inspect-pipeline-levers — Claude Code command: setup and features
inspect-pipeline-levers diagnoses sales pipeline coverage, conversion velocity, and deal friction directly inside CRM data.
Apache-2.0 ★ 450 updated 2026-04-03
.claude/commands/inspect-pipeline-levers.mdWhat inspect-pipeline-levers does
The command pulls pipeline tables, enrichment data, and coaching notes out of your CRM. Next, it splits records by product, region, or persona to calculate stage-to-stage transition times. At-risk opportunities get flagged alongside concrete next steps.
Execution relies on specialized agents and skills: pipeline-analytics-lead runs the core diagnostics, revenue-intelligence-director builds the executive memo, while deal-quality-model and cohort-analysis inspect hygiene signals against historical cohorts.
Without direct access to CRM records and deal notes, the underlying agents cannot compute stage leakage or velocity metrics.
What it helps with
- diagnose conversion leaks across pipeline stages
- identify stuck enterprise opportunities before quarter close
- compare segment win rates against historical cohort benchmarks
- generate pipeline risk memos for sales leadership
Example prompts for the agent
- /revenue-analytics:inspect-pipeline-levers --stage commit --segments enterprise --window 30d --output dashboard
- /revenue-analytics:inspect-pipeline-levers --stage qualify --window quarter --output memo
- /revenue-analytics:inspect-pipeline-levers --stage pipeline --metrics coverage,slip_rate --output slack
How to install inspect-pipeline-levers
Manually: put the files in place
.claude/commands/inspect-pipeline-levers.mdCall it with /inspect-pipeline-levers. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/inspect-pipeline-levers.mdCall it with /prompts:inspect-pipeline-levers. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/inspect-pipeline-levers.prompt.mdManually: put the files in place
.gemini/commands/inspect-pipeline-levers.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about inspect-pipeline-levers
How to install inspect-pipeline-levers in Claude Code?
Place the command specification file into .claude/commands/inspect-pipeline-levers.md in your repository.
What output formats are supported?
The command accepts dashboard, memo, csv, or slack through the --output parameter.
Which sub-agents and skills are invoked?
It orchestrates pipeline-analytics-lead and revenue-intelligence-director, plus the deal-quality-model and cohort-analysis skills.
Source text
inspect-pipeline-levers.md · Apache-2.0
--- name: inspect-pipeline-levers description: Diagnoses pipeline coverage, conversion velocity, and stuck deal patterns. usage: /revenue-analytics:inspect-pipeline-levers --stage commit --segments enterprise --window 30d --output dashboard --- # Command: inspect-pipeline-levers ## Inputs - **stage** – stage or grouping to inspect (create, qualify, pipeline, best-case, commit, closed). - **segments** – persona, region, product, or team filters. - **window** – lookback window (7d, 30d, quarter, custom). - **metrics** – focus metrics (coverage, velocity, win_rate, asp, slip_rate). - **output** – dashboard | memo | csv | slack. ## Workflow 1. **Data Extraction** – pull CRM pipeline tables plus enrichment fields and coach notes. 2. **Segmentation** – slice by requested segments, highlight outliers vs benchmark. 3. **Leakage & Velocity** – compute stage-to-stage conversion, cycle time, and stuck counts. 4. **Opportunity Drilldown** – flag top stuck/at-risk deals with context + next steps. 5. **Packaging & Alerts** – produce requested view plus Slack/Email summary for owners. ## Outputs - Pipeline lever dashboard with stage conversion, velocity, and coverage deltas. - Stuck/at-risk deal list with recommended plays. - Summary memo highlighting root causes + action plan. ## Agent/Skill Invocations - `pipeline-analytics-lead` – runs diagnostics + highlights at-risk segments. - `revenue-intelligence-director` – frames executive-ready narrative. - `deal-quality-model` skill – evaluates opportunity hygiene + win signals. - `cohort-analysis` skill – benchmarks performance vs historical cohorts. ---
© gtmagents · Apache-2.0 · gtmagents/gtm-agents