agentleFS
Sign inStart free
heypastelheypastel/pastel-outbound-system/skills/priority-rank/SKILL.md

priority-rank

Skill2 starsChanged 56 days agoMITView on GitHub

Ranker — scores each lead 0-100 on signal, fit, seniority, reach, and timing next to Pastel's Copilot ranking, then splits the list into act now, warm up, and park. Use for "rank / prioritise these", before writing or launching, or to pick who gets messaged first.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Remove anyone already in a run or a conversation (pastel_list_sequence_runs(lead_id=…)) — they're not new outreach.

    line 34

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Priority rank — Ranker

House rules: ../command-center/shared/house-rules.md · Pastel tools: ../command-center/shared/pastel-tools.md

The ranking answers one question: who deserves one of today's limited LinkedIn slots?

Scorecard

PartPointsFull points when…
Signal40🔥 from intent-radar (🟠 = 25, 🟡 = 12)
Fit25All three gates open in fit-check
Seniority15Can sign or owns the budget (user = 8, champion without budget = 10)
Reach10Already connected, or engaged with us before (reachable cold = 5)
Timing10why-now is sharp (thin = 5, no-moment = 0)
PriorityDecision
70–100Act now — first message this week
50–69Warm up — social-warmup first, message later
0–49Park — stays in Pastel; revisit when a new signal arrives

Steps

  1. Take leads that passed fit-check and went through why-now.
  2. For leads from pastel_recommend_best_leads, use evidence as input: activity_intent_score and freshness_score inform Signal and Timing, lead_quality_score informs Fit (each 0–1). Show priority_score as "Copilot #n" — it's a ranking value on Pastel's own scale (often above 1000), never the total.
  3. Score every part visibly. Use outbound-brief.md's threshold instead of 70 if it sets one.
  4. Remove anyone already in a run or a conversation (pastel_list_sequence_runs(lead_id=…)) — they're not new outreach.

Output

# Priority — [date]
Act now: n · Warm up: n · Park: n

| # | Person | Company | Total | Signal | Fit | Seniority | Reach | Timing | Copilot | Decision |

Act now → message-writer. Warm up → social-warmup. Park → nothing, for now.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free