Skip to content

gooseworks-ai/goose-skills / skills/marketing/research-competitors

research-competitors

Verified

Competitor research: what every main rival is running, launching, charging and saying now, what works for them, and what that means for you. Use when the marketer asks for competitor research or a teardown, "what ads are my competitors running", "how do they price", "find gaps and angles", "what changed this week" (a weekly watch), or "X just launched / shut down / cut prices" (react now). Also builds a sales battlecard, checks a competitor page's tools/pixels, or studies who engages with their LinkedIn posts. Delivers a readable report saved to the brand, so the next run reports what changed. Never copies their words or disparages them. Not for what people say about you or your market — use research-market; not for who your buyers are — use research-audience.

tests/examples/2026-10-22/engagement-report.md

View on GitHub
# BillPilot LinkedIn engagement — 22 October 2026

## In short

**What we looked at:** a fictional supplied export covering two posts published 1–22 October; these are not a full company feed. Engagement dates were not the window filter.

1. **Five distinct person/post/type rows remain from nine raw rows, covering four people** — confirmed within this supplied export after exclusions and dedupe.
2. **The rows include three comments and two reactions** — confirmed within the export. One reaction has no engagement date; a reaction alone does not show a problem or buying intent.

**So, do this first (because of 1 and 2):** the analyst should use this as engagement evidence; qualify current roles/accounts separately before calling anyone a prospect.

## Decisions for you

None for this export test. A fresh managed extraction still needs a verified live route, quoted cost and the user's approval.

## Posts inspected

| Supplied post | Published | Reactions | Comments | Coverage |
|---|---|---|---|---|
| [Review post](https://www.linkedin.com/posts/billpilot_review-activity-101/) | 10 Oct | 220 | 12 | Supplied post only |
| [Export post](https://www.linkedin.com/posts/billpilot_export-activity-102/) | 12 Oct | 110 | 8 | Supplied post only |

Counts are from the [supplied metadata](../../fixtures/focused-evidence.md), captured 22 October; URLs are fictional fixture values. No ranking substitute was made because the request named these posts. The engagement export is a sample, not all 350 visible post interactions.

## Reconciliation and private rows

| Stage | Count |
|---|---|
| Raw rows supplied | 9 |
| Exact duplicate person/post/type | 1 |
| Rival staff identified by export | 1 |
| Missing profile URL | 1 |
| Post outside the supplied selection | 1 |
| Kept person/post/type rows | 5 |
| Unique people by profile URL | 4 |

[Private engagement rows](engagers.csv) and [exclusions](excluded.csv) are local fixture outputs. In a brand run, these files stay in the brand workspace and are not imported to the brain. Names, profile links and comment text are deliberately absent from this aggregate report. Two separate people sharing a name remain distinct; a person's comment and reaction remain separate evidence rows. One formula-like comment was escaped for spreadsheet viewing; the original stays in the supplied source export.

## Audience observations

The supplied headlines suggest two controllers, one AP lead and one marketing manager. These are first-look role statements from the export, not independently verified employment or qualified prospects. The marketing role falls outside the supplied controller/AP groups. Reaction rows receive no invented pain or intent tag.

## What to do

1. If the user requests a prospect list, the analyst checks current company/role evidence, account fit and suppression using the existing list workflow. Success: each retained prospect has independently supported fit and an honest contact route.

## What we're not doing

No outreach, inferred consent, email finding or claim that a like proves dissatisfaction. No names or contact rows are saved as brand learning.

## What we couldn't check

Managed commenter/reactor collection, complete company-feed pagination, all interactions, current employment and the unknown reaction date. This verifies supplied-export processing only. With an engagement-date filter, that unknown-date row would be excluded or left uncounted.

## Sources

[Supplied metadata and research context](../../fixtures/focused-evidence.md) and the private [original export](../../fixtures/engagers.csv), 22 October 2026. Source skew: fictional exported sample with no live collection. No paid call, live save or external message occurred.
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall