arcmira — Claude Code skill: what it does, how to install
Searches mentions, sponsors, and quotes across YouTube and podcast transcripts. Helps track brand buzz, research advertisers, and extract exact spoken clips.
npx skills add arcmira/mcp --skill arcmira -a claude-codeWhat arcmira does
The skill links the assistant to Arcmira through its MCP server or CLI commands. It executes JavaScript routines to inspect indexed transcripts, discover on-air recommendations, and measure discussion momentum. Dedicated sub-skills cover specific workflows: vetting sponsor deals, comparing two shows side by side, or extracting exact timestamps for audio clips.
Arcmira rejects raw names in filters. Any show, speaker, or product must be resolved to its literal entity or channel identifier first, or the call fails with id_required. This extra step makes scripted lookups reliable, though it forces two-phase queries.
Queries consume account credits based on the plan. Beyond the first five passages, searches charge four credits for each extra passage, and active email or Slack monitors deduct twenty-five credits per alert.
What it helps with
- track podcast advertisers and recurring show sponsors
- extract verbatim quotes with YouTube timestamps
- measure discussion momentum for brands across talk shows
- compare topic coverage and shared sponsors between two channels
- dispatch Slack alerts for fresh entity mentions
Example prompts for the agent
- Search indexed podcast transcripts with arcmira for mentions of OpenAI over the last 90 days.
- Find who sponsors this YouTube show and list all recent ad reads.
- Compare these two tech podcasts: do they share any sponsors or recurring topics?
How to install arcmira
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill arcmira -a claude-code2Manually: put the files in place
~/.claude/skills/arcmira/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/arcmira/
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill arcmira -a codex2Manually: put the files in place
.agents/skills/arcmira/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill arcmira -a cursor2Manually: put the files in place
.cursor/skills/arcmira/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install arcmira/mcp arcmira2Manually: put the files in place
.github/skills/arcmira/SKILL.md1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill arcmira -a gemini-cli2Platform CLI
gemini skills install https://github.com/arcmira/mcp --path plugins/arcmira/skills/arcmiraManually: put the files in place
.devin/skills/arcmira/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add arcmira/mcp --skill arcmira -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about arcmira
How to install arcmira in Claude Code?
Run npx skills add arcmira/mcp --skill arcmira -a claude-code. This installs the skill file into ~/.claude/skills/arcmira/SKILL.md.
What does the arcmira skill do?
It gives coding agents access to indexed podcast and YouTube transcripts via the Arcmira MCP server. It lets you inspect brand mentions, research sponsors, and monitor spoken topics.
Why does an Arcmira search fail with an id_required error?
Filters accept only literal entity, channel, or video IDs rather than raw strings. You must resolve the name first using arcmira.resolve before applying it as a query filter.
