manage-pipeline
Skill1 starsChanged 3 months agoMITView on GitHub
Review and advance every lead and deal — stages, next actions, follow-ups due, stalled-deal plays, honest forecasting. Run on a standing rhythm (at least weekly) and before any planning conversation.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-funnelSkill
- close-dealSkill
- connect-toolsSkill
- create-contentSkill
- define-positioningSkill
- design-offerSkill
- experimentSkill
- grow-referralsSkill
- grow-seoSkill
- health-checkSkill
- launch-campaignSkill
- launch-productSkill
- measureSkill
- plan-strategySkill
- research-marketSkill
- review-monthlySkill
- run-adsSkill
- run-outboundSkill
- run-partnershipsSkill
- setup-teamSkill
- tune-revopsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Fire due follow-ups: Every follow-up due today/overdue is drafted and sent (within existing approvals) or queued for the operator where a …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/manage-pipeline — Nothing Falls Through
Inputs: knowledge/pipeline.md, deal files in knowledge/deals/, knowledge/tool-registry.md (CRM if connected).
Agents: sales-developer (top of funnel) + deal-closer (active deals); growth-analyst for forecast math.
Method: knowledge/methods/outbound-prospecting.md (cadence), knowledge/methods/consultative-selling.md (advances).
Steps
- Sync sources. If a CRM is connected, reconcile it with
knowledge/pipeline.md(the knowledge file remains the team's source of truth; tools-operator syncs). While reconciling, run hygiene basics: merge obvious duplicates, correct entries sitting in the wrong stage, flag contacts with no dated next action. Recurring hygiene problems, scoring, routing, and CRM configuration belong to/tune-revops— flag, don't improvise. B2C businesses: "pipeline" = leads/subscribers and their follow-up flows — same review, different shape. - Walk every entry. For each lead/deal: stage correct? last touch when? next action with a date — the non-negotiable field. Anything without one gets one now.
- Fire due follow-ups. Every follow-up due today/overdue is drafted and sent (within existing approvals) or queued for the operator where a human step is needed (e.g., a call).
- Stalled-deal plays. Anything silent past its expected rhythm gets a play: a new value touch, a different channel, a direct "should we close the file?" note — or honest disqualification. A clean no beats a zombie deal; disqualify without drama and log why.
- Forecast honestly. Deals by stage × historical conversion (or conservative defaults early on;
/tune-revopsmaintains the stage-conversion rates once enough history exists). Flag the gap between forecast and target while there's time to fix it — the fix is usually more top-of-funnel activity now (see the lag principle in the method). - Report. Pipeline summary: adds, advances, stalls, closes (won/lost with reasons), forecast vs target, and the one bottleneck stage.
Before you start
- Required inputs:
knowledge/pipeline.mdatseeded+ (ships seeded); deal files as they exist. - Scan
knowledge/decision-log.mdfor tagpipeline— stage definitions and disqualification rules are recorded decisions. - Gate check: due follow-ups send only under existing outbound approvals; anything outside a covered sequence queues for approval.
If things go wrong
- CRM and knowledge file disagree → the knowledge file wins for state, but investigate why (usually a sync gap); recurring divergence →
/tune-revops. - A follow-up requires a human step (call, meeting) and the operator is unavailable → schedule it in
knowledge/pending.mdwith the prepared talking points. - Pipeline is empty → that's a finding, not a failure: report it and route to
/run-outbound(B2B) or the traffic skills (B2C).
Outputs
An accurate pipeline with a dated next action on every entry; the summary for the operator/scorecard. Close with the report per templates/skill-report.md.
Writeback
knowledge/pipeline.md + touched deal files; wins/losses + reasons to knowledge/results-history.md; process learnings (tag: pipeline) to knowledge/decision-log.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

