agentleFS
heypastelheypastel/pastel-outbound-system/skills/why-now/SKILL.md

why-now

Skill2 starsChanged 56 days agoMITView on GitHub

Detective — builds a one-sentence reason to talk to a specific person now, from what they did (Pastel signal), what changed around them (company news), and what they care about (their posts). Use to research a lead or an account, after fit-check, before writing.

The file

Files
SKILL.md

Why now — Detective

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

The output is a single sentence that ties this person to this week. Everything else is working notes.

Three sources, one sentence

For each lead marked yes:

  1. What they did — the Pastel signal: pastel_get_details, and the post or comment itself.
  2. What changed around them — company news from the last 90 days: a launch, a hire, a round, a new market. Company website, LinkedIn page, blog, press page. Dates matter more than adjectives.
  3. What they care about — their own recent posts (pastel_query_posts with their name), and the words they use for their work.

Then write why now in their language: "You asked your network last week how other teams handle X, two months after opening Y."

Quality bar

  • Specific: it names something only this person did, said, or is going through.
  • Dated: it points to something from the last 90 days. Without that, mark it no-moment — priority-rank scores it lower.
  • Ours to say: the proof it leans on comes from outbound-brief.md, never from assumptions.

Output per lead

lead_id:
did:         # the signal, dated
changed:     # company news, dated, or "nothing found"
cares_about: # from their posts, or "no posts"
why_now:     # one sentence
proof:       # from outbound-brief.md only
avoid:
quality: sharp | thin | no-moment
sources:

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.