Agent skill

Developing Change

by rapidaai in rapidaai/voice-ai

Implement an approved repository change with explicit ownership, minimal scope, test-first evidence, and scoped verification.

Custom licenceAuto-check passedAI & LLM Engineering

Install Developing Change

skills CLI
$ npx skills add rapidaai/voice-ai --skill developing-change -a claude-code

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

GitHub CLI
$ gh skill install rapidaai/voice-ai developing-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/rapidaai/voice-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/developing-change .claude/skills/developing-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
developing-change
GitHub stars
744
Token cost
~661 tokens
SKILL.md length
319 words
Files
3
Skills in repo
26
Repo updated
First seen
Licence
Custom licence

At a glance

Implement an approved repository change with explicit ownership, minimal scope, test-first evidence, and scoped verification.

  • Works in 6 steps: Add or update the focused test and… → Change the established owner with the… → Run the focused test. → …
  • Tasks that involve Speech recognition and synthesis
  • SKILL.md covers Mission, Preconditions, Ownership and Implementation loop, plus 4 more sections
  • Calls just

What it does

Developing Change is an agent skill from rapidaai/voice-ai. Implement an approved repository change with explicit ownership, minimal scope, test-first evidence, and scoped verification. Use after lifecycle routing and analysis have established the intended behavior and allowed paths.

Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `agents/openai.yaml` and `examples/sample.md`).

It sits in AI & LLM Engineering, covering Speech recognition and synthesis and Test-driven development. The repository describes itself as: Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel…

When your agent uses it

  • Tasks that involve Speech recognition and synthesis
  • Tasks that involve Test-driven development

Example prompts

  • “/developing-change”

Workflow steps

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

  1. Add or update the focused test and confirm it fails for the expected reason.
  2. Change the established owner with the smallest direct control flow.
  3. Run the focused test.
  4. Exercise the relevant fallback or failure path.
  5. Remove accidental complexity and unrelated edits.
  6. Continue only after the current increment is understood and green.

What it can do on your machine

Read from SKILL.md and the folder at commit 3c9caac. 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:

    • just

    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

Developing Change loads about 661 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 319 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~661

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 319 words (~661 tokens).

“Make the smallest complete change at the owning layer and leave a deterministic evidence trail for verification and review.”

— opening of SKILL.md by rapidaai, Custom licence
name
developing-change

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files in .codex/skills/developing-change of rapidaai/voice-ai.

  • SKILL.md
  • agents/openai.yaml
  • examples/sample.md

Open the folder on GitHubat commit 3c9caac

Compare with similar skills

Developing 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.

Developing Change compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Developing Change this skillrapidaai/voice-ai744—~661Automated safety check: PassCustom licence
Vibe To SpecFAIRY123456789/human-edge-agent-skills103—~997Automated safety check: PassMIT
Digital Health Clinical Asr SetupNVIDIA/skills3.5k—~4.5kAutomated safety check: NotesApache-2.0
Quick Fixdanielvm-git/bigpowers257—~1.2kAutomated safety check: PassMIT
TriageTalAter/annyang6.8k1 repos~810Automated safety check: NotesMIT
Yichen Asrmcncarl/yichen-skills4.3k—~780Automated safety check: PassCustom licence

Similar skills

  • Vibe To Spec

    FAIRY123456789/human-edge-agent-skills

    Convert messy voice input, imperfect speech recognition, half-formed product ideas, and iterative corrections into an implementation-ready software specification for Codex, Claude Code, Copilot…

    103 GitHub stars~997 tokensUpdated 8 days ago
    AI & LLM EngineeringAuto-check passed
  • Official

    Stage 1 of Clinical ASR Flywheel. An agent skill from NVIDIA/skills.

    3.5k GitHub stars~4.5k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Quick Fix

    danielvm-git/bigpowers

    Streamlined fast-path for trivial data-only fixes — no TDD, no branching ceremony.

    257 GitHub stars~1.2k tokensUpdated 16 days ago
    AI & LLM EngineeringAuto-check passed
  • Triage

    TalAter/annyang

    Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.

    6.8k GitHub starsUsed in 1 repo~810 tokens
    AI & LLM EngineeringAuto-check: notes
  • Yichen Asr

    mcncarl/yichen-skills

    逸尘自用的统一音视频转写入口,在 StepFun Step ASR 与火山引擎豆包 ASR 之间按输出需求、安全边界和可用状态路由。用于本地音频或视频的纯文本转写、时间戳、SRT 字幕、口播粗剪,以及转写前体检;用户明确指定服务商时不得静默切换。Use when a local audio or video file needs transcription and the correct…

    4.3k GitHub stars~780 tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed
  • Dingtalk Minutes

    DingTalk-Real-AI/dingtalk-workspace-cli

    钉钉 AI 听记。Use when 查询或修改听记摘要、完整逐字稿、关键词、标签、行动项、录音、上传、思维导图、发言人洞察、ASR 热词/识别词配置或分享权限。写文档走 dingtalk-doc;建待办走 dingtalk-todo;日程走 dingtalk-calendar。命令前缀:dws minutes。

    3.2k GitHub stars~2.3k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from rapidaai/voice-ai

All 26 skills in this repo
  • End Of Speech Integration

    rapidaai/voice-ai

    Add or modify end-of-speech integrations in assistant-api with strict separation from VAD internals.

    744 GitHub stars~877 tokensUpdated yesterday
    Auto-check passed
  • Local Setup And Run

    rapidaai/voice-ai

    Explain and validate local setup paths for this repository with Docker and without Docker.

    744 GitHub stars~595 tokensUpdated yesterday
    Auto-check passed
  • System Understanding

    rapidaai/voice-ai

    Build a code-grounded implementation plan before coding. An agent skill from rapidaai/voice-ai.

    744 GitHub stars~721 tokensUpdated yesterday
    Auto-check passed
  • Vad Integration

    rapidaai/voice-ai

    Add or modify VAD providers and tuning in assistant-api with strict separation from EOS internals.

    744 GitHub stars~758 tokensUpdated yesterday
    Auto-check passed
  • Local Setup And Run

    rapidaai/voice-ai

    Explain and validate local setup paths for this repo with Docker and without Docker.

    744 GitHub stars~683 tokensUpdated yesterday
    Auto-check passed
  • System Understanding

    rapidaai/voice-ai

    Build a code-grounded implementation plan before coding. An agent skill from rapidaai/voice-ai.

    744 GitHub stars~727 tokensUpdated yesterday
    Auto-check passed

Questions about Developing Change

What does Developing Change do?

Implement an approved repository change with explicit ownership, minimal scope, test-first evidence, and scoped verification. Developing Change is an agent skill from rapidaai/voice-ai. Implement an approved repository change with explicit ownership, minimal scope, test-first evidence, and scoped verification.

When should I use Developing Change?

Developing Change fits situations like: tasks that involve Speech recognition and synthesis; tasks that involve Test-driven development.

How do I install Developing Change in Claude Code?

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

How do I install Developing Change in Codex?

Run `npx skills add rapidaai/voice-ai --skill developing-change -a codex`. Or copy the skill folder (.codex/skills/developing-change in rapidaai/voice-ai) into .agents/skills/developing-change in your project. Codex loads it when a task matches its description.

Can I use Developing 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 rapidaai/voice-ai --skill developing-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/developing-change, .gemini/skills/developing-change, .github/skills/developing-change and .opencode/skills/developing-change in your project.

What does Developing Change need to run?

Going by SKILL.md and its folder, Developing Change needs the command-line tools its instructions call (just).

Does Developing 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 Developing 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 Developing Change use?

Developing Change has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Developing Change use?

About 661 tokens (SKILL.md is roughly 2.6k 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 Developing Change?

Skills that share tags, products or a category with Developing Change: Vibe To Spec (FAIRY123456789/human-edge-agent-skills, 103 stars), Digital Health Clinical Asr Setup (NVIDIA/skills, 3.5k stars), Quick Fix (danielvm-git/bigpowers, 257 stars) and Triage (TalAter/annyang, 6.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Developing Change?

rapidaai (a GitHub organization) maintains it in rapidaai/voice-ai, which has 744 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 6, 2026.

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