win-loss-reviewRun a monthly win-loss review of your CRM's closed deals, landed in context/ as one pull request: the ICP verified against won versus lost with a disqualifier, dated insights with counts and denominators, objections from recorded lost reasons, and a client file per closed-won account; a five-line Slack digest says what changed. Never edits a persona, nor the ICP after the first pass. Triggers: "verify our ICP against won and lost deals", "what do closed-lost deals say about who we should not sell to", "keep the context repo current from the CRM every month", "our lost reasons should become objections", "run a monthly win-loss review". Cargo project, harness claudeCode, HubSpot, Salesforce, Attio, Slack. Skip when: there is no CRM yet and the context should come from the website, which is web-capture; or you want one account researched before a call, which is research-account.
Install via ClawdBot CLI:
clawdbot install cargo-ai/win-loss-reviewGenerated Nov 21, 2026
A RevOps lead points the agent at their HubSpot pipeline once a month. It pulls every closed deal, compares won versus lost against the current ICP, and names a disqualifier that separates the two. Output lands as a single pull request in context/ with the ICP verification and dated insight files carrying counts and denominators.
Sales leadership wants the lost-reason field to actually drive enablement instead of sitting unread. The agent reads recorded lost reasons, checks the fill rate as a hygiene finding, and generates objection files where the CRM supports it. Each objection traces back to a query result in the run record so a reader can verify it.
A GTM engineering team already runs crm-enrichment and crm-deduplication and wants one shared copy of CRM data. Using the same crm_accounts and crm_contacts models, the agent appends monthly win-loss findings without duplicating extraction. Nothing is auto-merged, so the team reviews the PR before the next deploy syncs context into the workspace.
A startup with fewer than twenty closed-won deals runs the same review but gets hypothesis-mode output. Every finding carries its denominator and a confidence label, and the PR body states how many wins would turn it into an analysis. The team uses it to avoid overfitting strategy to a handful of deals while still logging what is changing.
A sales ops manager suspects closed deals are missing contact associations that block stakeholder mapping. The review opens with two hygiene findings, including deal-to-contact association rate, so the gap is visible every month. Insights about titles at won accounts show which roles correlate with wins, with counts tied to explicit denominators.
Per-user monthly or annual plans where win-loss patterns vary by account size and industry. The review surfaces which segments actually close and which lose, informing pricing and qualification without touching the ICP mid-cycle.
Revenue scales with consumption, so closed-deal analysis must separate true fit from accounts that churn after trial. Monthly win-loss runs show where deals are won and lost by segment, and disqualified deals reduce wasted usage-based trial spend.
Long sales cycles with committee buying where stakeholder mapping and objection handling decide outcomes. The review's association-rate hygiene finding and title-at-won-account insights directly target multi-threading and require Salesforce-style CRM adaptation.
💬 Integration Tip
Wire up the Cargo CLI, Anthropic, GitHub, Slack, and CRM connectors first, and confirm your repo has context/ and outputs/ at the root before the first run. Expect the initial pass to size the pipeline against the twenty-won-deal verify threshold, since below it every insight is marked hypothesis until your data fills out.
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.