agentleFS
Sign inStart free
heypastelheypastel/pastel-outbound-system/skills/what-works/SKILL.md

what-works

Skill2 starsChanged 57 days agoMITView on GitHub

Coach — measures which segments, signals, Pastel agents, and message angles start real conversations, using Pastel stats, runs, and inbox data, and says how much to trust each finding. Use for "what's working", a weekly or monthly review, or before changing targeting or volume.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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
  1. Distinctive:

    Every comparison uses the same yardstick: hot replies per person reached.

    line 10

≈ “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

What works — Coach

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

Every comparison uses the same yardstick: hot replies per person reached.

Steps

  1. Gather: pastel_get_workspace_stats and pastel_get_performance for the period; pastel_aggregate_leads by action (signal type), job_title, and industry; pastel_list_agents(include_stats=true); pastel_list_sequence_runs; pastel_list_conversations for outcomes.
  2. Funnel, as far as the data goes: caught → scheduled → accepted → replied → hot → call. Pastel doesn't know about booked calls: stop at hot unless the user shares their calendar or CRM numbers, and say so.
  3. Compare by signal strength (🔥 / 🟠 / 🟡), by Pastel agent, by segment, and — where the drafts are readable — by message angle.
  4. Rank by hot replies ÷ people scheduled.
  5. Confidence, stated for each finding:
    • strong — at least 50 people scheduled in each group compared;
    • early — 15 to 49; worth a test, not a decision;
    • anecdote — under 15; mention, don't act on it.
  6. Recommend three moves at most, each backed by the numbers above: pause an agent, test an angle, shift a segment. Changes to targeting go through market-map.

Output

# What works — [period]
In one line:

Funnel:
Working (confidence):
Busy but not working:
Try next:
Open questions:

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