Skip to content
Agentmart
Submit a tool

analyze

Fetch a Loom recording's transcript and produce a reviewed action plan in the chat.

Skill by fontezbrooks

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fontezbrooks-analyze

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Fetch a Loom recording's transcript and produce a reviewed action plan in the chat. Read-only - does not mark the recording processed.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/analyze

Tools it pre-approves 3

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Write,
  • Bash

What's inside

Skill name
analyze
Description
Fetch a Loom recording's transcript and produce a reviewed action plan in the chat. Read-only - does not mark the recording processed.
License
MIT
Allowed tools
Read,, Write,, Bash
Instructions
25 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves any shell command

Files (1)

  • SKILL.md

SKILL.md (first lines)

Analysis contract (rules + output schema) for this run:

!`cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/print-analyze-contract.ts`

Produce an action plan for recording `$1`:

1. Fetch the transcript and metadata (writes `artifacts/$1.transcript.json` and `artifacts/$1.meta.json`):
   ```bash
   cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/download.ts $1
   ```
2. Read `artifacts/$1.transcript.json` and `artifacts/$1.meta.json`.
3. Following the analysis contract above, produce a single action-plan JSON object. Stamp
   `recordingId`, `recordingName`, `recordingDate` from the meta file. Use only what the transcript
   supports; set owners/priority/timeframe to null when not implied, and set `ownerIsGuess` true
   for any inferred owner.
4. Write that object to `artifacts/$1.plan.json`.
5. Validate it:
   ```bash
   cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/validate-plan.ts $1
   ```
   If validation fails, correct the plan and re-write it until it passes.
6. Present the plan to the user (summary, decisions, action items, open questions). Do NOT mark the
   recording processed - offer `/loom-daddy:publish $1` if they want it saved.

From fontezbrooks/loomDaddy, MIT.

More from fontezbrooks/loomDaddy

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 30, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from fontezbrooks

Cite this page

analyze skill. Agent Mart. https://agentmart.dev/skills/fontezbrooks-analyze (last updated 2026-10-24)