tracking.---# Performance Review Workflow**CONCEPT:KG-2.12 — Company Operations Domain**Periodic performance evaluation leveraging KG OKR cascadingfor transparent, data-driven reviews.## Steps### Step 0: Gather OKR Progress**Agent**: `hr-coordinator`**Tools**: `graph_query`Query KG for employee's OKR hierarchy using cascadesTo traversal:- Organization-level OKRs → Department OKRs → Individual OKRs- okrProgress (0.0–1.0) for each objective- Key result completion rates- Cross-functional contributions (edges to other team's goals)### Step 1: Compute Metrics & Trends**Agent**: `analytics-agent`**Tools**: `graph_query`, `data_science_mcp`Analyze performance data:- OKR completion rate vs. targets- Competency growth (proficiencyLevel changes)- Peer review scores (if available)- Sprint velocity / throughput metrics- Comparison to role-level benchmarks### Step 2: Generate Review Document**Agent**: `report-generator`**Tools**: `graph_write`, `document_tools`Generate structured performance review:- Strengths and achievements- Areas for improvement- OKR scorecard with evidence links- Development plan recommendations- Compensation review recommendation (if applicable)### Step 3: KG Persistence**Agent**: `graph-os`Create PerformanceReview node linked to:- Employee via reviewedIn edge- OKR nodes via measuresGoal edges- Next review cycle via scheduledFor## Output- Performance review document (PDF/MD)- PerformanceReview node in KG with reviewRating- Development plan recommendations- Compensation adjustment recommendation (for human review)## Human Oversight Required✅ Final performance ratings and compensation changes require manager approval.## ExecutionRun this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.- **Run first (in parallel):** Step 0 — Gather OKR Progress; Step 1 — Compute Metrics & Trends; Step 2 — Generate Review Document; Step 3 — KG Persistence**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.

Frequently asked questions