Meetings
alirezarezvani/claude-skills
A skill your agent uses when someone wants to decide whether a meeting is worth calling, price a meeting in dollars, build a timeboxed agenda with desired outcomes, or turn messy meeting notes into…
Clean raw workshop or meeting transcripts from small talk, filler words, and off-topic tangents.
MITAuto-check passed
Install Tsh Transcript Processing
$ npx skills add TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TheSoftwareHouse/copilot-collections tsh-transcript-processing --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/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/tsh-transcript-processing .claude/skills/tsh-transcript-processing && 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 "tsh-transcript-processing" agent skill from https://github.com/TheSoftwareHouse/copilot-collections/tree/main/.github/skills/tsh-transcript-processing into .claude/skills/tsh-transcript-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsh-transcript-processing", 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/TheSoftwareHouse/copilot-collections/tree/main/.github/skills/tsh-transcript-processingType 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 TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TheSoftwareHouse/copilot-collections tsh-transcript-processing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/tsh-transcript-processing .agents/skills/tsh-transcript-processing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tsh-transcript-processing" agent skill from https://github.com/TheSoftwareHouse/copilot-collections/tree/main/.github/skills/tsh-transcript-processing into .agents/skills/tsh-transcript-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsh-transcript-processing", 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 TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TheSoftwareHouse/copilot-collections tsh-transcript-processing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/tsh-transcript-processing .cursor/skills/tsh-transcript-processing && 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 "tsh-transcript-processing" agent skill from https://github.com/TheSoftwareHouse/copilot-collections/tree/main/.github/skills/tsh-transcript-processing into .cursor/skills/tsh-transcript-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsh-transcript-processing", 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/TheSoftwareHouse/copilot-collections.git --path .github/skills/tsh-transcript-processing--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 TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TheSoftwareHouse/copilot-collections tsh-transcript-processing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/tsh-transcript-processing .gemini/skills/tsh-transcript-processing && 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 "tsh-transcript-processing" agent skill from https://github.com/TheSoftwareHouse/copilot-collections/tree/main/.github/skills/tsh-transcript-processing into .gemini/skills/tsh-transcript-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsh-transcript-processing", 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 TheSoftwareHouse/copilot-collections tsh-transcript-processingInstalls 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 TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/tsh-transcript-processing .github/skills/tsh-transcript-processing && 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 "tsh-transcript-processing" agent skill from https://github.com/TheSoftwareHouse/copilot-collections/tree/main/.github/skills/tsh-transcript-processing into .github/skills/tsh-transcript-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsh-transcript-processing", 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 TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install TheSoftwareHouse/copilot-collections tsh-transcript-processing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/tsh-transcript-processing .opencode/skills/tsh-transcript-processing && 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 "tsh-transcript-processing" agent skill from https://github.com/TheSoftwareHouse/copilot-collections/tree/main/.github/skills/tsh-transcript-processing into .opencode/skills/tsh-transcript-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsh-transcript-processing", 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
tsh-transcript-processing- GitHub stars
- 284
- Token cost
- ~1.4k tokens
- SKILL.md length
- 645 words
- Files
- 2
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- MIT
At a glance
Clean raw workshop or meeting transcripts from small talk, filler words, and off-topic tangents.
- SKILL.md covers Transcript Processing Process and Connected Skills
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Tsh Transcript Processing is an agent skill from TheSoftwareHouse/copilot-collections. Clean raw workshop or meeting transcripts from small talk, filler words, and off-topic tangents. Extract and structure business-relevant content into a standardized format with discussion topics, key decisions, action items, and open questions.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `cleaned-transcript.example.md`).
The repository describes itself as: Opinionated AI-enabled workflows for product engineering. The licence is MIT.
Example prompts
- “/tsh-transcript-processing”
What it can do on your machine
Read from SKILL.md and the folder at commit 2fbe51e. 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
Tsh Transcript Processing loads about 1.4k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 645 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 TheSoftwareHouse/copilot-collections at commit 2fbe51e, republished under its MIT licence (© TheSoftwareHouse). 645 words, ~1,382 tokens.
Download SKILL.mdSave it as
.claude/skills/tsh-transcript-processing/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- tsh-transcript-processing
- description
- Clean raw workshop or meeting transcripts from small talk, filler words, and off-topic tangents. Extract and structure business-relevant content into a standardized format with discussion topics, key decisions, action items, and open questions.
- user-invocable
- false
Transcript Processing
This skill helps you clean raw workshop or meeting transcripts and produce a structured, business-relevant document. It removes noise (small talk, greetings, filler words, off-topic tangents) while preserving all actionable and business-critical discussion points.
Transcript Processing Process
Use the checklist below and track your progress:
Processing progress:
- [ ] Step 1: Identify transcript format and meeting metadata
- [ ] Step 2: Identify and tag participants
- [ ] Step 3: Remove non-business content
- [ ] Step 4: Group remaining content by discussion topics
- [ ] Step 5: Extract key decisions
- [ ] Step 6: Extract action items and open questions
- [ ] Step 7: Preserve critical raw context
- [ ] Step 8: Save the cleaned transcriptStep 1: Identify transcript format and meeting metadata
Determine the format of the raw transcript:
- Speaker-labelled transcript (e.g.,
[Speaker Name]: text) - Plain text notes without speaker labels
- Timestamped transcript (e.g.,
[00:12:34] text) - Mixed format
- PDF document (transcript or meeting notes exported/provided as PDF — use
pdf-readertool to extract text content first)
Extract meeting metadata where available:
- Date and time of the workshop
- Duration (if timestamps are present, calculate from first to last entry)
- Workshop topic or title
- Context (e.g., "Discovery workshop for Project X, Sprint 3 planning")
If metadata is not explicitly stated in the transcript, ask the user to provide it.
Step 2: Identify and tag participants
Scan the transcript for participant names or speaker labels. For each participant:
- Note their name or identifier
- Infer their role if mentioned or obvious from context (e.g., "Product Owner", "Developer", "Client stakeholder")
- If roles are not clear, list participants without roles — do not guess
Step 3: Remove non-business content
Systematically identify and remove:
- Greetings and sign-offs: "Hi everyone", "Let's wrap up", "Have a good weekend"
- Small talk: Weather, personal anecdotes, unrelated banter
- Filler words and verbal tics: "um", "uh", "you know", "like" (when used as filler)
- Technical difficulties discussion: "Can you hear me?", "Let me share my screen", "You're on mute"
- Off-topic tangents: Discussions clearly unrelated to the workshop's purpose
- Repetitive restatements: When the same point is made multiple times, keep the clearest version
Important: When in doubt about whether content is business-relevant, keep it. It is better to preserve potentially useful context than to accidentally remove important information.
Step 4: Group remaining content by discussion topics
Analyze the cleaned content and organize it into logical discussion topics:
- Identify natural topic boundaries (when the conversation shifts to a new subject)
- Create descriptive topic headings that summarize the theme
- Under each topic, list the key points discussed as bullet points
- Attribute points to speakers when speaker labels are available
- Maintain chronological order within each topic
- If a topic spans multiple disconnected parts of the transcript, consolidate them under one heading
Step 5: Extract key decisions
Show full SKILL.md (256 more words)Show less
Review the structured content and identify explicit and implicit decisions:
- Explicit decisions: Statements like "We agreed to...", "The decision is...", "Let's go with..."
- Implicit decisions: When discussion converges on a direction without formal declaration
- For each decision, note:
- What was decided
- Who made or endorsed the decision (if clear)
- Any conditions or caveats attached
Step 6: Extract action items and open questions
Scan for action items:
- Commitments to do something (e.g., "I'll prepare the wireframes by Friday")
- Assigned tasks (e.g., "Can you check the API documentation?")
- For each action item, note: what, who (if assigned), and any deadline mentioned
Scan for open questions:
- Unanswered questions raised during the workshop
- Items deferred for later discussion ("We'll revisit this next week")
- Ambiguities that were acknowledged but not resolved
Step 7: Preserve critical raw context
Identify and preserve exact quotes or passages where the original wording is important:
- Requirements stated in specific business language
- Constraints or limitations mentioned by stakeholders
- Conflicting viewpoints that need to be captured verbatim
- Domain-specific terminology defined or explained during the workshop
Place these in a "Preserved Context" section with attribution to the speaker.
Step 8: Save the cleaned transcript
Generate the final output following the ./cleaned-transcript.example.md template.
Save the file to specifications/<workshop-name>/cleaned-transcript.md.
Review the output to ensure:
- No business-relevant content was accidentally removed
- Topics are logically grouped and clearly labelled
- Decisions, action items, and open questions are complete
- The document is readable and useful as a standalone reference
Connected Skills
tsh-task-extracting- uses the cleaned transcript as a primary input for identifying epics and stories
© TheSoftwareHouse, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .github/skills/tsh-transcript-processing of TheSoftwareHouse/copilot-collections.
- SKILL.md
- cleaned-transcript.example.md
Open the folder on GitHubat commit 2fbe51e
Compare with similar skills
Tsh Transcript Processing 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 |
|---|---|---|---|---|---|---|
| Tsh Transcript Processing this skillTheSoftwareHouse/copilot-collections | 284 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Meetingsalirezarezvani/claude-skills | 28k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Meeting Distiller Prosickn33/agentic-awesome-skills | 47k | 1 repos | ~1k | Automated safety check: Pass | MIT | |
| Meeting Ingestiongarrytan/gbrain | 31k | — | ~7.1k | Automated safety check: Pass | MIT | |
| Meeting Transcripthuytieu/COG-second-brain | 1.3k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Youtube Transcriptbrowser-act/skills | 6.1k | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Meeting Distiller Pro
sickn33/agentic-awesome-skills
Transform messy meeting notes and transcripts into structured action items, decisions, and follow-ups.
Meeting Ingestion
garrytan/gbrain
Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge.
Meeting Transcript
huytieu/COG-second-brain
Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering
Youtube Transcript
browser-act/skills
YouTube transcript extraction and content reformatting: given a YouTube video URL, opens the video's transcript panel, extracts all timestamped segments, and transforms the raw transcript into…
Meeting Notes And Actions
composio-community/awesome-codex-skills
Turn meeting transcripts or rough notes into crisp summaries with decisions, risks, and owner-tagged action items; use for Zoom/Meet/Teams transcripts, call notes, or long meeting chats to generate…
More from TheSoftwareHouse/copilot-collections
All 31 skills in this repoTsh Creating Skills
TheSoftwareHouse/copilot-collections
Create new skills (SKILL.md) for GitHub Copilot. An agent skill from TheSoftwareHouse/copilot-collections.
Tsh Implementing Frontend
TheSoftwareHouse/copilot-collections
Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow.
Tsh Implementing Terraform Modules
TheSoftwareHouse/copilot-collections
Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices.
Tsh Optimizing Frontend
TheSoftwareHouse/copilot-collections
Frontend rendering optimization, code splitting, memoization strategies, bundle size control, asset optimization, and memory management.
Tsh Reviewing Frontend
TheSoftwareHouse/copilot-collections
Frontend-specific code review criteria, component anti-patterns, hooks quality, rendering correctness, accessibility and performance spot-checks, and module organization issues.
Tsh Writing Hooks
TheSoftwareHouse/copilot-collections
Custom hook and composable patterns — naming, composition, stable return shapes, lifecycle cleanup, and testing strategies.
Questions about Tsh Transcript Processing
What does Tsh Transcript Processing do?
Clean raw workshop or meeting transcripts from small talk, filler words, and off-topic tangents. Tsh Transcript Processing is an agent skill from TheSoftwareHouse/copilot-collections. Clean raw workshop or meeting transcripts from small talk, filler words, and off-topic tangents.
How do I install Tsh Transcript Processing in Claude Code?
Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a claude-code`. Or copy the skill folder (.github/skills/tsh-transcript-processing in TheSoftwareHouse/copilot-collections) into .claude/skills/tsh-transcript-processing in your project. Claude Code loads it when a task matches its description.
How do I install Tsh Transcript Processing in Codex?
Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a codex`. Or copy the skill folder (.github/skills/tsh-transcript-processing in TheSoftwareHouse/copilot-collections) into .agents/skills/tsh-transcript-processing in your project. Codex loads it when a task matches its description.
Can I use Tsh Transcript Processing 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 TheSoftwareHouse/copilot-collections --skill tsh-transcript-processing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsh-transcript-processing, .gemini/skills/tsh-transcript-processing, .github/skills/tsh-transcript-processing and .opencode/skills/tsh-transcript-processing in your project.
What does Tsh Transcript Processing need to run?
SKILL.md names no scripts, command-line tools or credentials: Tsh Transcript Processing is instructions for the agent only.
Does Tsh Transcript Processing 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 Tsh Transcript Processing 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 Tsh Transcript Processing use?
Tsh Transcript Processing 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 Tsh Transcript Processing use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 Tsh Transcript Processing?
Skills that share tags, products or a category with Tsh Transcript Processing: Meetings (alirezarezvani/claude-skills, 28k stars), Meeting Distiller Pro (sickn33/agentic-awesome-skills, 47k stars), Meeting Ingestion (garrytan/gbrain, 31k stars) and Meeting Transcript (huytieu/COG-second-brain, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tsh Transcript Processing?
TheSoftwareHouse (a GitHub organization) maintains it in TheSoftwareHouse/copilot-collections, which has 284 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 5, 2026.
Source: TheSoftwareHouse/copilot-collections on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.