Agent skill

Performance Reviews

by manager-dot-dev in manager-dot-dev/manager-skills

Helps diagnose underperformance, structure a performance case, decide whether to put someone on a PIP or let them go, and think through your own manager review.

MITAuto-check passedBusiness, Finance & HR

Install Performance Reviews

skills CLI
$ npx skills add manager-dot-dev/manager-skills --skill performance-reviews -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install manager-dot-dev/manager-skills performance-reviews --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/performance-reviews .claude/skills/performance-reviews && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
performance-reviews
GitHub stars
114
Token cost
~2.8k tokens
SKILL.md length
1,574 words
Files
2 (incl. references)
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Helps diagnose underperformance, structure a performance case, decide whether to put someone on a PIP or let them go, and think through your own manager review.

  • Works in 3 steps: Read .agents/em-context.md if it exists… → If a person is mentioned, look for… → Use that context — only ask for…
  • The user says perf review
  • SKILL.md covers Before Starting, Response Style, How to Use This Skill and Default Response Shape, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Performance Reviews is an agent skill from manager-dot-dev/manager-skills. Helps diagnose underperformance, structure a performance case, decide whether to put someone on a PIP or let them go, and think through your own manager review. Use when the user says "perf review," "review cycle," "performance calibration," "write a review," "rating," "meets expectations," "performance improvement," "PIP," "promotion case," "end of year review," "mid-year review," "underperformer," "struggling employee," or "should I let them go." Do NOT use for delivering day-to-day feedback (use feedback) or…

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/sources.md`).

It sits in Business, Finance & HR, covering Performance reviews. The repository describes itself as: Skills for engineering managers. The licence is MIT.

When your agent uses it

  • The user says perf review
  • Performance calibration
  • Meets expectations
  • Performance improvement

Example prompts

  • “perf review,”
  • “review cycle,”
  • “performance calibration,”
  • “/performance-reviews”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Read .agents/em-context.md if it exists (for review cycle format, rating scale, etc.)
  2. If a person is mentioned, look for .agents/reports/[name].md — it will have their role, level, goals, current projects, and feedback history
  3. Use that context — only ask for information not already covered

What it can do on your machine

Read from SKILL.md and the folder at commit c47ebc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Performance Reviews loads about 2.8k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 147 tokens; SKILL.md has 1,574 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~147
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from manager-dot-dev/manager-skills at commit c47ebc7, republished under its MIT licence (© manager-dot-dev). 1,574 words, ~2,760 tokens.

Download SKILL.mdSave it as .claude/skills/performance-reviews/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
performance-reviews
description
Helps diagnose underperformance, structure a performance case, decide whether to put someone on a PIP or let them go, and think through your own manager review. Use when the user says "perf review," "review cycle," "performance calibration," "write a review," "rating," "meets expectations," "performance improvement," "PIP," "promotion case," "end of year review," "mid-year review," "underperformer," "struggling employee," or "should I let them go." Do NOT use for delivering day-to-day feedback (use feedback) or for evaluating a new hire candidate (use hiring).
metadata.version
2.1.2

Performance Reviews

Before Starting

Check for EM context first:

  1. Read .agents/em-context.md if it exists (for review cycle format, rating scale, etc.)
  2. If a person is mentioned, look for .agents/reports/[name].md — it will have their role, level, goals, current projects, and feedback history
  3. Use that context — only ask for information not already covered

If .agents/em-context.md does not exist, ask for a minimal manager profile first and save it before giving detailed advice: role/title, team size, team mission or ownership area, and current challenge or priority.

If a specific person is central to the conversation and .agents/reports/[name].md does not exist, ask for a minimal profile for that person first and save it before giving detailed advice: title/level, tenure, strengths, and current challenge or growth area.

If the conversation reveals durable new context later, update .agents/em-context.md or .agents/reports/[name].md automatically. Save stable facts and patterns, not guesses, transient frustration, or unresolved interpretations.

Response Style

Keep the first answer concise and useful. Do not dump the whole framework unless the user asks for depth.

Default to:

  • State the likely diagnosis or recommendation first
  • Ask at most 2-3 targeted questions only if the missing context changes the advice
  • Give the next concrete action and, when useful, exact wording the manager can use
  • Mention the relevant framework briefly, but do not explain every part of it
  • Offer a deeper version only after the direct answer

How to Use This Skill

Identify the situation first:

  • Someone on the team isn't performing — not sure what's wrong → Diagnosing Underperformance: Work Left to Right (start here)
  • You've diagnosed the problem — now need to address the behavior → 4-Stage Process for Addressing Persistent Behavior Problems
  • Wondering if you've been tolerating underperformance too long → Recognizing Underperformance Early
  • Seriously considering letting someone go → Making the Hard Call + When to Act
  • Writing or structuring your own manager review → The Meta Performance Review Question

Default Response Shape

When helping with performance, separate diagnosis from action:

  1. Performance read: behavior, impact, pattern, and severity.
  2. Root-cause hypothesis: resources, training, desire, fit, or ability.
  3. Evidence needed: examples, expectations, prior feedback, and business impact.
  4. Manager action: feedback, support plan, PIP, promotion case, or separation path.
  5. Wording: review language or conversation script.

Do not let empathy turn into vagueness. Be humane and specific at the same time.


Recognizing Underperformance Early

The most common trap: confusing improvement with potential. An engineer who goes from bad to mediocre is improving — but they may still be below the bar.

The key question isn't "are they getting better?" It's "are they at the level I need?"

Ray Dalio: "If someone who has been getting grades of 30s and 40s raised their scores to 50s for a few months, it would be accurate to say they are getting better — but they would still be woefully inadequate."

Why managers tolerate underperformers too long
  1. Emotional connection — you've invested in this person, you like them, you don't want to hurt them
  2. Sunk cost fallacy — you've spent months training them and don't want to start over

Both are real. Both lead to lying to yourself and settling for mediocrity.

How to stay objective
  • Set concrete expectations before problems start — 30/60/90 day goals, on-call readiness, project lead criteria. Without a clear bar, "improving" will always feel like enough.
  • Use the "would I hire today?" question — Not "am I better with or without them?" (always anchors on sunk cost). Instead: "Knowing what I know now, would I hire this person?" If no, that's your answer.
  • Set a checkpoint in advance — 30 days, 60 days, end of cycle. A forced decision point prevents indefinite deferral.
Staying humble

You will be wrong sometimes. A struggling engineer can turn into a standout with time, the right environment, or a role that fits them better. Frameworks are guides, not verdicts.


Making the Hard Call: Letting Someone Go

Deep inside, you usually know. When you start to genuinely consider firing someone, it's probably already overdue.

The relief test: Imagine the employee tells you they're quitting. Do you feel relieved — or upset? If relieved, that's your answer.

(The Netflix "keeper test" — would you fight to keep them? — is the stricter version. The relief test is more realistic for most teams.)

Why it's always hard

Usually it's one of three situations: you hired someone not suitable for the role; you didn't provide clear expectations or enough support; or the role changed and they no longer fit it. In all three cases, you share responsibility for the situation. That's why it should be hard — and why good managers struggle.

Don't confuse "they have potential" with "I can't make a hard decision." They're different things.

The price of waiting
  • The employee suffers — coming every day to a job where you're not doing well is exhausting
  • You suffer — trying to help someone thrive when you know deep down they won't is draining
  • The team suffers — working alongside underperformers is demotivating; when you finally act, the team almost always understands

I haven't yet encountered a manager who regretted a firing. Only ones who regretted waiting.

Before you act: do this first

To know you did everything right before letting someone go:

  1. Give feedback immediately — as soon as they step off track. Don't wait for it to accumulate.
  2. Be specific — give concrete examples of what went wrong and what better looks like
  3. Have them repeat it back — until what they say matches what you mean. People often think they understand expectations but don't.
  4. Write it down — a clear list of what needs to change, measurable, visible to both of you
  5. Be patient — changing behavior takes real work. It's often worth it.

Note: 50% of people on performance improvement plans become repeat offenders. Smart employees know how to rise to the occasion temporarily. Watch for the pattern.


Show full SKILL.md (610 more words)Show less

When to Act: The Fire Quickly Heuristic

A rough but useful signal: if you've thought seriously about firing someone even once, you should probably act sooner rather than later.

With genuinely strong employees, the thought doesn't arise. The fact that it arose at all is diagnostic.

This doesn't mean fire impulsively. It means: if you've crossed the threshold of "should I let this person go?" without acting on it, examine why you're waiting. The most common reason is discomfort — not evidence that the situation will resolve itself.


The Meta Performance Review Question

The most useful question for evaluating a manager's performance: "What would have been different if this person hadn't been here?"

This targets manager delta — not what the team shipped, but what the manager caused to happen that wouldn't have happened otherwise. Apply it to yourself: what is your contribution to outcomes that your team couldn't have produced without you?

Common contributions that count:

  • A hard conversation that shifted someone's trajectory
  • Hiring decisions that raised the bar
  • Removing a blocker nobody else could remove
  • Growing someone who was stuck

4-Stage Process for Addressing Persistent Behavior Problems

For an engineer who repeatedly shows a problematic pattern (constant complaining, missing commitments, interpersonal friction):

Stage 1 — Listen and understand. Do everything you can to understand what's behind the behavior. There is almost always some legitimate grievance underneath. Don't skip this — going straight to "stop doing X" ignores the signal.

Stage 2 — Address the root cause. Identify the 1–2 biggest underlying issues and address them in partnership with the person. This requires actually solving something, not just acknowledging it.

Stage 3 — Discuss the behavior itself. Once you've addressed the root cause, have an explicit conversation about how the behavior needs to change: what's acceptable, what isn't, and what the expectations are going forward.

Stage 4 — Let them go. If the behavior persists after stages 1–3, it's a choice, not a circumstance. Act.

The failure mode is skipping stages. Managers who haven't done stages 1–2 don't have standing to hold stage 3 conversations with credibility.


Diagnosing Underperformance: Work Left to Right

Before deciding "up or out," work through this spectrum in order. As you move right, ownership shifts from you to the employee:

  1. Resources — do they have what they need? Access, software, tooling, support. If not, that's 100% your problem. Fix it before drawing any conclusions about them.
  2. Training — do they have enough knowledge to do the job? This is shared responsibility: you ensure they have access to training; they own using it. Avoid the bottomless training trap — aim for sufficient, not exhaustive.
  3. Desire — do they actually want to do this work? The hardest conversation, with real personal stakes for them. If you've been clear about expectations from day one, and they still don't want to meet them, that's theirs to own. You can be their fan or their coach — you can't want it for them.
  4. Fit — are they in the right role for their strengths? Someone can be talented and still be wrong for this specific job.
  5. Ability — do they have the raw capability to reach the required level?

Most underperformance diagnoses jump straight to #3 or #5 without addressing #1 and #2. This is a mistake: it skips the manager's responsibility, burns trust, and produces a weak performance case.


Dive Deeper

If the user asks where a framework came from, wants to read the original article, or wants more context on any topic — read references/sources.md for the full list of source articles (with links) and books.


  • feedback — Immediate, specific feedback is the prerequisite for any of this
  • hiring — Setting concrete expectations starts at hire time

© manager-dot-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/performance-reviews of manager-dot-dev/manager-skills.

  • SKILL.md
  • references/sources.md

Open the folder on GitHubat commit c47ebc7

Compare with similar skills

Performance Reviews next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Performance Reviews compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Performance Reviews this skillmanager-dot-dev/manager-skills114—~2.8kAutomated safety check: PassMIT
Wp Performance Reviewelvismdev/claude-wordpress-skills2341 repos~4.5kAutomated safety check: PassMIT
Align Humanagentscope-ai/OpenJudge867—~3.1kAutomated safety check: PassApache-2.0
Performance ReportAffitor/affiliate-skills6981 repos~2.5kAutomated safety check: PassMIT
Run Mv Hoi Reconstructionnvidia-isaac/video_to_data847—~1.5kAutomated safety check: PassCustom licence
Company Analysiszhu1090093659/dsh-trading230—~4.2kAutomated safety check: PassCustom licence

Similar skills

  • Wp Performance Review

    elvismdev/claude-wordpress-skills

    WordPress performance code review and optimization analysis.

    234 GitHub starsUsed in 1 repo~4.5k tokens
    Business, Finance & HRAuto-check passed
  • Align Human

    agentscope-ai/OpenJudge

    A skill your agent uses when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic…

    867 GitHub stars~3.1k tokensUpdated 26 days ago
    Business, Finance & HRAuto-check passed
  • Performance Report

    Affitor/affiliate-skills

    Generate affiliate performance reports with KPIs and recommendations.

    698 GitHub starsUsed in 1 repo~2.5k tokens
    Business, Finance & HRAuto-check passed
  • Run Mv Hoi Reconstruction

    nvidia-isaac/video_to_data

    Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.

    847 GitHub stars~1.5k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Company Analysis

    zhu1090093659/dsh-trading

    A skill your agent uses when the user wants to analyze a listed company, stock, business, or investment target; challenge or revise an existing company report; compare A/H or primary-listing/ADR…

    230 GitHub stars~4.2k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed
  • Slurm Pipeline Manager

    CliMA/EnsembleKalmanProcesses.jl

    Scaffold and maintain a SLURM/HPC job-dependency tree for an EnsembleKalmanProcesses.jl (EKP) calibration pipeline.

    127 GitHub stars~3.4k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

More from manager-dot-dev/manager-skills

All 27 skills in this repo
  • Em Grid Scorer

    manager-dot-dev/manager-skills

    Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack.

    114 GitHub stars~5.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Em Context

    manager-dot-dev/manager-skills

    Foundation skill for engineering managers. An agent skill from manager-dot-dev/manager-skills.

    114 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check passed
  • 1on1s

    manager-dot-dev/manager-skills

    Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports.

    114 GitHub stars~3k tokensUpdated 5 mo ago
    Auto-check passed
  • Business Literacy

    manager-dot-dev/manager-skills

    Explains business financial terms and frameworks for engineering managers — produces term definitions (ARR, COGS, CAC, LTV, gross margin, burn rate, EBITDA, AARRR), translation formulas for making…

    114 GitHub stars~2.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Career Development

    manager-dot-dev/manager-skills

    Helps engineering managers support direct report growth — produces a stage-by-stage model of engineering impact (Circles of Influence), a framework for non-linear career planning (Tarzan Method)…

    114 GitHub stars~2.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Delegation

    manager-dot-dev/manager-skills

    Guides managers out of the bottleneck role — provides the Team Rep pattern, Epic Ownership model, Task-Relevant Maturity framework, kingdom ownership, and three-layer assignment strategy.

    114 GitHub stars~3.3k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Performance Reviews

What does Performance Reviews do?

Helps diagnose underperformance, structure a performance case, decide whether to put someone on a PIP or let them go, and think through your own manager review. Performance Reviews is an agent skill from manager-dot-dev/manager-skills. Helps diagnose underperformance, structure a performance case, decide whether to put someone on a PIP or let them go, and think through your own manager review.

When should I use Performance Reviews?

Performance Reviews fits situations like: the user says perf review; performance calibration; meets expectations; performance improvement.

How do I install Performance Reviews in Claude Code?

Run `npx skills add manager-dot-dev/manager-skills --skill performance-reviews -a claude-code`. Or copy the skill folder (skills/performance-reviews in manager-dot-dev/manager-skills) into .claude/skills/performance-reviews in your project. Claude Code loads it when a task matches its description.

How do I install Performance Reviews in Codex?

Run `npx skills add manager-dot-dev/manager-skills --skill performance-reviews -a codex`. Or copy the skill folder (skills/performance-reviews in manager-dot-dev/manager-skills) into .agents/skills/performance-reviews in your project. Codex loads it when a task matches its description.

Can I use Performance Reviews in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add manager-dot-dev/manager-skills --skill performance-reviews -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/performance-reviews, .gemini/skills/performance-reviews, .github/skills/performance-reviews and .opencode/skills/performance-reviews in your project.

What does Performance Reviews need to run?

SKILL.md names no scripts, command-line tools or credentials: Performance Reviews is instructions for the agent only.

Does Performance Reviews access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Performance Reviews safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Performance Reviews use?

Performance Reviews is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Performance Reviews use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 234 tokens, read only when the agent opens those files.

What are the alternatives to Performance Reviews?

Skills that share tags, products or a category with Performance Reviews: Wp Performance Review (elvismdev/claude-wordpress-skills, 234 stars), Align Human (agentscope-ai/OpenJudge, 867 stars), Performance Report (Affitor/affiliate-skills, 698 stars) and Run Mv Hoi Reconstruction (nvidia-isaac/video_to_data, 847 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Performance Reviews?

manager-dot-dev (a GitHub organization) maintains it in manager-dot-dev/manager-skills, which has 114 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on May 9, 2026.

Source: manager-dot-dev/manager-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.