Agent skill

Meeting Transcript

by huytieu in huytieu/COG-second-brain

Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering

MITAuto-check passedAgent Workflows

Install Meeting Transcript

skills CLI
$ npx skills add huytieu/COG-second-brain --skill meeting-transcript -a claude-code

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

GitHub CLI
$ gh skill install huytieu/COG-second-brain meeting-transcript --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/huytieu/COG-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/meeting-transcript .claude/skills/meeting-transcript && 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
meeting-transcript
GitHub stars
1.3k
Used in
1 other repo
Token cost
~2.3k tokens
SKILL.md length
846 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering

  • Works in 12 steps: Setup (Orchestrator) → Parallel Processing (Spawn 2-3 Agents… → Assembly (Orchestrator) → …
  • Tasks that involve Subagents
  • SKILL.md covers When to Invoke, Agent Mode Awareness, Purpose and Command: /meeting-transcript, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Meeting Transcript is an agent skill from huytieu/COG-second-brain. Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering

Its SKILL.md is about 2.3k 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 Agent Workflows, covering Subagents. The repository describes itself as: Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework… The licence is MIT.

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/meeting-transcript”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Setup (Orchestrator)
  2. Parallel Processing (Spawn 2-3 Agents Simultaneously)
  3. Assembly (Orchestrator)
  4. Meeting Overview
  5. Key Decisions (Verified Content Only)
  6. Action Items (Substantive Only)
  7. Strategic Themes (From Substantial Discussion)
  8. Unresolved Issues
  9. Team Dynamics Assessment
  10. Initial Scan
  11. Relevance Assessment
  12. Accuracy Verification

What it can do on your machine

Read from SKILL.md and the folder at commit 36ac9d7. 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 (its code samples are yaml).

    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

Meeting Transcript loads about 2.3k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 846 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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 huytieu/COG-second-brain at commit 36ac9d7, republished under its MIT licence (© huytieu). 846 words, ~2,280 tokens.

Download SKILL.mdSave it as .claude/skills/meeting-transcript/SKILL.md (or your agent's skills folder).
name
meeting-transcript
description
Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering
roles
product-manager, engineering-lead, founder, designer

COG Meeting Transcript Skill

When to Invoke

  • User shares a meeting transcript or recording notes
  • User says "process meeting", "meeting notes", "meeting transcript"
  • User has a block of text from a meeting they want structured
  • User mentions wanting to extract action items from a meeting

Agent Mode Awareness

Check agent_mode in 00-inbox/MY-PROFILE.md frontmatter:

  • If agent_mode: team — use the full parallel agent execution strategy below (3 agents)
  • If agent_mode: solo — process sequentially: extract content first, then analyze dynamics, then enrich with context.

Purpose

Extract strategic insights from meeting recordings and notes with intelligent content filtering to focus on substantive, actionable content while removing noise and irrelevant information.

Command: /meeting-transcript

Parallel Agent Team Execution Strategy

Use parallel agents to process different aspects of the transcript simultaneously.

Phase 1: Setup (Orchestrator)
  1. Receive transcript content from user
  2. Detect content type (meeting vs braindump) and classify domain
  3. Split transcript into logical sections for parallel processing
Phase 2: Parallel Processing (Spawn 2-3 Agents Simultaneously)

Launch ALL agents in a single message using Task tool with run_in_background: true:

Agent 1: "content-extractor" (subagent_type: general-purpose)
Extract structured content from the meeting transcript.

1. Filter out side chats, technical difficulties, and irrelevant banter
2. Identify and extract: decisions made (with rationale), action items (with owners/deadlines), strategic themes
3. Capture key quotes and insights from participants
4. Note unresolved issues and follow-up needs

Return: Decisions list, action items list, strategic themes, key quotes, unresolved issues.
Agent 2: "dynamics-analyst" (subagent_type: general-purpose)
Analyze team dynamics and meeting effectiveness.

1. Assess communication patterns and participation levels
2. Identify leadership moments and collaboration quality
3. Evaluate decision-making process effectiveness
4. Assess meeting efficiency (time well spent vs wasted)
5. Note any tensions, disagreements, or alignment issues

Return: Team dynamics assessment, participation analysis, meeting effectiveness score.
Agent 3: "context-enricher" (subagent_type: general-purpose)
Enrich meeting content with project/product context.

1. If project-related: read recent braindumps and notes for context
2. Check if discussed topics relate to known issues/PRs on GitHub
3. Connect decisions to existing strategic priorities
4. Identify competitive intelligence if competitors mentioned

Return: Contextual connections, related documents, strategic alignment notes.
Phase 3: Assembly (Orchestrator)
  1. Collect results from all processing agents
  2. Assemble structured meeting summary following Content Structure template
  3. Add proper metadata (participants, duration, type, action item count)
  4. Save to appropriate domain meeting folder
  5. Flag urgent action items for immediate attention

Content Filtering Guidelines

EXCLUDE (Filter Out)
  • Side Conversations: "Hey, did you see the game last night?"
  • Technical Difficulties: "Can you hear me now?" "Your mic is muted"
  • Incomplete Thoughts: "So I was thinking we should... never mind"
  • Casual Banter: Weather, personal anecdotes unrelated to work
  • Interruptions: "Sorry, I have to take this call"
  • Unclear Statements: Mumbled or inaudible content
INCLUDE (Keep and Analyze)
  • Strategic Discussions: Market analysis, competitive positioning
  • Decision Points: "We've decided to move forward with Option A"
  • Action Items: "Alex will complete the analysis by Friday"
  • Problem Solving: Discussion of challenges and proposed solutions
  • Planning: Timeline discussions, resource allocation
  • Insights: "The key insight is that customers want..."
  • Concerns: "My concern is that this approach might..."

Metadata Template

yaml
---
type: meeting-transcript
domain: [personal|professional|project-specific]
project: [project-name] # Only for project-specific meetings
date: YYYY-MM-DD
created: YYYY-MM-DD HH:MM
meeting_type: [1-on-1|team-meeting|strategic-planning|project-review|other]
participants: [participant1, participant2, participant3]
duration: [minutes]
content_filtered: true
accuracy_verified: [true|false|pending]
action_items_count: [number]
decisions_count: [number]
tags:
  - meeting
  - transcript
  - domain-tag
  - project-tag
status: [processed|needs-follow-up|action-required]
---

Content Structure

1. Meeting Overview
  • Date/Time: When the meeting occurred
  • Participants: Who was present and their roles
  • Purpose: Primary objective of the meeting
  • Duration: Actual meeting length
  • Type: Category of meeting
2. Key Decisions (Verified Content Only)
  • Decision: What was decided
  • Rationale: Why this decision was made
  • Owner: Who is responsible for implementation
  • Timeline: When decision takes effect
  • Impact: Expected outcomes and implications
3. Action Items (Substantive Only)
  • Task: Specific action to be taken
  • Owner: Person responsible
  • Deadline: When it's due
  • Dependencies: What needs to happen first
  • Success Criteria: How completion will be measured
4. Strategic Themes (From Substantial Discussion)
  • Theme: Major topic or pattern discussed
  • Context: Why this theme is important
  • Implications: What this means for the team/project
  • Next Steps: How to address or leverage this theme
5. Unresolved Issues
  • Issue: Problem or question that remains open
  • Context: Background and importance
  • Blocking Factors: What's preventing resolution
  • Proposed Next Steps: How to move forward
Show full SKILL.md (339 more words)Show less
6. Team Dynamics Assessment
  • Communication Quality: How effectively team communicated
  • Decision-Making Process: How decisions were reached
  • Participation: Who contributed and how
  • Meeting Efficiency: Time management and focus
  • Areas for Improvement: Suggestions for better meetings

Domain-Specific Processing

Personal Domain Meetings
  • Focus on career development and personal growth
  • Maintain strict privacy for personal discussions
  • Extract learning and development opportunities
  • Save to [CUSTOMIZE: path/to/personal/]meetings/
Professional Domain Meetings
  • Analyze leadership and team management aspects
  • Extract strategic business insights
  • Identify professional development opportunities
  • Save to [CUSTOMIZE: path/to/professional/]meetings/
Project-Specific Meetings
  • Connect to project metrics and milestones
  • Analyze progress against project goals
  • Extract competitive and market intelligence
  • Save to [CUSTOMIZE: path/to/projects/][project-name]/meetings/

Content Filtering Protocol

Step 1: Initial Scan
  • Identify meeting phases (intro, main discussion, wrap-up)
  • Mark obvious side conversations and technical issues
  • Flag incomplete or unclear statements
Step 2: Relevance Assessment
  • Evaluate each segment for strategic value
  • Determine if content relates to meeting objectives
  • Assess completeness and accuracy of information
Step 3: Accuracy Verification
  • Cross-check contradictory statements
  • Flag information that seems incorrect
  • Note areas requiring clarification
Step 4: Context Preservation
  • Ensure decisions have sufficient context
  • Maintain background for action items
  • Preserve strategic discussion flow

Quality Assurance

Verification Standards
  • All decisions must have clear context and rationale
  • Action items must have specific owners and deadlines
  • Strategic themes must be supported by substantial discussion
  • Team dynamics assessment must be based on observable patterns
Uncertainty Handling
  • Flag potentially incorrect information for user confirmation
  • State confidence levels for interpretations
  • Request clarification for ambiguous content
  • Explicitly note when information is incomplete

Integration with Daily Brief

Meeting notes processed by this command feed directly into the daily brief:

  • Phase 2, Agent 3 (meeting-reviewer) scans for recent meeting files
  • Phase 3 cross-references action items against GitHub PRs and Linear issues
  • Section 13 (Meeting Follow-Up Tracker) tracks commitment completion

This creates accountability: decisions and action items from meetings are automatically tracked against actual execution in code and project management tools.

Learning Integration

  • Track meeting effectiveness patterns over time
  • Identify successful decision-making processes
  • Learn team communication preferences
  • Adapt filtering based on user feedback on relevance

© huytieu, MIT. 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 skills/meeting-transcript of huytieu/COG-second-brain.

Open the folder on GitHubat commit 36ac9d7

Used in 1 other repository

We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in huytieu/COG-second-brain, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Meeting Transcript 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.

Meeting Transcript compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Meeting Transcript this skillhuytieu/COG-second-brain1.3k1 repos~2.3kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26138 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25841 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 38 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 41 repos~1.5k tokens
    Agent WorkflowsAuto-check passed
  • Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed
  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from huytieu/COG-second-brain

All 37 skills in this repo
  • Voice Baseline

    huytieu/COG-second-brain

    Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style.

    1.3k GitHub stars~957 tokensUpdated 6 days ago
    Auto-check passed
  • Daily Journal

    huytieu/COG-second-brain

    A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.

    1.3k GitHub stars~1.3k tokensUpdated 6 days ago
    Auto-check passed
  • Editorial Illustrations

    huytieu/COG-second-brain

    Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent.

    1.3k GitHub stars~2.4k tokensUpdated 6 days ago
    Auto-check passed
  • Loop Engineering

    huytieu/COG-second-brain

    Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns.

    1.3k GitHub stars~1.5k tokensUpdated 6 days ago
    Auto-check passed
  • Knowledge Consolidation

    huytieu/COG-second-brain

    Build frameworks from scattered insights across all braindumps and notes

    1.3k GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed
  • Release Video

    huytieu/COG-second-brain

    Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a…

    1.3k GitHub stars~1.7k tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Meeting Transcript

What does Meeting Transcript do?

Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering. Meeting Transcript is an agent skill from huytieu/COG-second-brain.

When should I use Meeting Transcript?

Meeting Transcript fits situations like: tasks that involve Subagents.

How do I install Meeting Transcript in Claude Code?

Run `npx skills add huytieu/COG-second-brain --skill meeting-transcript -a claude-code`. Or copy the skill folder (skills/meeting-transcript in huytieu/COG-second-brain) into .claude/skills/meeting-transcript in your project. Claude Code loads it when a task matches its description.

How do I install Meeting Transcript in Codex?

Run `npx skills add huytieu/COG-second-brain --skill meeting-transcript -a codex`. Or copy the skill folder (skills/meeting-transcript in huytieu/COG-second-brain) into .agents/skills/meeting-transcript in your project. Codex loads it when a task matches its description.

Can I use Meeting Transcript 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 huytieu/COG-second-brain --skill meeting-transcript -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meeting-transcript, .gemini/skills/meeting-transcript, .github/skills/meeting-transcript and .opencode/skills/meeting-transcript in your project.

What does Meeting Transcript need to run?

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

Does Meeting Transcript 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 Meeting Transcript 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 Meeting Transcript use?

Meeting Transcript is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Meeting Transcript use?

About 2.3k tokens (SKILL.md is roughly 9.1k 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 Meeting Transcript?

Skills that share tags, products or a category with Meeting Transcript: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Meeting Transcript?

huytieu (a GitHub user) maintains it in huytieu/COG-second-brain, which has 1,265 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

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