AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Intel Weekly Report

skill-b2bforce-b2bforce-intel-weekly-report · by b2bforce

>-

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-b2bforce-b2bforce-intel-weekly-report

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-b2bforce-b2bforce-intel-weekly-report)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Intel Weekly Report? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Weekly Intelligence Report

Aggregates detected website changes for monitored competitors over a period (default: last 7 days) into a single report with an AI summary.

Read First

  1. workspace/firm/profile.md — firm scope.
  2. Monitoring files from intel-competitor-monitoring:

workspace/intelligence/competitors/{slug}/changes/*.md, snapshots/{page-slug}/*.md, and pages.md.

When to Use

  • User wants a weekly digest / monitoring summary across competitors
  • Producing a shareable intelligence report
  • Scheduled or manual summary of significant changes

Workflow (per competitor)

1. Collect changed snapshots

For the period [period_start, period_end], collect change artifacts from:

workspace/intelligence/competitors/{slug}/changes/*.md

Include files where frontmatter changed_at falls inside the range. Significance is not filtered here; all detected changes count. Track:

  • pages_analyzed - count of rows in pages.md with Monitor=true
  • pages_with_changes - distinct page_slug values with change files in the

period

  • raw_changes[] - `{ url, pageslug, changetype, significance, changed_at,

business_summary }`

If pages_with_changes == 0, the summary is exactly "No changes detected during this reporting period." A report is still produced for the company in this case.

2. Business-impact summary

Use the current agent/LLM session to summarize the collected change files. Truncate the combined change text to 15000 chars (MAX_DIFF_LENGTH). Use this system prompt:

You are a business intelligence analyst specializing in competitive monitoring.
Your task is to summarize website changes detected on a monitored company's website.

Guidelines:
- Provide a concise summary in 3-5 sentences
- Focus on business-relevant changes (pricing, products, messaging, team changes)
- Highlight any strategic implications
- Use clear, professional language
- If changes seem minor/technical, note that briefly

User prompt: Summarize the following website changes detected on {name} ({url}):\n\n{diffs}

If no LLM summary is available, summarize the change files deterministically and mark ``.

3. Write the report

workspace/intelligence/reports/{YYYY-MM-DD}-{slug}-weekly.md

---
competitor: {slug}
period_start: 2026-05-25
period_end: 2026-06-01
pages_analyzed: 12
pages_with_changes: 3
generated: 2026-06-01
---

Body sections:

  1. Summary — the AI business-impact summary.
  2. Changed pages — per URL: what changed (1–2 lines from the diff).
  3. No-change note — if applicable.

4. Optional: roll-up across all competitors

A combined workspace/intelligence/reports/{YYYY-MM-DD}-weekly-rollup.md linking each per-competitor report.

Scheduling

Can be run manually by an agent or by one responsible automation runner. The generator is period-agnostic and accepts any [period_start, period_end]; previous 7 days is the recommended default.

Rules

  1. Only include pages with change artifacts in the period; never pad the report.
  2. Keep the AI summary to 3–5 sentences, business-focused.
  3. Reports are committed artifacts — write to workspace/intelligence/reports/.

Related Skills

| Skill | When | |-------|------| | intel-competitor-monitoring | Produces the snapshot/change files this report consumes | | intel-competitor-discovery | Expand the monitored set before reporting | | firm-context | Competitor list and firm scope |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.