Systems Lab

Agent skill

kpi-reporting

Produce a weekly GTM KPI report with north-star metric, leading + lagging indicators, what's-working/what's-not, WoW deltas, and recommended actions.

slowingNeeds a keyActs undeclared468 words

Filed under Analytics and reporting.

From devangk003/gtm-agent-skills · 32 skills · 0 · pushed 2026-06-18

What it does when it runs

Produce a weekly GTM KPI report with north-star metric, leading + lagging indicators, what's-working/what's-not, WoW deltas, and recommended actions. Use when the user says "weekly GTM report", "board snapshot", "SDR metrics", or "what's working this week.

Read from the skill and the 4 files 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
  • AGENTIC_APP_TOKEN
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 does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shell

Ask about kpi-reporting

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

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/devangk003/gtm-agent-skills.git /tmp/gtm-agent-skills
git -C /tmp/gtm-agent-skills sparse-checkout set "kpi-reporting"
mkdir -p ~/.claude/skills/kpi-reporting
cp -R "/tmp/gtm-agent-skills/kpi-reporting/." ~/.claude/skills/kpi-reporting/

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.

Before you install: this skill will not complete its job on a bare agent. It needs AGENTIC_APP_TOKEN, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from devangk003/gtm-agent-skills/blob/6b9a1b0094ffd83d6c02bc03b7ce1610661a1644/kpi-reporting/SKILL.md, which is licensed MIT (skill frontmatter). 468 words, 6 headings.

KPI Reporting

Produce the recurring GTM KPI report: north-star metric with trend, leading + lagging tables, per-channel summary, pipeline snapshot, what's-working/what's-not, WoW deltas + benchmarks, recommended actions. One screen (≤450 words top section); deeper data linked. Apple-MPP-aware: open rate excluded.

When to Use

  • Weekly GTM review — standard report
  • Board update needs a snapshot
  • SDR/AE coaching — activity vs outcome data
  • Q3 retro — what worked, what didn't
  • Something's off in pipeline — check the report
  • User says "weekly GTM report" or "board snapshot"

Quick Reference

ConceptValue
North-star (default)Pipeline-generated revenue (weighted pipeline added in window)
Leading metricsTouches sent / meetings booked / replies / discovery completion rate
Lagging metricsClosed-won revenue / deal count / win rate / forecast accuracy
Activity-vs-outcome pairingEvery leading metric paired with an outcome metric
WoW material-change flag±20%
Open rate exclusionAppears only with "noisy metric" caveat; never as KPI
One-screen rule≤450 words top section; deeper data linked

Procedure

  1. Validate window + sources. Pull data from functions 3/4/5/6 for the window. Flag freshness gaps. See ${HERMES_SKILL_DIR}/references/metric-definitions.md.
  2. Compute north-star + trend. Pipeline-generated revenue this period vs last vs 4-week avg. Express as: dollar + WoW % + 4w trend direction.
  3. Compute leading + lagging tables. Each metric: value + WoW absolute + WoW % + trend + benchmark. Activity paired with outcome.
  4. Per-channel summary. From channel-performance data: volume + reply/acceptance/connect rate + CPM trend.
  5. Pipeline snapshot. From pipeline-stages: stage distribution + stuck deals + cycle times + win rate per tier.
  6. What's-working / what's-not. 2–3 wins (improving WoW) + 2–3 concerns (degrading). Per finding: 1-line context + 1-line recommended action. See ${HERMES_SKILL_DIR}/references/report-template.md.
  7. Recommended actions per finding. Wins: "double down on X." Concerns: "investigate Y" with specific next step + named skill.
  8. Compose one-screen report. ≤450 words top: north-star + tables + what's-working/not. Deeper linked.
  9. Push + deliver. Full report as interaction:research. Deliver via Slack/email/Notion per config. See ${HERMES_SKILL_DIR}/scripts/push_to_crm.py.

Pitfalls

  • Open rate as KPI — Apple MPP noise; report only with explicit caveat
  • Touches sent as success metric — pair with replies/meetings/deals
  • One-screen → 12 pages — discipline matters; deeper data linked
  • Cherry-picking what's working — always include what's-not
  • Recommended actions vague — "improve email" → useless; "re-run data-enrichment for stale phones" → actionable
  • Forecast accuracy not surfaced — surface MAPE periodically

Verification

  1. Every metric value traces to a source skill's run
  2. Activity-vs-outcome pairing enforced
  3. One-screen ≤450 words
  4. What's-working + what's-not each have 2–3 items
  5. Recommendations are specific (named action + named skill)

Files bundled with it

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

Need help setting it up?

This page tells you what kpi-reporting 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.