agentleFS
bottyBotzbottyBotz/claude-rolodex/.claude/skills/rolodex/SKILL.md

rolodex

Skill0 starsChanged 6 months agoMITView on GitHub

Use whenever the user is logging, querying, or preparing for an interaction with a known person in their personal or professional network. Triggers on phrases like "[name] mentioned/said/is", "prep me for [name]", "what do I know about [name]", "who haven't I talked to lately". Do NOT use for strangers, public figures, or generic scheduling without a person attached.

  • Commits and pushes

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Edge-City/agentvillage-skills★ 1same 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.

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:

    After the confirmation, do the file work + git add + git commit + git push silently.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Rolodex

Personal CRM. People live in people/<slug>.md. Each capture flows: confirm → write → commit → push.

Data model

Filename: people/<firstname>-<distinguisher>.md. Lowercase, hyphenated, permanent. Distinguisher = employer, relationship, or whatever's most memorable. Never rename on job change — update frontmatter instead.

Frontmatter:

---
name: Alex Rivera
slug: alex-acme
aliases: [Alex, Al]
role: Lead AI Engineer
employer: Acme
based_in: Springfield
relationship: colleague
last_contact: 2026-05-07
summary_through: 2026-05-07
birthday: 1989-03-14
---

last_contact = date of newest Log entry. summary_through = date of newest Log entry as of the last Summary regen. Optional fields: anniversary, pronouns, anything else useful — frontmatter is open.

Body sections, in this order:

  1. ## Summary — 2–4 sentences. Regenerated lazily by /prep.
  2. ## Facts — bullet list of stable traits.
  3. ## Open threads — pending follow-ups (things you owe them, things they owe you, topics to revisit).
  4. ## Log — dated bullets, newest at top: - YYYY-MM-DD — <gist>.

Router

Decide which sub-skill file to read before acting:

  1. Bare name matches >1 file → read .claude/skills/rolodex/disambiguate.md first.
  2. User is logging new info about a person:
    • New info contradicts an existing Fact or structured frontmatter field → read .claude/skills/rolodex/update.md.
    • Otherwise → read .claude/skills/rolodex/add.md.
  3. User wants a brief on someone ("prep me for X", "what do I know about X") → read .claude/skills/rolodex/prep.md.
  4. User wants a query across people ("who works at X", "whose birthday is in May") → read .claude/skills/rolodex/find.md.

New-person signal ("just met", "new contact", "introduce X") → skip disambiguation, go straight to add.md step 3.

Confirmation contract

Always reply with the confirmation line BEFORE writing, committing, or pushing. The user is on mobile and wants to close the app immediately.

  • New log → ✓ Logged <slug>: <gist>
  • Fact update → ✓ Updated <slug>: <field> → <new-value>
  • New person → ✓ New: <slug>
  • Synthesis (/prep, /who, /stale, /upcoming) → no ✓ prefix; just return the answer.

After the confirmation, do the file work + git add + git commit + git push silently. Only surface output if there's an error.

Commit conventions

Single-line, lowercase, slug-based. Push to origin/main non-interactively.

  • log: <slug> <gist>
  • update: <slug> <field> <new-value>
  • new: <slug>
  • prep: <slug> summary regen (only when /prep actually regenerates)

Truncate the gist to ~60 chars in the commit subject if it runs long.

Date handling

Resolve every relative date ("today", "yesterday", "last Thursday", "two weeks ago") to absolute YYYY-MM-DD before writing. Use the session date as "today". Never write a relative date into a file.

Read-only ops

/prep, /who, /stale, /upcoming are read-only by default. The single exception: /prep may regenerate and commit a stale Summary (see prep.md).

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.