Systems Lab

Agent skill

weekly-report

Monday morning full pipeline review with metrics, channel performance, and forecast.

dormantSelf-containedInstructions only824 words

Filed under Analytics and reporting.

From ekatasingh1107/b2b-gtm-skills · 99 skills · 2 · pushed 2026-04-11

What it does when it runs

Monday morning full pipeline review with metrics, channel performance, and forecast. Reads all CRM tabs, calculates deltas vs previous week, and generates actionable recommendations.

Read from the skill and the 1 file bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about weekly-report

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/ekatasingh1107/b2b-gtm-skills.git /tmp/b2b-gtm-skills
git -C /tmp/b2b-gtm-skills sparse-checkout set "skills/playbooks/weekly-report"
mkdir -p ~/.claude/skills/weekly-report
cp -R "/tmp/b2b-gtm-skills/skills/playbooks/weekly-report/." ~/.claude/skills/weekly-report/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from ekatasingh1107/b2b-gtm-skills/blob/eae8dd0bb98da1c8e84abd297066a87015dd860f/skills/playbooks/weekly-report/SKILL.md, which is licensed MIT (repository). 824 words, 12 headings.

Weekly Report

Full pipeline review designed to run every Monday morning. Pulls data from all CRM tabs, computes week-over-week deltas, and generates a structured report with metrics, channel performance, lead quality analysis, revenue forecasting, and concrete recommendations for the week ahead.

Prerequisites

  • agency.config.json fully populated (run /agency-setup first)
  • CRM initialized with data from at least one week of pipeline activity
  • Tool stack configured (Apollo, email validator, email sender, LinkedIn tool)

Composites & Capabilities Used

  1. crm-writer -- read CRM data from all tabs
  2. pipeline-dashboard -- pull aggregated metrics (if built)

Phase 0: Data Collection

Read from CRM all tabs:

  • Pipeline tab: all leads with stages, scores, dates, and ownership
  • Outreach log: all actions this week (emails, LinkedIn, Instagram, calls)
  • Email drafts: sent vs drafted counts, subject lines, reply tracking
  • Calling tab: calls made, outcomes (connected, voicemail, no answer, meeting booked)
  • Dashboard tab: previous week's numbers for comparison

Pull the date range: Monday 00:00 through Sunday 23:59 of the reporting week.

Phase 1: Pipeline Metrics

Calculate and present:

WEEKLY PIPELINE REPORT -- Week of [Date]
===

PIPELINE SNAPSHOT:
- Total active leads: N (delta vs last week: +/-N)
- By stage:
  NEW:             N
  RESEARCHED:      N
  ENRICHED:        N
  OUTREACH_READY:  N
  CONTACTED:       N
  REPLIED:         N
  DEMO_BOOKED:     N
  WON:             N
  LOST:            N

NEW LEADS THIS WEEK: N
- Signal scan: N
- Platform scraper: N
- Inbound: N
- Referral: N

Include stage-by-stage delta vs previous week. Highlight any stage with > 20% change.

Phase 2: Outreach Performance

OUTREACH METRICS (Last 7 Days):
---
Emails:
- Sent: N
- Opens: N (X%) [if trackable]
- Replies: N (X%)
- Positive replies: N
- Demo from email: N

LinkedIn:
- Connections sent: N
- Accepted: N (X%)
- DMs sent: N
- Replies: N (X%)

Instagram:
- DMs sent: N
- Replies: N (X%)

Calls:
- Made: N
- Connected: N (X%)
- Meetings booked: N

BEST PERFORMING:
- Best email subject: "[subject]" (X% reply rate)
- Best channel: [channel] (X% response rate)
- Best touch point: Touch N (X% response rate)

Break down by day of week if enough data exists to surface timing patterns.

Phase 3: Lead Quality

LEAD QUALITY:
---
HOT leads generated: N
WARM leads generated: N
COOL leads (filtered): N

Conversion funnel:
Signal -> Lead: X%
Lead -> Enriched: X%
Enriched -> Contacted: X%
Contacted -> Replied: X%
Replied -> Demo: X%
Demo -> Won: X%

Average lead score: N
Top platforms by quality: [ranked list]

Flag any funnel stage with conversion below historical average.

Phase 4: Revenue Impact

REVENUE PIPELINE:
---
Demos booked this week: N
Demos booked total: N
Proposals sent: N
Deals in negotiation: N
Deals won this week: N
Revenue won: $X

Pipeline value (weighted):
- HOT leads * close rate: $X
- Demos scheduled: $X
- Proposals out: $X
Total pipeline value: $X

Use close rate estimates from agency.config.json if available, otherwise use industry defaults (HOT: 15%, Demo: 30%, Proposal: 50%).

Phase 5: Credit Usage

TOOL CREDITS:
---
Apollo credits used: N / N remaining
ZeroBounce credits used: N / N remaining
Email sends: N / N daily cap

Flag if any tool is below 20% remaining credits. Calculate projected depletion date at current burn rate.

Phase 6: Insights & Recommendations

Based on the data, generate 3-5 specific recommendations:

  • If reply rate < 3%: "Email copy needs revision. Consider testing new subject lines."
  • If LinkedIn outperforms email: "Shift more outreach to LinkedIn. Increase daily connection cap."
  • If HOT leads are low: "Expand signal scan to more platforms or broaden keywords."
  • If follow-ups are being missed: "N leads had overdue follow-ups. Catch up today."
  • If one segment outperforms: "India D2C segment has 2x reply rate. Prioritize."
  • If demo-to-won rate is dropping: "Review demo quality. Consider pre-qualifying harder."
  • If pipeline is top-heavy (many NEW, few CONTACTED): "Enrichment is the bottleneck. Allocate more time to Phase 2."

Each recommendation includes: observation, impact estimate, and suggested action.

Phase 7: Next Week Plan

Suggest adjustments based on this week's data:

  • Target lead count for next week (increase if pipeline is thin, maintain if healthy)
  • Channels to prioritize (based on Phase 2 performance data)
  • Cadence adjustments (touch timing, sequence changes)
  • Content angles to test (new subject lines, new value props, new case studies)
  • Specific accounts to focus on (stalled deals, high-value prospects)
NEXT WEEK TARGETS:
---
New leads: N
Enrichments: N
Outreach drafts: N
Follow-ups: N
Demos target: N
Calls target: N

PRIORITY ACTIONS:
1. [Specific action with owner and deadline]
2. [Specific action with owner and deadline]
3. [Specific action with owner and deadline]

Example Usage

Trigger phrases:

  • "Run the weekly report"
  • "Monday pipeline review"
  • "How did we do this week?"
  • "Generate weekly sales metrics"

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what weekly-report does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.