meeting-transcription
Skill20 starsChanged 2 months agoMITView on GitHub
Transcribe long local meeting audio into a validated rough transcript with bounded chunking, repetition and output-limit detection, targeted retries, optional stronger-model rescue, and auditable token usage. Use when a user provides an audio recording or asks for reliable multilingual meeting transcription.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- bks-lab/open-bridgetheir own version, first seen Oct 30, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- bks-lab/open-bridge★ 13same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- code-reviewSkill
- gemini-files-apiSkill
- harness-engineeringSkill
- hint-overlay-visual-verificationSkill
- ios-xcodegenSkill
- lifecycle-and-side-effects-correctnessSkill
- local-model-servingSkill
- mechanism-auditSkill
- public-source-release-auditSkill
- silent-pushes-setupSkill
- spec-creation-updatingSkill
- swift-testingSkill
- swiftui-view-refactorSkill
- xcode-buildSkill
- xcode-cloudSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 47
Run the bundled script from the installed skill directory:
- Distinctive: line 62
no persistent Gemini file retention.
- Very specific: line 64
Use --prepare-only to verify source metadata, hashing, and chunking without API calls.
- Distinctive: line 76
Only suspect five-minute chunks are split into one-minute retries.
- Distinctive: line 95
Treat output as a rough AI transcript, not certified verbatim evidence.
- Distinctive: line 97
Use generic speaker labels unless identity is grounded independently.
- Very specific: line 98
Prefer [unclear], [inaudible], or [overlapping speech] over invented content.
- Distinctive: line 99
Keep raw audio, chunks, and API envelopes outside downstream repositories unless the user explicitly requests approved retention.
- Distinctive: line 100
Create temporary evidence with owner-only permissions and repair restrictive permissions before resuming an existing work tree.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Meeting Transcription
Purpose
Turn long local meeting audio into a validated transcript body without treating a successful model response as proof of quality. This skill owns media preparation, transcription, outlier detection, retry/rescue, assembly, and usage evidence. Downstream business summaries, CRM changes, knowledge-base updates, and customer communication remain the consuming repository's responsibility.
Dependencies
ffmpegandffprobenode,jq, andshasum- The separately managed
gemini-files-apiskill - Gemini authentication configured outside this skill
Install the wrapper dependency and this skill into the same reviewed manager root before running the canonical command:
npx --yes skills@1.5.14 add fiveonecode/agent-skills \
--skill gemini-files-api --agent codex --global --yes
npx --yes skills@1.5.14 add fiveonecode/agent-skills \
--skill meeting-transcription --agent codex --global --yes
bash ~/.agents/skills/gemini-files-api/scripts/bootstrap.shFor Claude Code, use the same two pinned commands with --agent claude-code;
the bootstrap path is ~/.claude/skills/gemini-files-api/scripts/bootstrap.sh.
The script resolves the Gemini wrapper from:
GEMINI_MM, when set;${HOME}/.agents/skills/gemini-files-api/scripts/gemini-mm.mjs;${HOME}/.claude/skills/gemini-files-api/scripts/gemini-mm.mjs;${HOME}/.codex/skills/gemini-files-api/scripts/gemini-mm.mjsfor legacy installs.
The bootstrap script follows the same root order and can be overridden with
GEMINI_MM_BOOTSTRAP.
The wrapper must support --model, --temperature, --max-output-tokens, --json, --prompt, and --file, and return JSON containing text plus usageMetadata. The orchestration script intentionally omits model-specific thinking controls because supported knobs and levels vary by Gemini model family; a caller-selected model uses its compatible default.
Canonical Command
Run the bundled script from the installed skill directory:
scripts/transcribe_meeting_audio.sh \
--input /absolute/path/to/meeting.m4a \
--work-dir /tmp/meeting-transcription-account-dateDefaults:
gemini-3.1-flash-liteprimary model;300second primary chunks;60second retry chunks;- original spoken language preserved;
- temperature
0and minimal thinking; - no persistent Gemini file retention.
Use --prepare-only to verify source metadata, hashing, and chunking without API calls. Use --resume after an interrupted run; chunk sets are reused only when their completion marker matches the files on disk. Add --rescue-model <model> only when one-minute retries still fail validation.
Validation Contract
The primary response is suspect when it has:
- empty text or invalid JSON;
- any candidate finish reason other than
STOP; - output tokens at the configured cap;
- long generated runs of
I,Yeah, oruh; - the same substantial line repeated at least five times.
Only suspect five-minute chunks are split into one-minute retries. The script exits non-zero before assembly while any retry remains unresolved. A stronger rescue model may process only those unresolved one-minute pieces.
Outputs
The work directory contains:
source-metadata.jsonandsource.sha256;chunks/,raw/,retry/, and optionalrescue/evidence;validation.tsv,retry-validation.tsv, andunresolved-parts.txt;accepted-rescue-parts.txt, which limits assembly to rescue outputs accepted by the current validation pass;assembled-transcript-body.mdwith global chunk anchors;usage.jsonwith modality token counts;run-manifest.jsonwith source and output identity.
Pricing is intentionally not hardcoded. Compare usage.json with current first-party pricing when cost reporting is required.
Evidence Rules
- Treat output as a rough AI transcript, not certified verbatim evidence.
- Preserve original languages; do not silently translate.
- Use generic speaker labels unless identity is grounded independently.
- Prefer
[unclear],[inaudible], or[overlapping speech]over invented content. - Keep raw audio, chunks, and API envelopes outside downstream repositories unless the user explicitly requests approved retention.
- Create temporary evidence with owner-only permissions and repair restrictive permissions before resuming an existing work tree.
- Reconcile names, numbers, dates, prices, and commitments against the source before downstream use.
Completion Gate
unresolved-parts.txtis empty.validation.tsvand retry/rescue reports were reviewed.assembled-transcript-body.md,usage.json, andrun-manifest.jsonexist.bash -n scripts/transcribe_meeting_audio.shpasses.scripts/test_transcribe_meeting_audio.shpasses, including managed-root dependency discovery, interrupted-split recovery, and malformed-response retry coverage.- A short spoken fixture passes the normal path and an injected repetition/output-limit fixture reaches the retry path.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

