performance-review-assistant

performance-review-assistant is a skill for Claude Code, Codex from w95/awesome-claude-corporate-skills. It costs 58 tokens per session (4,518 once invoked), scanned A, original, MIT.

A guide for writing and conducting performance reviews, including manager feedback, self-assessments, peer feedback, development plans, and performance-improvement plans.

In plain words
What is it for?
Use it to prepare reviews, 360-degree feedback, growth plans, promotion assessments, difficult conversations, and corrective documentation.
Why use it?
It helps managers make feedback specific, constructive, and actionable while documenting performance decisions clearly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to prepare reviews, 360-degree feedback, growth plans, promotion assessments, difficult conversations, and corrective documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/w95/awesome-claude-corporate-skills/performance-review-assistant
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add w95/awesome-claude-corporate-skills --skill performance-review-assistant
Clone the repo
git clone --depth 1 https://github.com/w95/awesome-claude-corporate-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for performance-review-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/w95/awesome-claude-corporate-skills/performance-review-assistant/github.svg)](https://agentmods.dev/skills/w95/awesome-claude-corporate-skills/performance-review-assistant)
Your own site
<a href="https://agentmods.dev/skills/w95/awesome-claude-corporate-skills/performance-review-assistant"><img src="https://agentmods.dev/badge/skills/w95/awesome-claude-corporate-skills/performance-review-assistant/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for performance-review-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/w95/awesome-claude-corporate-skills/performance-review-assistant"><img src="https://agentmods.dev/badge/skills/w95/awesome-claude-corporate-skills/performance-review-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.04518
Opus 5 $0.00029 $0.02259
Sonnet 5 $0.00012 $0.00904
Haiku 4.5 $0.00006 $0.00452

Measured 9d ago against content hash 85584ebb5edd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

performance-review-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

03-human-resources/performance-review-assistant/SKILL.md · 543 lines

How it starts

The opening of the file, as written. The whole thing — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Review Assistant

Overview

This skill helps managers and HR professionals conduct effective performance reviews with constructive, specific, and actionable feedback. It provides frameworks for writing compelling performance narratives, gathering 360 feedback, creating development plans, building performance improvement plans (PIPs) when needed, and conducting conversations that strengthen employee performance and engagement.

When to Use This Skill

  • Conducting annual performance reviews
  • Writing manager feedback on employee performance
  • Creating employee self-assessments
  • Gathering and synthesizing peer/360 feedback
  • Creating performance improvement plans (PIPs)
  • Writing development and growth plans
  • Preparing for performance review conversations
  • Documenting performance issues
  • Creating succession or promotion readiness assessments
  • Handling corrective action and termination documentation

Key Components

1. Performance Review Framework

360-Degree Feedback Approach:

  • Manager assessment (primary perspective)
  • Self-assessment (employee perspective)
  • Peer/colleague feedback (3-5 peers)
  • Cross-functional feedback (if applicable)
  • Direct report feedback (if manager role)
  • Customer/stakeholder feedback (if relevant)

Review Dimensions:

  • Performance on Core Responsibilities: How well did they do their job?
  • Competency Development: Did they grow in required skills?
  • Values & Culture Alignment: Do they embody company values?
  • Collaboration & Teamwork: How effective are they with others?
  • Leadership (if applicable): Do they develop others and drive change?
  • Impact & Results: What measurable outcomes did they achieve?
  • Growth & Learning: Did they learn, develop, and adapt?

2. Rating Scale & Performance Levels

Typical 5-Point Rating System:

1 - Below Expectations / Does Not Meet Standards:

  • Consistently misses key responsibilities
  • Performance is significantly below job requirements
  • Requires immediate improvement or performance plan
  • Frequency: Rare (0-5% of workforce)

Read the full file on GitHub · 543 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 543 lines · 58 tokens per session scan A 85584ebb5edd

Subscribe to this mod's changes

performance-review-assistant is a skill published in the GitHub repository w95/awesome-claude-corporate-skills (198 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 4,518 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.