transcript-processor

A workflow for turning meeting transcripts—written records of spoken conversations—into action items, knowledge-base updates, and an HTML slide summary.

In plain words
What is it for?
Processing meeting notes or transcripts, identifying participants and topics, assigning follow-up work, and creating a presentation summary.
Why use it?
It extracts decisions and responsibilities from long conversations so they can be reused and acted on.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/breadchaincoop/labor.fun/transcript-processor
Any agent
npx skills add BreadchainCoop/labor.fun --skill transcript-processor
Clone the repo
git clone --depth 1 https://github.com/BreadchainCoop/labor.fun

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,180 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.02180
Opus 5 $0.00010 $0.01090
Sonnet 5 $0.00004 $0.00436
Haiku 4.5 $0.00002 $0.00218

Measured yesterday against content hash 03bc5f366779, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transcript-processor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

container/skills/transcript-processor/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Transcript Processor Skill

Overview

When someone pastes a meeting transcript or asks you to process meeting notes, follow this workflow to extract structured data and produce an HTML slideshow summary.

Detection

Recognize transcript intake when:

  • User says "transcript", "meeting notes", "process this meeting", "summarize this transcript"
  • A large block of text with multiple speakers, dialogue markers (e.g., "Alice:", timestamps, "Speaker 1:")
  • User says "here are the notes from..." followed by substantial text

Processing Steps

1. Parse the Transcript

Read the full text and identify:

  • Who spoke: List all unique speakers/participants
  • When: Date/time if mentioned
  • What was discussed: Group dialogue into topic clusters

2. Extract Structured Items

For each of these categories, scan the transcript thoroughly:

Action Items

Look for commitments: "I'll...", "Let's...", "We need to...", "Can you...", "Action item:", "TODO:"

[{
  "description": "What needs to be done",
  "assignee": "Who is responsible (or 'unassigned')",
  "due_date": "YYYY-MM-DD or null if not mentioned",
  "priority": "high/medium/low (infer from urgency language)",
  "status": "pending"
}]
New Events

Look for scheduled meetings, deadlines, gatherings: "next Thursday", "schedule a...", "let's meet on..."

[{
  "title": "Event name",
  "date": "YYYY-MM-DD or description like 'next Friday'",
  "time": "HH:MM or null",
  "location": "Where, or null",
  "description": "Context from transcript"
}]
New People

Cross-reference names against context/people/. Anyone not already in the KB:

[{
  "name": "Full name",
  "role": "Role if mentioned",
  "context": "How they came up in the meeting"
}]
Task Updates

References to existing work: "the website project", "TASK-042", "the thing we discussed last week"

[{
  "task_id": "TASK-NNN if identifiable, null otherwise",
  "title": "Task title for matching",
  "description": "What was said about it",
  "assignee": "New or confirmed assignee",
  "priority": "Changed priority if discussed",
  "status": "New status if discussed"
}]

Read the full file on GitHub · 215 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 215 lines · 19 tokens per session scan A 03bc5f366779

Subscribe to this mod's changes

transcript-processor is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 2,180 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens