# Self Review

> Write a performance self-review that's specific, evidenced, and balanced. Use when asked to write a self-review, self-assessment, or self-evaluation for a performance cycle. Produces a complete self-review — accomplishments mapped to impact and competencies, growth areas owned honestly, and a forward-looking development plan, in the voice of the person being reviewed.

- **Type:** Skill
- **Install:** `agentstack add skill-mohitagw15856-pm-claude-skills-self-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mohitagw15856](https://agentstack.voostack.com/s/mohitagw15856)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mohitagw15856](https://github.com/mohitagw15856)
- **Source:** https://github.com/mohitagw15856/pm-claude-skills/tree/main/plugins/pm-career/skills/self-review
- **Website:** https://mohitagw15856.github.io/pm-claude-skills/

## Install

```sh
agentstack add skill-mohitagw15856-pm-claude-skills-self-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Self-Review Skill

A self-review is your one chance to frame your own year before someone else does. Done badly it's a
vague list of activities; done well it's an evidenced narrative that maps your work to the competencies
you're measured on, owns growth honestly, and sets up the next level. This skill writes that — pulling
straight from a [`brag-doc`](../brag-doc/SKILL.md) if you have one.

## Required Inputs

Ask for these only if they aren't already provided:

- **Your role, level, and the review period.**
- **Accomplishments** — your wins with impact/metrics (or point to a brag doc).
- **The competency framework / rating dimensions** you're assessed on (if any).
- **Growth areas** — where you fell short or want to develop (be honest; reviewers trust self-awareness).
- **Goals** for the next period.

## Output Format

### Self-Review — [name], [role], [period]

**1. Summary** — 3–4 sentences: the headline of your period and the through-line. Lead with impact.

**2. Key accomplishments** — your top 3–6, each as **outcome → your contribution → evidence → which competency it demonstrates**. Quantify; tie to team/company goals.

**3. Strengths** — the 2–3 competencies you most demonstrated, with the proof.

**4. Growth areas** — 1–3, owned plainly: what was hard, what you learned, what you're changing. This section *builds* credibility when it's specific and non-defensive (not "I work too hard").

**5. Goals & development plan** — what you'll focus on next period and the support you need.

**6. Rating rationale** *(if self-rating)* — the rating you'd give and the evidence for it, calibrated to the framework — not inflated, not falsely modest.

## Quality Checks

- [ ] Accomplishments are quantified and tied to the competency framework / company goals
- [ ] Each claim is backed by specific evidence, not adjectives
- [ ] Growth areas are genuine and specific (not humble-brags), with what you're doing about them
- [ ] The narrative has a through-line, not just a list
- [ ] A self-rating (if used) is calibrated to the rubric with evidence — defensible, not aspirational

## Anti-Patterns

- [ ] Do not list activities — map every accomplishment to an outcome and a competency
- [ ] Do not disguise a strength as a weakness ("too detail-oriented") — it reads as evasive; name a real growth area
- [ ] Do not claim team wins as solo, or undersell your role out of modesty — be precise about your contribution
- [ ] Do not inflate the self-rating beyond what the evidence supports — it costs credibility in calibration
- [ ] Do not write in vague superlatives — "drove significant impact" means nothing without the number

## Based On

Competency-based performance-review practice — evidence-mapped accomplishments and calibrated self-assessment.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mohitagw15856](https://github.com/mohitagw15856)
- **Source:** [mohitagw15856/pm-claude-skills](https://github.com/mohitagw15856/pm-claude-skills)
- **License:** MIT
- **Homepage:** https://mohitagw15856.github.io/pm-claude-skills/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mohitagw15856-pm-claude-skills-self-review
- Seller: https://agentstack.voostack.com/s/mohitagw15856
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.