New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audit Performance

by dzhng in dzhng/skills

Audit and prioritize performance work through bounded-work and forward-progress checks.

MITAuto-check passed

Install Audit Performance

skills CLI
$ npx skills add dzhng/skills --skill audit-performance -a claude-code

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

GitHub CLI
$ gh skill install dzhng/skills audit-performance --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/dzhng/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/engineering/audit-performance .claude/skills/audit-performance && 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
audit-performance
GitHub stars
1k
Token cost
~1.3k tokens
SKILL.md length
718 words
Files
1
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Audit and prioritize performance work through bounded-work and forward-progress checks.

  • Works in 6 steps: Trace hot paths. Find recurring syncs,… → Compute the amplification. State the… → Check forward progress. For every retry,… → …
  • Asked to find performance issues
  • SKILL.md covers Workflow, Priority Policy, Guardrails and Done
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Audit Performance is an agent skill from dzhng/skills. Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other… The licence is MIT.

When your agent uses it

  • Asked to find performance issues
  • Investigate freezes/500s/OOMs
  • Polling for no-progress loops
  • Rank a performance backlog

Example prompts

  • “/audit-performance”

Workflow steps

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

  1. Trace hot paths. Find recurring syncs, polls, streams, retries, queues, scheduled jobs,
  2. Compute the amplification. State the trigger and worst-case work in concrete units: rows,
  3. Check forward progress. For every retry, fixed-prefix batch, cutoff, or transitional poll,
  4. Falsify severity. Inspect existing caps, indexes, backoff, deadlines, healing owners, and
  5. Record before fixing. If the project keeps a performance ledger, append every supported
  6. Prioritize with the policy below. If implementation is authorized, invoke the project's

What it can do on your machine

Read from SKILL.md and the folder at commit d513228. 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

Audit Performance loads about 1.3k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 718 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 dzhng/skills at commit d513228, republished under its MIT licence (© dzhng). 718 words, ~1,313 tokens.

Download SKILL.mdSave it as .claude/skills/audit-performance/SKILL.md (or your agent's skills folder).
name
audit-performance
description
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes.

Audit Performance

Find work that grows without a useful bound or repeats without progress. Produce an evidence-backed ledger or report, then prefer the smallest fix that preserves recovery.

Workflow

  1. Trace hot paths. Find recurring syncs, polls, streams, retries, queues, scheduled jobs, filesystem walks, and request-time reads. Follow each through its production caller; ignore test-only paths.
  2. Compute the amplification. State the trigger and worst-case work in concrete units: rows, queries, pages, entries, bytes, jobs, retries, or full-file rewrites. Distinguish a bounded large constant from work that grows with history, tenants, paths, or outage duration.
  3. Check forward progress. For every retry, fixed-prefix batch, cutoff, or transitional poll, identify what changes before the next attempt. If nothing must change, it can loop or starve forever. Check that partial fixes do not merely delay the same work.
  4. Falsify severity. Inspect existing caps, indexes, backoff, deadlines, healing owners, and caller frequency. Dismiss findings already bounded cheaply enough or continuously healing.
  5. Record before fixing. If the project keeps a performance ledger, append every supported finding and important dismissal using its existing convention. Otherwise return a compact report. Include priority, trigger, impact, current owner, acceptance seam, and evidence.
  6. Prioritize with the policy below. If implementation is authorized, invoke the project's test-writing workflow and prove the old behavior red at the outermost practical seam. Fix, review, and update the ledger or report with verification evidence.

Priority Policy

Rank highest when the issue can cause a user-visible freeze or error, memory/disk growth, blocked request processing, data loss, fleet-wide amplification, or a poison item that prevents later work.

Prefer low-risk fixes that bound existing work: stream pagewise, honor backpressure, coalesce schedules, move poison rows aside, skip proven no-ops, or make one exhaustive search end in a terminal verdict. A safety cap is a pathology guard, not a normal product limit: set it above legitimate large workloads, emit actionable telemetry when reached, and define what happens next.

Do not prioritize by scary-looking counts alone:

  • Polling may continue forever when the polled state has a real recovery owner and can eventually change. Fix states that can never heal, not timers that are merely long-lived.
  • Cheap bounded database work is acceptable without production evidence. Do not build a projection, cache, cursor state machine, or alternate read model just to reduce a modest fixed query count.
  • Do not optimize information away when it may soon support product UI or behavior.
Show full SKILL.md (316 more words)Show less

Guardrails

  • Preserve healing. A cache or no-op shortcut must retain cheap recovery signals and fall back to ordinary reconciliation on drift, uncertainty, restart, or prior failure.
  • A recovery scan must either finish or persist forward progress. For a local, prunable namespace, prefer one complete pass with a ceiling high enough to indicate pathology rather than an ordinary large project. For a legitimately huge namespace, persist a cursor and resume after it. Finding the target updates identity; an exhaustive miss or abnormal ceiling produces the domain's terminal verdict. Never restart the same partial prefix forever.
  • Separate retryable failures from terminal ones. A permanent rejection must not sit at a queue head or fixed prefix forever.
  • Bound both sides of a transport and every durable/in-memory queue. State the overflow behavior; never silently drop accepted durable data.
  • Judge a cache, an index or a delta protocol by its worst edit, not its quiet average: an insertion into a long retained collection, a change far from the active view, a move, a deletion. Assert the bounded work alongside the exact result.
  • Check that a measured workload does what it claims before trusting its numbers: that the forces meet, the route is travelled, the failure arm runs. Measure the failure arm too.
  • Isolate a cost measurement from everything else running in the process.
  • Match compatibility work to the product lifecycle. In prelaunch code, prefer direct changes and add no legacy branches or migrations unless real persisted data requires them.
  • Every limit introduced or changed must have an observable log or metric with the limit kind, configured bound, affected owner, and overload outcome.

Done

The audit is complete only when every finding has a production trigger, quantified amplification, priority rationale, acceptance seam, and recorded disposition; every dismissed candidate says which bound or healing mechanism makes it acceptable. An implementation is complete only when its red/green proof shows bounded work and continued recovery.

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

Files

Just SKILL.md in skills/engineering/audit-performance of dzhng/skills.

Open the folder on GitHubat commit d513228

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in dzhng/skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Audit Performance 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.

Audit Performance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Performance this skilldzhng/skills1k—~1.3kAutomated safety check: PassMIT
Impediment Prioritizationgithub/awesome-copilot40k1 repos~2.3kAutomated safety check: PassMIT
Prioritize Assumptionsphuryn/pm-skills27k—~571Automated safety check: PassMIT
Prioritize Featuresphuryn/pm-skills27k—~623Automated safety check: PassMIT
Prioritization Frameworksphuryn/pm-skills27k—~1.1kAutomated safety check: PassMIT
Performing Cve Prioritization With Kev Catalogmukul975/Anthropic-Cybersecurity-Skills34k—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • Impediment Prioritization

    github/awesome-copilot

    Official

    Ranks any list of impediments and their countermeasures using a value-stream scoring model (ROI, Cost to Implement, Ease of Deployment, Risk Factor) and a fixed prioritization formula.

    40k GitHub starsUsed in 1 repo~2.3k tokens
    Product & Project ManagementAuto-check passed

  • Prioritize Assumptions

    phuryn/pm-skills

    Prioritize assumptions using an Impact × Risk matrix and suggest experiments for each.

    27k GitHub stars~571 tokensUpdated 24 days ago
    Product & Project ManagementAuto-check passed

  • Prioritize Features

    phuryn/pm-skills

    Prioritize a backlog of feature ideas based on impact, effort, risk, and strategic alignment with top 5 recommendations.

    27k GitHub stars~623 tokensUpdated 24 days ago
    Product & Project ManagementAuto-check passed

  • Prioritization Frameworks

    phuryn/pm-skills

    Reference guide to 9 prioritization frameworks with formulas, when-to-use guidance, and templates — RICE, ICE, Kano, MoSCoW, Opportunity Score, and more.

    27k GitHub stars~1.1k tokensUpdated 24 days ago
    Product & Project ManagementAuto-check passed

  • Performing Cve Prioritization With Kev Catalog

    mukul975/Anthropic-Cybersecurity-Skills

    Fetch and parse the CISA Known Exploited Vulnerabilities (KEV) catalog, enrich it with EPSS scores and CVSS metrics, and build a multi-factor prioritization engine and report that ranks CVE…

    34k GitHub stars~2.6k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Progressive Jpeg

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Use progressive JPEG encoding.

    74k GitHub stars~426 tokensUpdated 2 days ago
    Auto-check passed

More from dzhng/skills

All 27 skills in this repo

  • Compare Screenshots

    dzhng/skills

    Compare screenshots against the intended design, distinguishing approved references from historical baselines.

    1k GitHub stars~2.6k tokensUpdated 3 days ago
    Auto-check passed

  • Claude

    dzhng/skills

    Use Claude Code as an independent claude -p subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude.

    1k GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Refactor Clean

    dzhng/skills

    Refactor cleanly instead of layering sediment. An agent skill from dzhng/skills.

    1k GitHub stars~3.1k tokensUpdated 3 days ago
    Auto-check passed

  • Write Skills

    dzhng/skills

    Create or revise agent skills. An agent skill from dzhng/skills.

    1k GitHub stars~2.7k tokensUpdated 3 days ago
    Auto-check passed

  • Codex

    dzhng/skills

    Use the local Codex CLI as an independent second agent. An agent skill from dzhng/skills.

    1k GitHub stars~2.4k tokensUpdated 3 days ago
    Auto-check: warnings

  • Implement Spec With Codex

    dzhng/skills

    Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review.

    1k GitHub starsUsed in 1 repo~543 tokens
    Auto-check passed

Questions about Audit Performance

What does Audit Performance do?

Audit and prioritize performance work through bounded-work and forward-progress checks. Audit Performance is an agent skill from dzhng/skills. Audit and prioritize performance work through bounded-work and forward-progress checks.

When should I use Audit Performance?

Audit Performance fits situations like: asked to find performance issues; investigate freezes/500s/OOMs; polling for no-progress loops; rank a performance backlog.

How do I install Audit Performance in Claude Code?

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

How do I install Audit Performance in Codex?

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

Can I use Audit Performance 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 dzhng/skills --skill audit-performance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-performance, .gemini/skills/audit-performance, .github/skills/audit-performance and .opencode/skills/audit-performance in your project.

What does Audit Performance need to run?

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

Does Audit Performance 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 Audit Performance 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 Audit Performance use?

Audit Performance 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 Audit Performance use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audit Performance?

Skills that share tags, products or a category with Audit Performance: Impediment Prioritization (github/awesome-copilot, 40k stars), Prioritize Assumptions (phuryn/pm-skills, 27k stars), Prioritize Features (phuryn/pm-skills, 27k stars) and Prioritization Frameworks (phuryn/pm-skills, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Performance?

dzhng (a GitHub user) maintains it in dzhng/skills, which has 1,016 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 5, 2026.

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