pipeline-manager
Skill9 starsChanged 6 months agoMITView on GitHub
Manage the sales pipeline: add/update prospects, score with FIT+INTENT+TIMING, track stage transitions, generate status reports. Central orchestrator for all pipeline skills. For signal detection, see signal-scanner. For outreach execution, see outreach-sender.
In this repository78 other files it gives its agents.
- anti-pattern-auditSkill
- brand-storytellingSkill
- business-investigationSkill
- ceo-weekly-reviewSkill
- cold-emailSkill
- community-buildingSkill
- company-intelSkill
- competitive-analysisSkill
- competitor-researchSkill
- composio-cliSkill
- conducting-user-interviewsSkill
- content-strategySkill
- copywritingSkill
- daily-recapSkill
- decision-playbookSkill
- designing-growth-loopsSkill
- discovery-debriefSkill
- email-sequenceSkill
- enterprise-salesSkill
- evening-recapSkill
- exa-code-searchSkill
- exa-company-researchSkill
- exa-lead-genSkill
- exa-people-researchSkill
- exa-personal-siteSkill
- exa-x-searchSkill
- feedback-trackerSkill
- find-email-by-nameSkill
- focus-keeperSkill
- founder-salesSkill
- fpf-problem-solvingSkill
- github-stars-monitorSkill
- google-calendarSkill
- grafana-monitoringSkill
- humanizerSkill
- hypothesis-trackerSkill
- idea-generatorSkill
- install-openclaw-to-digitaloceanSkill
- install-openclaw-to-hetznerSkill
- install-openclaw-to-ycSkill
- launch-marketingSkill
- lead-enrichmentSkill
- measuring-product-market-fitSkill
- meeting-prepSkill
- metrics-briefingSkill
- morning-briefSkill
- openclaw-guideSkill
- openclaw-user-onboardingSkill
- orthogonalSkill
- outreach-senderSkill
- person-lookupSkill
- ph-launch-timelineSkill
- positioning-messagingSkill
- positioning-workshopSkill
- posthog-analyticsSkill
- prepare-yc-workshopSkill
- pricing-strategySkill
- problem-definitionSkill
- product-hunt-launchSkill
- product-led-salesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Before helping, read MEMORY.md for: current wedge, ICP, competitors, PMF stage.
- Very specific: line 20
All prospect data lives in memory/pipeline.json.
- Distinctive: line 61
When a new prospect is identified (via signal-scanner, manual, or inbound):
- Very specific: line 63
Check if prospect already exists in pipeline.json (match by domain)
- Very specific: line 64
If new: create entry with initial data, set stage = signal_detected
- Distinctive: line 69
25-49: Add to nurture list
- Distinctive: line 75
When new information arrives (enrichment, reply, meeting):
- Very specific: line 77
Read current prospect state from pipeline.json
- Very specific: line 82
Write back to pipeline.json
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
[YOUR_PRODUCT] Context
Before helping, read MEMORY.md for: current wedge, ICP, competitors, PMF stage.
Pipeline state lives in memory/pipeline.json. Read it at the start of every pipeline operation.
Output in Russian (company names, emails, scores in original).
For chat platforms: compact pipeline card, max 15 lines.
Pipeline Manager
Central orchestrator for the full-cycle sales pipeline. Manages prospect state, scoring, stage transitions, and reporting.
Pipeline State
All prospect data lives in memory/pipeline.json. Structure:
{
"prospects": [{
"id": "company-slug",
"company": "Company Name",
"domain": "company.com",
"contact": {
"name": "Full Name",
"title": "VP Engineering",
"email": "name@company.com",
"linkedin": "linkedin.com/in/username"
},
"scores": {
"fit": 0,
"intent": 0,
"timing": 0,
"total": 0
},
"stage": "signal_detected",
"signals": [],
"outreach": [],
"next_action": { "type": "", "date": "", "detail": "" },
"notes": "",
"created": "ISO",
"updated": "ISO"
}],
"stats": {
"total": 0,
"by_stage": {},
"last_scan": "",
"last_review": ""
}
}Operations
1. Add Prospect
When a new prospect is identified (via signal-scanner, manual, or inbound):
- Check if prospect already exists in pipeline.json (match by domain)
- If new: create entry with initial data, set stage =
signal_detected - Score using FIT+INTENT+TIMING (see Scoring below)
- Route based on score:
- 75+: Notify CEO immediately via Telegram. Tag as priority.
- 50-74: Queue for agent-drafted outreach
- 25-49: Add to nurture list
- <25: Monitor, re-score next month
- Log via
structured-log
2. Update Prospect
When new information arrives (enrichment, reply, meeting):
- Read current prospect state from pipeline.json
- Update relevant fields
- Re-score if new signals detected
- Advance stage if transition criteria met
- Set next_action with date and detail
- Write back to pipeline.json
3. Stage Transitions
signal_detected → researched → qualified → outreach_sent →
follow_up_1 → follow_up_2 → follow_up_3 →
meeting_booked → discovery_done → proposal_sent →
closed_won | closed_lost | nurtureTransition triggers:
signal_detected→researched: company-intel + person-lookup + lead-enrichment completedresearched→qualified: FIT+INTENT+TIMING score calculated, ≥25qualified→outreach_sent: CEO approved draft, email sent via outreach-senderoutreach_sent→follow_up_N: Automatic by cadence (Day 3/5/7/10)- Any →
meeting_booked: Reply with meeting intent received meeting_booked→discovery_done: After call + discovery-debrief completeddiscovery_done→proposal_sent: Proposal or demo delivered- Terminal:
closed_won,closed_lost,nurture
4. Pipeline Report
Generate a pipeline status report. Use for weekly reviews or on-demand.
Report contents:
- Total prospects by stage (funnel visualization)
- Top 5 highest-scored prospects with next actions
- Stale prospects (>7 days without activity)
- Conversion rates between stages (if enough data)
- Signals detected this week vs last week
- Outreach stats: sent, replied, bounced, meetings booked
Telegram format:
Pipeline Report [date]:
[N] total | [N] active | [N] stale
Top prospects:
1. Company (score) — stage — next action
2. ...
This week: [N] signals, [N] outreach, [N] replies
Conversion: signal→meeting [X]%FIT+INTENT+TIMING Scoring
FIT (0-40) — ICP Match
| Factor | Points | Criteria |
| Company size | 0-10 | Score against the size bands in your ICP from MEMORY.md (e.g. sweet spot=10, adjacent=5, edge=2) |
| Use-case complexity | 0-10 | Score against the complexity profile that matches your wedge (e.g. high=10, medium=7, low=3) |
| Tool maturity | 0-10 | Active in the category=10, evaluating=7, greenfield=3 |
| Budget authority | 0-10 | VP+ contact=10, team lead=7, IC=3 |
INTENT (0-40) — Active Buying Signals
| Signal | Points |
| Pain language (public) | 8-10 |
| Competitor evaluation | 8-10 |
| Active hiring (AI/DevTools) | 6-8 |
| Tech stack changes | 6-8 |
| Published content on pain | 5-6 |
| Event attendance | 3-5 |
TIMING (0-20) — Window Open
| Factor | Points |
| Funding (<90 days) | 8-10 |
| Hiring surge | 5-8 |
| Leadership change | 5-7 |
| Quarter start | 3-5 |
| Signal freshness (<7d) | 5 |
Score Routing
| Score | Action |
| 75-100 | CEO direct outreach, personalized demo |
| 50-74 | Agent drafts, CEO approves |
| 25-49 | Nurture sequence |
| 0-24 | Monitor, re-score monthly |
Self-Optimization (Weekly Review)
During weekly pipeline-review:
- Calculate conversion rates by stage
- Identify which signal types → highest reply rates
- Identify which outreach templates → highest reply rates
- Flag patterns: "Funding signal + CTO contact → 3x better than hiring signal + IC"
- Recommend weight adjustments for next week
- Log insights via structured-log, promote to MEMORY.md if confirmed 2+ times
Related Skills
- signal-scanner — detects signals that feed into pipeline
- outreach-sender — executes outreach from pipeline
- meeting-prep — prepares for meetings with pipeline prospects
- prospect-demo — generates [YOUR_PRODUCT] demos for prospects
- founder-sales — sales strategy and discovery framework
- sales-qualification — qualification framework
- structured-log — logging pipeline events
- hypothesis-tracker — tracking outreach template hypotheses
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.

