agentleFS
Faaz17Faaz17/Agents-and-Skills/skills/outreach/outreach-status/SKILL.md

outreach-status

Skill1 starsChanged 2 months agoMITView on GitHub

Report where the internship outreach stands for one or both people — what is sent, awaiting reply, due for follow-up, and the literal next action. Use when starting a session cold, or when asked "where are we" or "what's next".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 are 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.

  • 5

    Very specific

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

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

    Do the tracker rows match the files in sent/?

    line 22
  2. Very specific:

    Say so explicitly where they disagree: If PROJECT_NOTES claims Phase 3 and shared/companies/ is empty, the project is in Phase 2.

    line 24
  3. Very specific:

    If PROJECT_NOTES says a phase is done and the deliverable is not on disk, the phase is not done.

    line 67
  4. Very specific:

    Never report a contact as verified when the tracker says pattern or unverified.

    line 68
  5. Very specific:

    Senders in different fields do not share a target list: Never report one sender's state against another's targets.

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

/outreach-status, the honest snapshot

Usage: /outreach-status (both) · /outreach-status "<Person Name>"

Fast and honest. No encouragement, no padding.

Steps

  1. Read .claude/PROJECT_NOTES.md — the phase tracker and next action are the stated position.
  2. Check the stated position against what is on disk. Notes drift and stale notes mislead the next session:
    • Does <person>/cv/ actually contain a CV, or is the profile still running on vault data?
    • Does profile.md still contain TBD?
    • How many files are actually in drafts/ versus sent/?
    • Does shared/companies/ have real dossiers or empty stubs?
    • Does shared/targets.md have real companies or only the seed list?
    • Do the tracker rows match the files in sent/?
  3. Say so explicitly where they disagree. If PROJECT_NOTES claims Phase 3 and shared/companies/ is empty, the project is in Phase 2.
  4. Compute what is due — spawn followup_planner if anything has been sent.
  5. Report per person, then the shared state.
  6. Give exactly one next action. The plan lists everything; this skill picks the next thing.

Output format

## Outreach status — <date>

### Phase: <n, name> (<on track | behind | blocked>)

### <Person Name>
Profile: complete | TBD in <fields>
Sent: <n> · Awaiting reply: <n> · Replied: <n> · No-reply: <n>
Follow-ups due: <n>
In drafts: <n> (<statuses>)

### <Second Person>
<same>

### Shared
Targets: <n> (T1 <n> / T2 <n> / T3 <n>)
Dossiers written: <n>
Contacts verified: <n> of <n>

### Notes vs reality
<discrepancies, or "consistent">

### Blocked on
<what, and who has to unblock it>

## Next action (do this literally next)
<one concrete step>

Rules

  • One next action, not five.
  • Respect phase discipline. Never suggest a Phase N+1 task while Phase N's deliverable does not exist.
  • If PROJECT_NOTES says a phase is done and the deliverable is not on disk, the phase is not done. Say it.
  • Never report a contact as verified when the tracker says pattern or unverified.
  • Report reply rates as they are. A zero reply rate after ten sends is information about the angle, and hiding it wastes the next ten.
  • Senders in different fields do not share a target list. Never report one sender's state against another's targets. While a sender still has open questions in their profile.md, lead with those.

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.