agentleFS
askoulwassimaskoulwassim/perfect-placement/skills/inbox/SKILL.md

inbox

Skill3 starsChanged 34 days agoMITView on GitHub

Read Gmail (read-only) for replies about roles in the pipeline, classify each message (confirmation, interview request, offer, rejection, outreach reply, other) with a probability, and hand the verdicts to the `inbox.ingest` op, which applies the confidence x impact policy and moves roles forward with the no-downgrade guard. Never replies, archives, deletes or sends.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use task, tasks and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • endlessblinkSkill

    task

    Create a new task in MASTER_PLAN.md with auto-generated sequential IDs. Supports TASK, BUG, FEATURE, and INQUIRY types. Triggers on "/task", "add task", "new task", "create task", "track this".

    Also in 3 projects that use this

  • genomewalkerSkill

    tasks

    Browse and resume tasks, threads, and background jobs across sessions

    Also in 3 projects that use this

  • AnthropicSkill

    onboarding

    Generate an onboarding checklist and first-week plan for a new hire. Use when someone has a start date coming up, building the pre-start task list (accounts, equipment, buddy), scheduling Day 1 and Week 1, or setting 30/60/90-day goals for a new team member.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 6 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Read-only on email: search and read only. Never send, reply, forward, draft, archive, trash, delete, label, mark spam or mark read (those …

    line 49
  2. Distinctive:

    Every write is an op. Never submit an application or send an email.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “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

Inbox

Turn application replies into pipeline movement, for every company in the pipeline. You supply the classification and its probability; inbox.ingest does the rest: policy per message (confident -> applied now with a 24h undo, unsure -> Needs you with your pick attached), status moves, interview rows, events, the run log, and skipping messages it already handled.

When

Daily (scheduled) once applications are out, and on demand.

Steps

  1. runs.start { skill: "inbox" }.
  2. Watch set: roles.list { status: ["draft-ready", "applied", "interviews", "offers", "active"] } plus outreach in Gmail (in_gmail drafts). Derive companies from it; never hardcode a company or sender.
  3. Search Gmail (read-only, see Tools: {{gmail.search}}, then {{gmail.thread}} or {{gmail.message}} to read) for the last 2 days (newer_than:2d): ATS and recruiting senders (Greenhouse, Lever, Ashby, Workday, Jobvite, iCIMS, SmartRecruiters, Workable, BambooHR, and no-reply, talent, recruiting, careers, notifications addresses) or mail naming a watch-set company. Each message's id and thread id are the message_id and thread_id you pass to inbox.ingest. A Gmail search or read tool denied: finish as error with tool denied; {{connector.not_loaded}}; never guess.
  4. For each message pick one class:
    • confirmation: "thank you for applying", application received.
    • interview_request: next steps, availability, scheduling. Add interview_at (ISO) when a time is fixed.
    • offer: an offer or offer call.
    • rejection: "not moving forward", "unfortunately".
    • outreach_reply: a reply to one of the user's outreach drafts (set outreach_id).
    • other: anything else (ignored). Map it to role_id (or null if no role matches). Give an honest p (0 to 1) for the class.
  5. inbox.ingest { messages: [{ message_id, thread_id, received_at, role_id, outreach_id?, class, p, interview_at? }] }. Relay applied, queued (Needs you) and ignored.
  6. runs.finish { run_id, status: "ok" }.

CLI equivalent: pp inbox --in messages.json.

What the op does (do not do it yourself)

confirmation -> applied (records applied_at), interview_request -> interviews (adds an interview round), offer -> offers, rejection -> archived with reason rejected, outreach_reply -> outreach replied. A message never moves a role backwards (a late confirmation will not pull a role out of interviews); a rejection archives from any stage.

Tools

A headless run pre-approves exactly these (SKILL_GRANTS in packages/engine/runners/grants.ts; a test keeps this list and that one equal) and denies everything else. If one you need is denied or missing, do not work around it: runs.finish { run_id, status: "error", summary: { error: "tool denied: <tool>", denied_tools: [...] } }. {{connector.tools}}

  • {{tool:pp}}: the pp MCP tools (every Perfect Placement read and write is an op).
  • {{tool:gmail.search}}: search Gmail{{gmail.connector_note}}.
  • {{tool:gmail.thread}}: read a thread found by the search.
  • {{tool:gmail.message}}: read one message.

Gmail is read-only here: every Gmail write (send, reply, forward, draft create / update / delete, trash, spam, labels) is denied.{{gmail.other_clients}}

Rules

  • Read-only on email: search and read only. Never send, reply, forward, draft, archive, trash, delete, label, mark spam or mark read (those tools are denied). Never accept or decline anything.
  • Notify only on new meaningful items (interview, offer, rejection, first confirmation), interviews and offers first with dates. Silent on empty days.
  • Every write is an op. Never submit an application or send an email.

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.