signal-scanner
Skill9 starsChanged 6 months agoMITView on GitHub
Scan for buying signals across ICP companies using Exa and social listening. Detects 7 signal types (hiring, funding, pain language, competitor mentions, tech stack changes, content, news), scores them, and routes to pipeline-manager. Run as daily cron or on-demand. For manual prospect research, see exa-company-research.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- sami2919/SignalForcetheir own version, first seen Aug 4, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- sami2919/SignalForce★ 9same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- pipeline-managerSkill
- positioning-messagingSkill
- positioning-workshopSkill
- posthog-analyticsSkill
- prepare-yc-workshopSkill
- pricing-strategySkill
- problem-definitionSkill
- product-hunt-launchSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Before scanning, read MEMORY.md for: current ICP, wedge, competitors.
- Very specific: line 10
Read memory/pipeline.json to avoid re-detecting known prospects.
- Distinctive: line 11
Follow output preferences from USER.md.
- Distinctive: line 104
When CEO asks "scan for signals" or "find new prospects":
- Distinctive: line 105
Ask for focus (or use default ICP from MEMORY.md)
- Distinctive: line 106
Run all 7 signal scans with wider date range (7-14 days)
- Distinctive: line 108
Ask which to add to pipeline
- Distinctive: line 112
Before adding to pipeline, verify against ICP criteria from MEMORY.md.
- Very specific: line 141
Use startPublishedDate to avoid re-scanning old content
≈ “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
Context
Before scanning, read MEMORY.md for: current ICP, wedge, competitors.
Read memory/pipeline.json to avoid re-detecting known prospects.
Follow output preferences from USER.md.
For chat platforms: compact signal list, max 15 lines.
Signal Scanner
Automated buying signal detection for your ICP. Scans multiple sources, scores signals, and feeds qualified prospects into the pipeline.
Signal Types (7)
Tier 1: High-Value (7-9 pts, respond in 24-48h)
1. Leadership Changes / Job Moves (9 pts)
exa-search__web_search_advanced_exa \
query="new CTO OR new VP Engineering OR Head of Engineering hired" \
category=company \
numResults=20 \
startPublishedDate="YYYY-MM-DD"Window: 2-4 weeks after announcement.
2. Funding Rounds (9 pts)
exa-search__web_search_advanced_exa \
query="series A OR series B OR funding round developer tools OR engineering platform" \
category=news \
numResults=20 \
startPublishedDate="YYYY-MM-DD"Window: 2-6 weeks post-announcement.
3. Hiring Surge — Target Roles (8 pts)
exa-search__web_search_advanced_exa \
query="hiring [TARGET_ROLE] OR [TARGET_TEAM] expansion [YOUR_DOMAIN_KEYWORDS]" \
category=company \
numResults=20Window: Active while postings live.
Tier 2: Medium-Value (6-7 pts, respond in 1-2 weeks)
4. Competitor Mentions (7 pts)
exa-search__web_search_advanced_exa \
query="[COMPETITOR_A] OR [COMPETITOR_B] OR [COMPETITOR_C] OR [COMPETITOR_D] review evaluation" \
category=tweet \
numResults=20 \
startPublishedDate="YYYY-MM-DD"5. Tech Stack Changes (7 pts)
exa-search__web_search_advanced_exa \
query="[TECH_MIGRATION_KEYWORDS related to your wedge — e.g. migrating to X, modernizing Y, adopting Z]" \
numResults=20 \
startPublishedDate="YYYY-MM-DD"6. Published Content on Pain (6 pts)
exa-search__web_search_advanced_exa \
query="[PAIN_KEYWORDS your buyers complain about publicly]" \
numResults=20 \
startPublishedDate="YYYY-MM-DD"7. Company News / Expansion (6 pts)
exa-search__web_search_advanced_exa \
query="[TARGET_TEAM] expansion OR new [TARGET_LOCATION] office OR [JTBD_KEYWORDS]" \
category=news \
numResults=20 \
startPublishedDate="YYYY-MM-DD"Scan Workflow
Daily Cron Mode
- Set date range —
startPublishedDate= yesterday's date (YYYY-MM-DD) - Run Tier 1 scans (3 queries) — highest value signals first
- Run Tier 2 scans (4 queries) — if Tier 1 yields <3 results
- Deduplicate — Match against existing pipeline.json prospects by domain
- Score each signal — Assign points based on signal type
- ICP filter — Quick check against ICP criteria from MEMORY.md
- Route to pipeline-manager:
- New prospects: Add with stage
signal_detected - Existing prospects: Update signals array, re-score
- New prospects: Add with stage
- Report to chat — Summary of new signals detected
On-Demand Mode
When CEO asks "scan for signals" or "find new prospects":
- Ask for focus (or use default ICP from MEMORY.md)
- Run all 7 signal scans with wider date range (7-14 days)
- Present top 10 signals ranked by score
- Ask which to add to pipeline
ICP Quick Filter
Before adding to pipeline, verify against ICP criteria from MEMORY.md. Typical filter slots:
- Must have: [must-have buyer attributes]
- Must have: [must-have company attributes]
- Nice to have: [intent signals]
- Disqualify: [auto-reject patterns]
Output Format (Chat)
Signal Scan [date]:
[N] new signals detected
Tier 1 (respond today):
1. [Company] — [signal type] — [detail snippet]
Score: [N] | Size: [N] [headcount metric]
Tier 2 (respond this week):
2. [Company] — [signal type] — [detail snippet]
...
Already in pipeline: [N] updated
Next scan: [tomorrow date]Cost Management
- Each Exa search: ~$0.01-0.05
- Daily scan (7 queries): ~$0.15-0.35
- Monthly: ~$3-7
- Use
startPublishedDateto avoid re-scanning old content - Skip Tier 2 if Tier 1 yields enough (>5 new signals)
Related Skills
- pipeline-manager — receives and stores detected signals
- exa-company-research — deeper research on a specific company
- exa-people-research — find contacts at detected companies
- social-listening — deeper social media monitoring
- competitor-research — competitor-specific intelligence
- lead-enrichment — enrich detected prospects
- company-intel — full company dossier
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.

