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

Peon Ping Sound Reroll

by PeonPing in PeonPing/peon-ping

Internal skill that rewrites and re-renders sound prompts in a draft PeonPing pack to follow a reroll caption, then records the change in a log.

MITAuto-check passedMedia & Creative

Install Peon Ping Sound Reroll

skills CLI
$ npx skills add PeonPing/peon-ping --skill peon-ping-remix -a claude-code

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

GitHub CLI
$ gh skill install PeonPing/peon-ping peon-ping-remix --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/PeonPing/peon-ping.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/peon-ping-remix .claude/skills/peon-ping-remix && 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
peon-ping-remix
GitHub stars
5.1k
Token cost
~910 tokens
SKILL.md length
443 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Internal skill that rewrites and re-renders sound prompts in a draft PeonPing pack to follow a reroll caption, then records the change in a log.

  • Works in 7 steps: Read the job JSON at the path you were… → Read /openpeon.json and /prompts.json. If → Determine the target sound files: scope… → …
  • Running as part of the peon eval reroll flow for a draft sound pack
  • SKILL.md covers If invoked without a job-file…, Procedure and Hard rules
  • Calls python3

What it does

This skill is meant to be started only by the peon eval server, which hands it a reroll job file. If a person runs it without a job path, it does nothing except say that the skill runs automatically and that they should use the `peon eval` command with the pack name instead. It works only inside the job's draft directory, installs nothing and commits nothing.

With a job, it reads the scope, category, index, caption and draft directory, then loads `openpeon.json` and `prompts.json`, failing clearly if the prompts are missing. A scope of sound targets one file and a scope of pack targets every file. For each target it writes a new render input that treats the caption as a correction rather than a reset, rewriting `prompt` for sound-effect entries or `text` for speech entries while keeping the voice. Renders go through `scripts/pack-render.py`, the run stops on any failure, and on success the prompts and `eval-log.json` are updated.

When your agent uses it

  • Running as part of the peon eval reroll flow for a draft sound pack
  • Regenerating one sound in a pack to match a short correction caption
  • Rerolling every sound in a draft pack with a new direction

Example prompts

  • “Use the peon-ping-remix skill to execute the reroll job at ./drafts/orc-pack/jobs/reroll-sound.json.”
  • “Reroll the second warning sound with the caption: softer and less harsh.”
  • “Reroll the whole draft pack with the caption: more cheerful.”

Requirements

  • A PeonPing install with scripts/pack-render.py
  • Python 3 to run the renderer
  • A draft pack folder containing openpeon.json and prompts.json

Workflow steps

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

  1. Read the job JSON at the path you were given: scope ("sound" or
  2. Read /openpeon.json and /prompts.json. If
  3. Determine the target sound files: scope "sound" → the one file at
  4. For each target, author a NEW render input honoring the caption
  5. Render each target: write the new input as a job file **under
  6. After ALL targets render successfully: update prompts.json with the new
  7. Print a one-line summary per rendered sound. Exit 0.

What it can do on your machine

Read from SKILL.md and the folder at commit de4ada7. 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

Peon Ping Sound Reroll loads about 910 tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 443 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~910

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 PeonPing/peon-ping at commit de4ada7, republished under its MIT licence (© PeonPing). 443 words, ~910 tokens.

Download SKILL.mdSave it as .claude/skills/peon-ping-remix/SKILL.md (or your agent's skills folder).
name
peon-ping-remix
description
Internal — invoked headlessly by the peon eval server; humans should run `peon eval <pack>` instead. Execute one PeonPing reroll job — invoked headlessly by the peon eval server as: "Use the peon-ping-remix skill to execute the reroll job at <path>". Reads the job JSON (scope, category, index, caption), rewrites the affected sound prompt(s) to honor the caption, re-renders via scripts/pack-render.py, and logs the change to eval-log.json.

peon-ping-remix

You are executing ONE reroll job for a draft PeonPing pack. Work only inside the job's draft_dir. Do not touch any other directory, do not install anything, do not commit anything.

If invoked without a job-file path

This skill is internal: it is only ever invoked headlessly by the peon eval server with a job-file path. If you were invoked WITHOUT one (a human ran this directly), do nothing except tell them this skill runs automatically from the eval server and that they should run peon eval <pack> instead. Do not touch any files. Exit.

Procedure

  1. Read the job JSON at the path you were given: scope ("sound" or "pack"), category, index, caption, draft_dir.
  2. Read <draft_dir>/openpeon.json and <draft_dir>/prompts.json. If prompts.json is missing, fail with a clear message — you cannot reroll without the current prompts.
  3. Determine the target sound files: scope "sound" → the one file at categories[category].sounds[index].file; scope "pack" → every file in every category.
  4. For each target, author a NEW render input honoring the caption:
    • Keep the pack's established aesthetic (read the other prompts for context). The caption is a correction, not a reset: "too harsh, want softer" means adjust intensity, keep the instrument palette unless the caption says otherwise.
    • sfx entries: rewrite prompt. tts entries: rewrite text (keep voice_id — never change a pack's voice in a reroll).
    • If the caption is empty, produce a fresh variation of the same idea.
  5. Render each target: write the new input as a job file under <draft_dir>/jobs/ (e.g. <draft_dir>/jobs/render-job-<category>_<index>.json — approve prunes everything under jobs/, so a render input left at the draft root would ship as junk in the approved pack) and run python3 <peon-ping>/scripts/pack-render.py --job <file> with out set to the target WAV path (overwrite in place). The renderer exits nonzero on silent/failed renders — if it fails, STOP and exit nonzero yourself with its stderr; do not half-update the log. (Resolve <peon-ping> as the scripts directory next to the running peon install, in order: $PEON_DIR/scripts when set, else ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/peon-ping/scripts, else the repo checkout you were invoked from.)
  6. After ALL targets render successfully: update prompts.json with the new inputs, and append one entry per rendered sound to <draft_dir>/eval-log.json (create as [] if missing): {"ts": "<ISO8601>", "scope", "category", "index", "caption", "old_prompt", "new_prompt", "file"}.
  7. Print a one-line summary per rendered sound. Exit 0.
Show full SKILL.md (59 more words)Show less

Hard rules

  • NEVER write outside draft_dir.
  • NEVER print or log the ElevenLabs key.
  • A failed render leaves the previous WAV in place — pack-render.py renders into a same-directory temp file and only replaces the out path (atomic os.replace) on a successful, non-silent render; do not delete a WAV before rendering.
  • Captions are the user's judgment. Honor them literally before creatively.

© PeonPing, 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/peon-ping-remix of PeonPing/peon-ping.

Open the folder on GitHubat commit de4ada7

Compare with similar skills

Peon Ping Sound Reroll 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.

Peon Ping Sound Reroll compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Peon Ping Sound Reroll this skillPeonPing/peon-ping5.1k—~910Automated safety check: PassMIT
HyperFrames Media Useheygen-com/hyperframes59k—~2.4kAutomated safety check: PassApache-2.0
Musictadaspetra/loop2962 repos~827Automated safety check: PassMIT
ElevenLabs Voiceover Generatordigitalsamba/claude-code-video-toolkit2.2k1 repos~2.7kAutomated safety check: NotesMIT
Sound Effectstadaspetra/loop2962 repos~1.1kAutomated safety check: PassMIT
Hyperframes Mediachmonitor/chmonitor2991 repos~2.8kAutomated safety check: NotesGPL-3.0

Similar skills

  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    59k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed

  • Music

    tadaspetra/loop

    Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.

    296 GitHub starsUsed in 2 repos~827 tokens
    Media & CreativeAuto-check passed

  • ElevenLabs Voiceover Generator

    digitalsamba/claude-code-video-toolkit

    Generates narration, sound effects and cloned voices through the ElevenLabs API, with model and setting choices tuned to the content's style.

    2.2k GitHub starsUsed in 1 repo~2.7k tokens
    Media & CreativeAuto-check: notes

  • Sound Effects

    tadaspetra/loop

    Generate sound effects from text descriptions using ElevenLabs.

    296 GitHub starsUsed in 2 repos~1.1k tokens
    Media & CreativeAuto-check passed

  • Hyperframes Media

    chmonitor/chmonitor

    Audio and media assets for HyperFrames compositions, produced by one shared audio engine (scripts/audio.mjs) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound…

    299 GitHub starsUsed in 1 repo~2.8k tokens
    Media & CreativeAuto-check: notes

  • Qiaomu Cut

    joeseesun/qiaomu-cut-skill

    把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频：介绍…

    372 GitHub stars~6.8k tokensUpdated 11 days ago
    Media & CreativeAuto-check: notes

More from PeonPing/peon-ping

  • Peon-Ping Settings Editor

    PeonPing/peon-ping

    Edits the peon-ping config file to change volume, sound packs, pack rotation, sound categories and notification options, then confirms the change.

    5.1k GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed

  • Peon-Ping Session Rename

    PeonPing/peon-ping

    Gives the current coding session a custom name that appears in peon-ping desktop notification titles and the terminal tab title, or resets it to automatic.

    5.1k GitHub stars~539 tokensUpdated 3 days ago
    Auto-check passed

  • Peon Ping Voice Pack Switcher

    PeonPing/peon-ping

    Switches which character voice pack (GLaDOS, Peon, Kerrigan and others) plays for the current chat session in Peon Ping.

    5.1k GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed

  • Peon Trainer Rep Logger

    PeonPing/peon-ping

    Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups"…

    5.1k GitHub stars~286 tokensUpdated 3 days ago
    Auto-check passed

  • Peon-Ping Sound Toggle

    PeonPing/peon-ping

    Mutes or unmutes peon-ping sound notifications during an agent session with one command, and explains which settings the toggle also silences.

    5.1k GitHub stars~427 tokensUpdated 3 days ago
    Auto-check passed

  • PeonPing Pack Creator

    PeonPing/peon-ping

    Drafts a new PeonPing notification sound pack across seven event categories for a given name, flavor and vibe, when called headlessly by peon create.

    5.1k GitHub stars~1.7k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Peon Ping Sound Reroll

What does Peon Ping Sound Reroll do?

Internal skill that rewrites and re-renders sound prompts in a draft PeonPing pack to follow a reroll caption, then records the change in a log. This skill is meant to be started only by the peon eval server, which hands it a reroll job file. If a person runs it without a job path, it does nothing except say that the skill runs automatically and that they should use the `peon eval` command with the pack name instead.

When should I use Peon Ping Sound Reroll?

Peon Ping Sound Reroll fits situations like: running as part of the peon eval reroll flow for a draft sound pack; regenerating one sound in a pack to match a short correction caption; rerolling every sound in a draft pack with a new direction.

How do I install Peon Ping Sound Reroll in Claude Code?

Run `npx skills add PeonPing/peon-ping --skill peon-ping-remix -a claude-code`. Or copy the skill folder (skills/peon-ping-remix in PeonPing/peon-ping) into .claude/skills/peon-ping-remix in your project. Claude Code loads it when a task matches its description.

How do I install Peon Ping Sound Reroll in Codex?

Run `npx skills add PeonPing/peon-ping --skill peon-ping-remix -a codex`. Or copy the skill folder (skills/peon-ping-remix in PeonPing/peon-ping) into .agents/skills/peon-ping-remix in your project. Codex loads it when a task matches its description.

Can I use Peon Ping Sound Reroll 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 PeonPing/peon-ping --skill peon-ping-remix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/peon-ping-remix, .gemini/skills/peon-ping-remix, .github/skills/peon-ping-remix and .opencode/skills/peon-ping-remix in your project.

What does Peon Ping Sound Reroll need to run?

Going by SKILL.md and its folder, Peon Ping Sound Reroll needs the command-line tools its instructions call (python3). Our summary lists: A PeonPing install with scripts/pack-render.py; Python 3 to run the renderer; A draft pack folder containing openpeon.json and prompts.json.

Does Peon Ping Sound Reroll 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 Peon Ping Sound Reroll 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 Peon Ping Sound Reroll use?

Peon Ping Sound Reroll 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 Peon Ping Sound Reroll use?

About 910 tokens (SKILL.md is roughly 3.6k 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 Peon Ping Sound Reroll?

Skills that share tags, products or a category with Peon Ping Sound Reroll: HyperFrames Media Use (heygen-com/hyperframes, 59k stars), Music (tadaspetra/loop, 296 stars), ElevenLabs Voiceover Generator (digitalsamba/claude-code-video-toolkit, 2.2k stars) and Sound Effects (tadaspetra/loop, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Peon Ping Sound Reroll?

PeonPing (a GitHub organization) maintains it in PeonPing/peon-ping, which has 5,068 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 6, 2026.

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