capture-my-call-notes

capture-my-call-notes is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 64 tokens per session (1,223 once invoked), scanned A, original, MIT.

A note-taking tool that turns a meeting transcript or recording into structured notes: the real agenda, attendees, customer concerns, decisions, action items, and next step. It can match the meeting to a lead and update the CRM only after you approve it.

In plain words
What is it for?
Use it to process a sales call, separate internal and external tasks, update a lead's record, and record the agreed follow-up.
Why use it?
Raw transcripts are difficult to search and easy to leave unused. Structured notes preserve who agreed to what while keeping CRM changes under your control.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to process a sales call, separate internal and external tasks, update a lead's record, and record the agreed follow-up.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/capture-my-call-notes
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.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill capture-my-call-notes
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for capture-my-call-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/capture-my-call-notes/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/capture-my-call-notes)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/capture-my-call-notes"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/capture-my-call-notes/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for capture-my-call-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/capture-my-call-notes"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/capture-my-call-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,223 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00064 $0.01223
Opus 5 $0.00032 $0.00611
Sonnet 5 $0.00013 $0.00245
Haiku 4.5 $0.00006 $0.00122

Measured 6d ago against content hash 53badef7c8cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

capture-my-call-notes 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 6d ago.

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.

store/agents/sales/.agents/skills/capture-my-call-notes/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture My Call Notes

Turn raw transcript into structured, queryable, CRM-ready notes.

When to use

  • User: "process my call with Acme" / pastes transcript / drops .txt or .vtt file / "capture notes from yesterday's meeting".
  • Called by routine pulling from connected meeting-notes app (Fathom, Fireflies, Grain, Circleback, etc. - discovered via composio search meeting-notes).

Connections I need

I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.

  • Meetings - pull the transcript when you point me at a meeting. Required unless you paste or drop the file.
  • CRM - upsert a meeting/activity record on the lead's contact. Optional.
  • Task tools - log a notes entry in your docs/notes app. Optional.

If none of the required categories are connected and you haven't pasted or dropped a file, I stop and ask you to connect Gong or Fireflies, or share the transcript directly.

Information I need

I read your sales context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.

  • The transcript or recording - Required. Why I need it: I extract pains, decisions, and action items from what was actually said. If missing I ask: "Drop the recording, paste the transcript, or tell me which Gong/Fireflies meeting to grab."
  • Which lead or deal this call belongs to - Required. Why I need it: I link notes to the right lead and update their dossier. If missing I ask: "Which prospect or customer was this call with?"
  • Whether to push notes to your CRM - Optional. Why I need it: I sync only with your nod. If you don't have a preference I keep going with TBD and ask before any external sync.
  1. Source transcript. If pasted, use it. If file, read it. If user points to connected provider, run composio search for list/search tool, find most recent meeting matching user's description, pull transcript.
  2. Identify meeting. Extract date/time, attendees (separate internal vs external), duration, meeting title if available.
  3. Match to lead. Find external attendee(s) in leads.json by name + company. If not found, create minimal lead row from transcript, mark source: "meeting-first-contact".
  4. Assign id. call_id = kebab(date-primary-external-name).
  5. Extract structured notes:
    • Agenda actual - what actually discussed (not what agenda said).
    • Pain points raised - specific phrases in their words, with transcript quote.
    • Objections raised - price, timing, authority, fit - quoted.
    • Decisions - anything agreed during call.
    • Action items - owner + what + by when. Split internal vs external.
    • Next step - single next scheduled touchpoint (if agreed) or "next step TBD."
  6. Write structured: calls/{call_id}/notes.json with full schema + calls/{call_id}/notes.md as human-readable rollup.
  7. Update lead dossier. Append to leads/{slug}/lead.jsonrecentCalls: [...] (id + date + one-line summary). Update lastContactedAt, status (likely "meeting-held" or "follow-up-owed").
  8. Add to calls.json index with id, date, lead slug, attendees, next-step summary.
  9. CRM sync (if connected). Run composio search crm. If linked, upsert meeting/activity record on lead's CRM contact. Include attendees + date + action items + next step. Never sync verbatim transcript unless user explicitly opts in (usually out of scope for CRM notes fields).
  10. Note-app sync (if connected). If user has connected notes/docs app AND config/notes-sync.json says push, create note there. Otherwise skip silently.
  11. Summarize to user: "Captured. 3 pain points, 2 action items (1 yours: {X}, 1 theirs: {Y}), next step: {Z}. CRM synced."

Read the full file on GitHub · 95 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. 6d ago First seen · 95 lines · 64 tokens per session scan A 53badef7c8cf

Subscribe to this mod's changes

capture-my-call-notes is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 64 tokens to every session and 1,223 once invoked, about $0.0003 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 2026-09-05.

Related

Other skills, from other repositories

afrexai-lead-hunter

Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.

LeoYeAI/openclaw-master-skills · 50 tokens

handle-linkedin-connection-request-signal

Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…

swan-gtm/gtm-skills · 160 tokens

proposals

Use when writing the document a buyer reads to say yes — a commercial proposal or Statement of Work, turning discovery notes into a scoped and priced document, adding tiers so the middle one wins, or diagnosing a proposal that will not close. NOT the binding legal agreement with its liability and IP clauses (that is…

ericrisco/rsc-harness · 100 tokens

handle-demo-request

Use this skill when someone requests a demo through your website — a "Book a demo" form, a webhook carrying little more than a work email — and the question is what happens in the next sixty seconds. Enriches the person and company, decides fit and buyer persona separately, and routes the request down one of three…

swan-gtm/gtm-skills · 142 tokens

rfp-response

Use this skill when an inbound RFP, RFI, or brief lands and a proposal has to go back by a deadline - "an RFP just came in", "should we bid on this", "build the response", "the proposal is due Friday", "set up the RFP", "where are we on the [brand] RFP", "what's the status of our RFPs", "which RFP is about to slip".…

swan-gtm/gtm-skills · 135 tokens

sales-playbook-foundations

Use this skill when a sales team has no written playbook, when success lives in one leader's head, when onboarding is inconsistent, or when the user says "we need a playbook", "document our sales process", "what should be in our playbook", or "reps ramp too slowly". It produces the playbook skeleton — the five P's in…

swan-gtm/gtm-skills · 100 tokens