Agent skill

Wait What

by egma-ai in egma-ai/egma

Stop. An agent skill from egma-ai/egma.

Custom licenceAuto-check passed

Install Wait What

skills CLI
$ npx skills add egma-ai/egma --skill wait-what -a claude-code

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

GitHub CLI
$ gh skill install egma-ai/egma wait-what --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/egma-ai/egma.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/wait-what .claude/skills/wait-what && 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
wait-what
GitHub stars
144
Used in
1 other repo
Token cost
~154 tokens
SKILL.md length
59 words
Files
2
Skills in repo
6
Repo updated
First seen
Licence
Custom licence

At a glance

Stop. An agent skill from egma-ai/egma.

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Wait What is an agent skill from egma-ai/egma. Stop. That last message did not land — re-pitch it.

Its SKILL.md is about 150 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: the first open-source platform for simulation testing, monitoring and self-improving voice agents.

Example prompts

  • “/wait-what”

What it can do on your machine

Read from SKILL.md and the folder at commit 6297cb0. 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

Wait What loads about 154 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 59 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~154

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 59 words (~154 tokens).

“Repository configuration overrides this skill's default planning paths. If a Planning root is defined, resolve CONTEXT.md, docs/adr/, docs/agents/, .scratch/, and .out-of-scope/ from that root. Skill-local paths remain unchanged.”

— opening of SKILL.md by egma-ai, Custom licence
name
wait-what
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .agents/skills/wait-what of egma-ai/egma.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 6297cb0

Used in 1 other repository

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

Compare with similar skills

Wait What 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.

Wait What compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wait What this skillegma-ai/egma1441 repos~154Automated safety check: PassCustom licence
Landingalirezarezvani/claude-skills28k—~3.8kAutomated safety check: PassMIT
Messages Opsaffaan-m/ECC276k1 repos~724Automated safety check: PassMIT
Ads LandingAgriciDaniel/claude-ads9.8k—~612Automated safety check: PassMIT
Land and Deploygarrytan/gstack136k—~18kAutomated safety check: NotesMIT
Channel Message Flowsopenclaw/openclaw392k—~306Automated safety check: PassMIT

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
  • Messages Ops

    affaan-m/ECC

    Evidence-first live messaging workflow for ECC. An agent skill from affaan-m/ECC.

    276k GitHub starsUsed in 1 repo~724 tokens
    Productivity & AutomationAuto-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.

    9.8k GitHub stars~612 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Land and Deploy

    garrytan/gstack

    Merges a pull request, waits for CI and the deploy, then verifies production health with canary checks, picking up where /ship leaves off.

    136k GitHub stars~18k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Channel Message Flows

    openclaw/openclaw

    A skill your agent uses when running QA Lab channel message flow evidence.

    392k GitHub stars~306 tokensUpdated today
    Auto-check passed
  • Commit Message Storyteller

    github/awesome-copilot

    Official

    Analyzes git diffs or staged changes and generates narrative commit messages that explain WHY a change was made, not just what changed — following Conventional Commits format.

    40k GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed

More from egma-ai/egma

  • Grill Me

    egma-ai/egma

    A relentless interview to sharpen a plan or design. An agent skill from egma-ai/egma.

    144 GitHub starsUsed in 40 repos~111 tokens
    Auto-check passed
  • Grill With Docs

    egma-ai/egma

    A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

    144 GitHub starsUsed in 35 repos~135 tokens
    Auto-check passed
  • Integrate Egma

    egma-ai/egma

    Integrate Egma into a repository containing voice agent code.

    144 GitHub stars~500 tokensUpdated 9 days ago
    Auto-check passed
  • Write Egma Tests

    egma-ai/egma

    Write or edit tests for a voice agent that can run on the Egma platform.

    144 GitHub stars~2.7k tokensUpdated 9 days ago
    Auto-check passed
  • Drive one ticketed effort through parallel implementation, independent review, serial integration, and one open pull request.

    144 GitHub stars~844 tokensUpdated 9 days ago
    Auto-check passed

Questions about Wait What

What does Wait What do?

Stop. An agent skill from egma-ai/egma. Wait What is an agent skill from egma-ai/egma. Stop.

How do I install Wait What in Claude Code?

Run `npx skills add egma-ai/egma --skill wait-what -a claude-code`. Or copy the skill folder (.agents/skills/wait-what in egma-ai/egma) into .claude/skills/wait-what in your project. Claude Code loads it when a task matches its description.

How do I install Wait What in Codex?

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

Can I use Wait What 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 egma-ai/egma --skill wait-what -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wait-what, .gemini/skills/wait-what, .github/skills/wait-what and .opencode/skills/wait-what in your project.

What does Wait What need to run?

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

Does Wait What 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 Wait What 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 Wait What use?

Wait What 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 Wait What use?

About 154 tokens (SKILL.md is roughly 616 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 Wait What?

Skills that share tags, products or a category with Wait What: Landing (alirezarezvani/claude-skills, 28k stars), Messages Ops (affaan-m/ECC, 276k stars), Ads Landing (AgriciDaniel/claude-ads, 9.8k stars) and Land and Deploy (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wait What?

egma-ai (a GitHub organization) maintains it in egma-ai/egma, which has 144 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 30, 2026.

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