Skip to content
cccskills
FreePublished on GitHubEnglish overview

find-in-circleback

Find statements, decisions, and commitments in Circleback meeting records. Search by people, company, tags, or dates, then use notes and transcripts to distinguish discussion from agreement and identify the meeting behind each answer.

OriginalShow the original description

Answer "what did we say, decide, or promise" from Circleback meetings — search by attendee, company, tag, or date before keyword, read the notes before the transcript, and cite the meeting behind every claim. Use when the user asks what happened on a call, what a customer or teammate said, what was agreed, or refers to a meeting, sync, demo, or interview.

ParadevAI/Paradev15,720 stars(GitHub 15,720 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Checking what was agreed with a customer
  • Finding who promised a deadline
  • Looking up exact wording in a meeting
  • Tracing a topic across recurring meetings

Overview

What it does

Searches Circleback meeting records to find what people said, decided, or promised. It can narrow meetings by attendees, company, tags, or dates, and reads meeting notes before consulting transcripts. When exact wording or numbers matter, it checks the transcript. Answers identify the meeting and date; for commitments or deadlines, they also name the speaker.

When it helps

Use it to check what was agreed in a sales conversation, find who committed to a deadline, or trace how a topic came up in recurring meetings. It distinguishes discussion, recorded follow-ups, and explicit agreement. If meeting records conflict, it reports the differences instead of silently choosing one account.

Example requests

  • “What did we agree on in the last meeting with this customer?”
  • “Check who promised the delivery date and find their exact words.”
  • “Look up how this topic was handled in our recurring meetings.”

Notes

The Circleback search and reading tools are required, and answers rely on records they can retrieve. AI-generated insights are not treated as definitive meeting records. If a meeting was not recorded, the skill can only check the calendar for a scheduled event. If it finds no matching record, it reports the search filters used.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Document check

AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).

SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt uses search and reading tools and does not treat generated insights as records.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingIt requires Circleback tools but gives no connection or setup instructions.

Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 29, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md3.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Find what was actually said

Circleback keeps notes, action items, insights, and a transcript for every captured meeting. The job is to find the right meeting, read what it records, and separate what was decided from what was discussed.

1. Filter by who and when before what

SearchMeetings matches keywords against titles and notes, and titles rarely contain the topic. Resolve people with FindProfiles and companies with FindCompanies, then search with profiles or domains and the date range the user gave you. Do not invent a date range to narrow results — if the user said "recently", say which window you used. Tags (ListTags) find a recurring series. Keep the intent argument honest: it is the user's question, and it shapes which excerpts the tool returns.

2. Notes first, transcript when the wording matters

ReadMeetings (up to 50 IDs at once) returns notes, attendees, action items, and insights — enough for "what was decided". Use SearchTranscripts to find where a phrase was said across meetings, and GetTranscriptsForMeetings when the exact words matter: a commitment, a number, a quote the user wants verbatim. Quote the line; never present a paraphrase as a quote.

3. Separate decided from discussed

An "agreed" line is a decision. An action item is a recorded follow-up, not proof that anyone agreed to what it follows from; call it a decision only when the notes or transcript show the agreement. A topic in the notes with no owner and no outcome was discussed, not decided; say so. Two meetings that disagree are a finding to report, not something to reconcile silently — the later one is not automatically right.

4. Cite the meeting

Every claim names the meeting and its date. For anything the user may act on — a promise to a customer, a deadline — also say who said it. When nothing matches, state the filters you searched (people, domain, dates, tags) so an empty answer can be checked. A meeting that was never captured leaves only a calendar event, which SearchCalendarEvents can confirm.

Anti-patterns

  • Keyword search first. Most meetings are found by attendee and date; keywords narrow, they do not locate.
  • Treating AI insights as the record. Insights are generated; the notes and the transcript are what happened.
  • Reading one instance of a recurring meeting. A weekly call decides things across weeks; check the neighbours before saying it never came up.
  • Paging blindly. Fetch the next page only when the last one was full and the question is still open.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

10x

FreeSummary

Review how you use Superset and identify unused features that fit your workflow. Get a short list of suggestions, learn about each option, and set up selected features such as scheduled agents, parallel workspaces, or shared tasks.

  • Find unused Superset features worth exploring
  • Set up scheduled agent tasks
  • Start parallel work in separate workspaces
ParadevAI/Paradev15.7KUpdated Oct 29, 2026

automate

FreeSummary

Set up recurring tasks in Superset with an agent prompt, a schedule or event trigger, and a chosen execution workspace. After explicit confirmation, create the automation, check its saved settings, and review a real first run.

  • Scheduling a daily or weekly agent task
  • Starting agent work when a GitHub pull request opens
  • Triggering tasks from selected Slack reactions
ParadevAI/Paradev15.7KUpdated Oct 29, 2026

browser

FreeSummary

Browse pages, click controls, fill fields, and inspect screenshots or console messages through Superset's browser pane. Use it to preview a running web app, check interface behavior, and work through browser tasks in a visible session.

  • Preview a locally running web app
  • Capture screenshots of a page
  • Inspect console errors
ParadevAI/Paradev15.7KUpdated Oct 29, 2026

Build Stripe payments, subscriptions, and invoicing using verified documentation and API parameter definitions. The skill guides product selection, sandbox testing, and webhook handling, where server notifications determine payment and subscription state.

  • Choose Stripe products for payments or recurring billing
  • Implement Checkout or invoice flows
  • Investigate Stripe code that compiles but behaves incorrectly
ParadevAI/Paradev15.7KUpdated Oct 29, 2026

cdp-verification

FreeSummary

Verify a UI change or reproduce a bug in the running desktop app using the Chrome DevTools Protocol (CDP), a browser debugging interface. Follow the real user journey and compare screenshots with measurements such as route, scroll position, and persisted state.

  • Reproducing a UI bug in the running app
  • Verifying a UI change end to end
  • Checking behavior after a route or workspace switch
ParadevAI/Paradev15.7KUpdated Oct 29, 2026

ci-triage

FreeSummary

Diagnose failed GitHub Actions runs by finding the first meaningful error, separating code problems from infrastructure issues and intermittent failures, and comparing the base branch. Get a focused report explaining the PR’s involvement and recommended next steps.

  • Investigating failed PR checks
  • Separating intermittent test failures from code defects
  • Checking whether the base branch already fails
ParadevAI/Paradev15.7KUpdated Oct 29, 2026

See all skills by ParadevAI

Report a problem with this skill