Monitoring Capture Service
PostHog/posthog
Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production.
Magic Mouth is trigger → message. An agent skill from Hmbown/Wizards-of-the-Ghosts.
Install Magic Mouth
$ npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Hmbown/Wizards-of-the-Ghosts magic-mouth --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git skills-src && mkdir -p .claude/skills && cp -r skills-src/generated/openclaw/magic-mouth .claude/skills/magic-mouth && rm -rf skills-srcUse ~/.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/
Install the "magic-mouth" agent skill from https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/openclaw/magic-mouth into .claude/skills/magic-mouth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-mouth", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/openclaw/magic-mouthType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Hmbown/Wizards-of-the-Ghosts magic-mouth --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git skills-src && mkdir -p .agents/skills && cp -r skills-src/generated/openclaw/magic-mouth .agents/skills/magic-mouth && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "magic-mouth" agent skill from https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/openclaw/magic-mouth into .agents/skills/magic-mouth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-mouth", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Hmbown/Wizards-of-the-Ghosts magic-mouth --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/generated/openclaw/magic-mouth .cursor/skills/magic-mouth && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "magic-mouth" agent skill from https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/openclaw/magic-mouth into .cursor/skills/magic-mouth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-mouth", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Hmbown/Wizards-of-the-Ghosts.git --path generated/openclaw/magic-mouth--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Hmbown/Wizards-of-the-Ghosts magic-mouth --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/generated/openclaw/magic-mouth .gemini/skills/magic-mouth && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "magic-mouth" agent skill from https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/openclaw/magic-mouth into .gemini/skills/magic-mouth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-mouth", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Hmbown/Wizards-of-the-Ghosts magic-mouthInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git skills-src && mkdir -p .github/skills && cp -r skills-src/generated/openclaw/magic-mouth .github/skills/magic-mouth && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "magic-mouth" agent skill from https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/openclaw/magic-mouth into .github/skills/magic-mouth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-mouth", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Hmbown/Wizards-of-the-Ghosts magic-mouth --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/generated/openclaw/magic-mouth .opencode/skills/magic-mouth && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "magic-mouth" agent skill from https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/openclaw/magic-mouth into .opencode/skills/magic-mouth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-mouth", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
magic-mouth- GitHub stars
- 110
- Token cost
- ~836 tokens
- SKILL.md length
- 309 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- CC0-1.0
At a glance
Magic Mouth is trigger → message. An agent skill from Hmbown/Wizards-of-the-Ghosts.
- Works in 4 steps: Extract the trigger: Identify the exact… → Specify the payload: List every variable… → Define boundaries: Document no-fire… → …
- The message payload
- SKILL.md covers Overview, When To Use, Workflow and Deliverables, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Magic Mouth is an agent skill from Hmbown/Wizards-of-the-Ghosts. Magic Mouth is trigger → message. The entire craft is specifying the trigger boundary, the message payload, and the suppression/escalation rules. It is NOT: - One-time messages: "Send a Slack message now saying X" (no trigger, no automation) - Full chatbots: "Build a conversational AI that understands context and handles open-ended questions" (requires NLU, dialogue management) - Monitoring dashboards: "Set up Grafana with real-time graphs and trend analysis" (visualization, not message routing) - Silent…
Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Backend & APIs, covering Chatbots and conversational support, Slides and decks and Cryptography. It works with Slack and Grafana. The repository describes itself as: Unofficial Hermes Agent skill pack built from fantasy spell and skill names. The licence is CC0-1.0.
When your agent uses it
- The message payload
- The suppression/escalation rules
Example prompts
- “Send a Slack message now saying X”
- “(requires NLU, dialogue management) - Monitoring dashboards:”
- “(visualization, not message routing) - Silent traps/wards:”
- “/magic-mouth”
Requirements
- A credential in SLACK_TOKEN
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Extract the trigger: Identify the exact condition that fires the message (metric threshold, event type, time window, keyword match). Note…
- Specify the payload: List every variable in the message (who, what, where, severity, links). Write the response template with placeholders.
- Define boundaries: Document no-fire cases, rate limits, suppression windows, and escalation stages. Explicitly state what happens on…
- Return the spec: Produce a trigger-response specification with test cases covering: nominal fire, no-fire, repeated-trigger suppression…
What it can do on your machine
Read from SKILL.md and the folder at commit 1f2e6a0. 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
Magic Mouth loads about 836 tokens when it runs. Until then it costs about 215 tokens; SKILL.md has 309 words of instructions outside code blocks.
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 Hmbown/Wizards-of-the-Ghosts at commit 1f2e6a0, republished under its CC0-1.0 licence (© Hmbown). 309 words, ~836 tokens.
Download SKILL.mdSave it as
.claude/skills/magic-mouth/SKILL.md (or your agent's skills folder).- name
- magic-mouth
- description
- Magic Mouth is trigger → message. The entire craft is specifying the trigger boundary, the message payload, and the suppression/escalation rules. It is NOT: - One-time messages: "Send a Slack message now saying X" (no trigger, no automation) - Full chatbots: "Build a conversational AI that understands context and handles open-ended questions" (requires NLU, dialogue management) - Monitoring dashboards: "Set up Grafana with real-time graphs and trend analysis" (visualization, not message routing) - Silent traps/wards: "Revert changes silently and log who tried" (defensive code manipulation, not messaging) - Encryption: "Encrypt a message so only the recipient can read it" (cryptography, not event-driven delivery) - Multimedia presentations: "Play a 20-slide deck with animations and narration" (media playback, not conditional messaging)
- user-invocable
- true
Magic Mouth
Bind a message to a trigger so the system speaks exactly when it should.
Overview
Magic Mouth is interpreted here as a metaphorical spell with a shipping-now execution model.
Canonical source: Magic Mouth (spell)
Provider target: OpenClaw
When To Use
- Use this spell when the user describes an event-driven message automation: a specific trigger condition (X) should cause a specific message or notification (Y) to be sent without manual intervention.
- Look for these patterns in the request:
- "When [condition], send/post/notify [message/recipient]"
- "Set up an autoresponder for [scenario]"
- "Create an alert rule for [metric/event]"
- "Design a webhook handler that posts to [channel] when [event]"
- Mentions of triggers, fire conditions, suppression rules, rate limits, or escalation stages
- Explicit no-fire cases ("don't fire if...", "suppress duplicates for...", "only once per...")
Workflow
- Extract the trigger: Identify the exact condition that fires the message (metric threshold, event type, time window, keyword match). Note any compound conditions or timing delays ("wait 5 minutes before firing").
- Specify the payload: List every variable in the message (who, what, where, severity, links). Write the response template with placeholders.
- Define boundaries: Document no-fire cases, rate limits, suppression windows, and escalation stages. Explicitly state what happens on repeated triggers.
- Return the spec: Produce a trigger-response specification with test cases covering: nominal fire, no-fire, repeated-trigger suppression, and escalation progression. If Slack or a messaging API is available, include the concrete API call or workflow configuration.
Deliverables
- A trigger-response specification or message template.
- Example payloads covering nominal and edge-case inputs.
- Notes on rate limits, suppression, escalation, and logging.
Guardrails
- Do not automate messages requiring human judgment, empathy, or legal review
- Protect against loops, spam, and easily-spoofed trigger conditions
- Always include a suppression mechanism for repeated triggers
Default Invocation
Use $magic-mouth to turn this trigger into a reliable automated response and show me the exact fire conditions.
© Hmbown, CC0-1.0. 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 generated/openclaw/magic-mouth of Hmbown/Wizards-of-the-Ghosts.
Open the folder on GitHubat commit 1f2e6a0
Compare with similar skills
Magic Mouth 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Magic Mouth this skillHmbown/Wizards-of-the-Ghosts | 110 | — | ~836 | Automated safety check: Pass | CC0-1.0 | |
| Monitoring Capture ServicePostHog/posthog | 40k | — | ~5k | Automated safety check: Pass | Custom licence | |
| ML AIgrafana/skills | 282 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Monitoring Ingestion PipelinePostHog/posthog | 40k | — | ~9.1k | Automated safety check: Pass | Custom licence | |
| Glean Reference Architecturejeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Alerting Irmgrafana/skills | 282 | 1 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
ML AI
grafana/skills
Turn on AI + ML features in Grafana Cloud — Grafana Assistant (NL → PromQL/LogQL/TraceQL, dashboard build, incident investigation, MCP integration), Dynamic Alerting (Prophet forecasting + DBSCAN…
- Official
Monitoring Ingestion Pipeline
PostHog/posthog
Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production.
Glean Reference Architecture
jeremylongshore/tons-of-skills-marketplace
Enterprise architecture: Source Systems to Connectors (Cloud Run/Lambda, event-driven or scheduled) to Glean Indexing API to Glean Search Index to Client API (Search + Chat) to Your Apps (Slack bot…
- Official
Alerting Irm
grafana/skills
Configure Grafana Alerting, Incident Response Management (IRM), and SLOs end-to-end — provisions Grafana-managed and data-source-managed alert rules, contact points (Slack/PagerDuty/email/webhook)…
- Official
Oncall Irm
grafana/skills
Route alerts, run on-call rotations, and drive incidents in Grafana IRM / OnCall — integrations (Alertmanager / Grafana Alerting / generic webhook / PagerDuty), Jinja2 routing + grouping templates…
More from Hmbown/Wizards-of-the-Ghosts
All 11 skills in this repoAnimate Objects
Hmbown/Wizards-of-the-Ghosts
This spell transforms inert → reactive. An agent skill from Hmbown/Wizards-of-the-Ghosts.
Dancing Lights
Hmbown/Wizards-of-the-Ghosts
Use this spell for lightweight indicators: status pips, progress markers, heartbeat widgets, and ambient observability that help humans orient quickly.
Detect Magic
Hmbown/Wizards-of-the-Ghosts
A skill your agent uses when you need a fast, structured scan for where the real magic is hiding in a repo, workflow, or system.
Dispel Magic
Hmbown/Wizards-of-the-Ghosts
Use this spell when you need to cleanly shut down, disable, or remove active AI tooling — the reverse of Detect Magic.
Foresight
Hmbown/Wizards-of-the-Ghosts
Foresight produces bounded forecasts with explicit uncertainty to guide decisions.
Glyph Of Warding
Hmbown/Wizards-of-the-Ghosts
A skill your agent uses when you need a watchful boundary around files, systems, metrics, queues, or workflows.
Related
Questions about Magic Mouth
What does Magic Mouth do?
Magic Mouth is trigger → message. An agent skill from Hmbown/Wizards-of-the-Ghosts. Magic Mouth is an agent skill from Hmbown/Wizards-of-the-Ghosts. Magic Mouth is trigger → message.
When should I use Magic Mouth?
Magic Mouth fits situations like: the message payload; the suppression/escalation rules.
How do I install Magic Mouth in Claude Code?
Run `npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a claude-code`. Or copy the skill folder (generated/openclaw/magic-mouth in Hmbown/Wizards-of-the-Ghosts) into .claude/skills/magic-mouth in your project. Claude Code loads it when a task matches its description.
How do I install Magic Mouth in Codex?
Run `npx skills add Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a codex`. Or copy the skill folder (generated/openclaw/magic-mouth in Hmbown/Wizards-of-the-Ghosts) into .agents/skills/magic-mouth in your project. Codex loads it when a task matches its description.
Can I use Magic Mouth 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 Hmbown/Wizards-of-the-Ghosts --skill magic-mouth -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/magic-mouth, .gemini/skills/magic-mouth, .github/skills/magic-mouth and .opencode/skills/magic-mouth in your project.
What does Magic Mouth need to run?
SKILL.md names no scripts, command-line tools or credentials: Magic Mouth is instructions for the agent only. Our summary lists: A credential in SLACK_TOKEN.
Does Magic Mouth 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 Magic Mouth 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 Magic Mouth use?
Magic Mouth is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Magic Mouth use?
About 836 tokens (SKILL.md is roughly 3.3k 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 Magic Mouth?
Skills that share tags, products or a category with Magic Mouth: Monitoring Capture Service (PostHog/posthog, 40k stars), ML AI (grafana/skills, 282 stars), Monitoring Ingestion Pipeline (PostHog/posthog, 40k stars) and Glean Reference Architecture (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Magic Mouth?
Hmbown (a GitHub user) maintains it in Hmbown/Wizards-of-the-Ghosts, which has 110 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on April 5, 2026.
Source: Hmbown/Wizards-of-the-Ghosts on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.