AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Triage Inbox

skill-jain777-jobclaw-skills-triage-inbox · by jain777

>

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-jain777-jobclaw-skills-triage-inbox

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jain777-jobclaw-skills-triage-inbox)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Triage Inbox? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

triage-inbox

Tell the user (or JobClaw) what each email is and what to do about it. Hard rules: [../_shared/RULES.md](../_shared/RULES.md). All enums, the decision table, the extraction-fields shape, and the suggested-action vocabulary live in [../../knowledge/status/taxonomy.md](../../knowledge/status/taxonomy.md) — read it first; don't re-derive.

Inputs

Single mode

  • A pasted email: from, subject, body, optional thread (prior messages), optional date.

Batch mode

  • --in inbox/incoming.json:

``jsonc { "emails": [ { "email_id": "...", "from": "...", "subject": "...", "body": "...", "date": "YYYY-MM-DD", "thread": ["..."] } ] } ``

If the input has only a body (no from/subject), warn but proceed — class confidence will be low unless body is decisive.

Method

  1. Read the taxonomy. [../../knowledge/status/taxonomy.md](../../knowledge/status/taxonomy.md) — the 10 classes, the extraction-fields contract, the suggested-action vocab.
  1. For each email, classify into exactly one class. Mutually exclusive; pick the most specific match (e.g., a "we received your application" auto-message is info, not screen; a take-home request is assessment, not interview-invite). Use the body + subject + sender domain together — sender alone is unreliable.
  1. Extract fields per the taxonomy's Extraction fields block (only fields the email genuinely provides — never invent):
  • company, role, job_id
  • dates[] — proposed slots / deadlines / start dates (ISO + time + tz + label)
  • links[]{ url, kind ∈ schedule|assessment|portal|other }
  • asks[] — verbatim recruiter asks ("send updated CV", "share notice period")
  • deadline — single hard cutoff if explicit
  • sentiment ∈ {neutral, positive, negative}
  • confidence ∈ {high, medium, low} — your own confidence in the classification
  1. Suggest one action from the taxonomy's vocab (reply-schedule | reply-accept | reply-decline | reply-ask | reply-info | acknowledge | ignore | escalate). Map per the decision table; always suggest escalate for class other or any classification with confidence: low.
  1. Apply guardrails.
  • offer emails → suggest reply-ask (acknowledge + buy time + recommend /coach-negotiation). Never suggest reply-accept directly.
  • assessment / interview-invite emails with a deadline within 48h → bump the email's priority field to urgent in the output (extension on the schema; downstream tooling can sort by it).
  • If the body looks like phishing (suspicious domain, prize wording, urgency + a link) → class spam regardless of subject.

Output

inbox/triage-.json

{
  "as_of": "YYYY-MM-DD",
  "triaged": [
    {
      "email_id": "...",
      "from": "...",
      "subject": "...",
      "class": "rejection | screen | interview-invite | assessment | offer | recruiter-outbound | info | request-info | spam | other",
      "extraction": {
        "company": "...", "role": "...", "job_id": "...",
        "dates": [...], "links": [...], "asks": [...],
        "deadline": "YYYY-MM-DD | null",
        "sentiment": "neutral | positive | negative",
        "confidence": "high | medium | low"
      },
      "suggested_action": "...",
      "priority": "normal | urgent",
      "notes": "string | null"
    }
  ]
}

Stdout

A concise table per email: id · class · company/role · action · priority · confidence. Highlight urgent rows and any escalate rows for the user to review.

Anti-patterns

  • Treating "we received your application" as screen (it's info).
  • Collapsing screen and interview-invite — they trigger different downstream actions.
  • Inventing job_id, dates, or company not in the source text.
  • Setting confidence: high on ambiguous emails just to clear the queue. Be honest — low is more useful.
  • Suggesting reply-accept for an offer (must be reply-ask + recommend /coach-negotiation).
  • Emoji.

Rubric

  • [ ] Class is one of the 10 taxonomy values, exactly.
  • [ ] Every extraction.* field is sourced from the email (or null/[]).
  • [ ] Suggested action is from the taxonomy vocab and consistent with the decision table.
  • [ ] No offer is paired with reply-accept.
  • [ ] confidence: low rows are flagged with suggested_action: escalate.
  • [ ] Urgent items (assessment / interview-invite with ≤48h deadline) marked priority: urgent.

Next steps

Triaged. Next: /infer-status to update the funnel, then /draft-reply for the suggested action.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.