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

Perf Change

by mattias800 in mattias800/prosper

Make, measure and land a prosper performance change - a switch for the A/B, a same-binary A/B on reference workloads, and a recorded verdict either way.

No licenceAuto-check passed

Install Perf Change

skills CLI
$ npx skills add mattias800/prosper --skill perf-change -a claude-code

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

GitHub CLI
$ gh skill install mattias800/prosper perf-change --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/mattias800/prosper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/perf-change .claude/skills/perf-change && 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
perf-change
GitHub stars
189
Token cost
~923 tokens
SKILL.md length
475 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
None found

At a glance

Make, measure and land a prosper performance change - a switch for the A/B, a same-binary A/B on reference workloads, and a recorded verdict either way.

  • Works in 8 steps: Read first. CLAUDE.md § Architecture and… → Make the change switchable for the A/B… → Reference workloads — one change is… → …
  • Calls python3

What it does

Perf Change is an agent skill from mattias800/prosper. Make, measure and land a prosper performance change - a switch for the A/B, a same-binary A/B on reference workloads, and a recorded verdict either way.

Its SKILL.md is about 920 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: A user-space PlayStation 5 to PC compatibility layer for Linux, Windows, and macOS.

Example prompts

  • “/perf-change”

Requirements

  • Python 3

Workflow steps

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

  1. Read first. CLAUDE.md § Architecture and performance ratchets (invariants P1-P6) and its
  2. Make the change switchable for the A/B (on by default once the A/B shows the win). One PROSPER_* switch selects the new path, so the
  3. Reference workloads — one change is measured on all three, not on the title it was written
  4. Measure the shipped path. prosper-app (built with -DPROSPER_APP=ON) with GPU present —
  5. Read before optimising. The [perf-alarm] summary lines at exit first. Then an F8 .prperf
  6. Compare honestly. prosper/tools/perf/compare_runs.py refuses mismatched runs but reads only
  7. Record the verdict either way. A win lands with its A/B in the PR. A loss or a null is a
  8. Run the ratchet in delta mode —

What it can do on your machine

Read from SKILL.md and the folder at commit 9818c8b. 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

    Shell commands in SKILL.md call:

    • python3

    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

Perf Change loads about 923 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 475 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~923

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 475 words (~923 tokens).

“Preserve task authorization, resource coordination and LOCAL.md; this skill grants no additional authority. It does not authorize GPU runs, claiming a GPU lease, pushing or merging — follow the task and prosper/docs/process/GAME_COMPAT_ORCHESTRATION.md for those.”

— opening of SKILL.md by mattias800
name
perf-change

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/perf-change of mattias800/prosper.

Open the folder on GitHubat commit 9818c8b

Compare with similar skills

Perf Change 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.

Perf Change compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Perf Change this skillmattias800/prosper189—~923Automated safety check: PassNone
Landingalirezarezvani/claude-skills28k—~3.8kAutomated safety check: PassMIT
Landing Page Conversion Auditgithub/awesome-copilot40k1 repos~1.8kAutomated safety check: PassMIT
SEO Aeo Landing Page Writersickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT
Ads LandingAgriciDaniel/claude-ads9.9k—~612Automated safety check: PassMIT
Perf ComparisonClickHouse/ClickHouse50k—~3.9kAutomated safety check: NotesApache-2.0

Similar skills

  • Landing

    alirezarezvani/claude-skills

    Generates a premium single-page HTML landing page with 3D CSS animations, GSAP scroll effects, and mouse-parallax depth.

    28k GitHub stars~3.8k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed

  • Landing Page Conversion Audit

    github/awesome-copilot

    Official

    Audit a landing page, sales page or checkout page for conversion leaks and return a fix list ordered by expected revenue impact.

    40k GitHub starsUsed in 1 repo~1.8k tokens
    Frontend & DesignAuto-check passed

  • SEO Aeo Landing Page Writer

    sickn33/agentic-awesome-skills

    Writes or improves conversion-focused landing pages for products, services, and offers with practical SEO and AEO structure.

    47k GitHub starsUsed in 1 repo~1.5k tokens
    Frontend & DesignAuto-check passed

  • Ads Landing

    AgriciDaniel/claude-ads

    Audit paid-ad landing pages for message match, mobile experience, performance, accessibility, trust, forms, consent, tracking, security, and conversion friction.

    9.9k GitHub stars~612 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed

  • Perf Comparison

    ClickHouse/ClickHouse

    Evaluate ClickHouse performance test results from existing CI/dashboard data or local perf.py runs.

    50k GitHub stars~3.9k tokensUpdated today
    DatabasesAuto-check: notes

  • Measure Before You Fix

    garrytan/gbrain

    Before fixing a slow/stale/timeout alert, measure the step yourself.

    31k GitHub stars~2.5k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

More from mattias800/prosper

  • Implement Hle Function

    mattias800/prosper

    Implement or fix a reimplemented Sony library function (HLE) in prosper, test-first.

    189 GitHub stars~563 tokensUpdated today
    Auto-check passed

  • Start Task

    mattias800/prosper

    Prepare an authorized prosper task using current instructions, issue ownership, an own worktree, and relevant verification.

    189 GitHub stars~661 tokensUpdated today
    Auto-check passed

Questions about Perf Change

What does Perf Change do?

Make, measure and land a prosper performance change - a switch for the A/B, a same-binary A/B on reference workloads, and a recorded verdict either way. Perf Change is an agent skill from mattias800/prosper. Make, measure and land a prosper performance change - a switch for the A/B, a same-binary A/B on reference workloads, and a recorded verdict either way.

How do I install Perf Change in Claude Code?

Run `npx skills add mattias800/prosper --skill perf-change -a claude-code`. Or copy the skill folder (.claude/skills/perf-change in mattias800/prosper) into .claude/skills/perf-change in your project. Claude Code loads it when a task matches its description.

How do I install Perf Change in Codex?

Run `npx skills add mattias800/prosper --skill perf-change -a codex`. Or copy the skill folder (.claude/skills/perf-change in mattias800/prosper) into .agents/skills/perf-change in your project. Codex loads it when a task matches its description.

Can I use Perf Change 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 mattias800/prosper --skill perf-change -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/perf-change, .gemini/skills/perf-change, .github/skills/perf-change and .opencode/skills/perf-change in your project.

What does Perf Change need to run?

Going by SKILL.md and its folder, Perf Change needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Perf Change 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 Perf Change 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 Perf Change use?

No licence was found for Perf Change or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Perf Change use?

About 923 tokens (SKILL.md is roughly 3.7k 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 Perf Change?

Skills that share tags, products or a category with Perf Change: Landing (alirezarezvani/claude-skills, 28k stars), Landing Page Conversion Audit (github/awesome-copilot, 40k stars), SEO Aeo Landing Page Writer (sickn33/agentic-awesome-skills, 47k stars) and Ads Landing (AgriciDaniel/claude-ads, 9.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Perf Change?

mattias800 (a GitHub user) maintains it in mattias800/prosper, which has 189 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 11, 2026.

Source: mattias800/prosper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.