CtrlK
BlogDocsLog inGet started
Tessl Logo

email-triage

Triage Joel's email inboxes via the joelclaw email CLI. Scan, categorize, archive noise, surface actionable items, and draft replies. Use when: 'check my email', 'scan inbox', 'triage email', 'what needs a reply', 'clean up inbox', 'archive junk', 'email summary', 'anything important in email', or any request involving email inbox review or cleanup.

89

2.87x
Quality

87%

Does it follow best practices?

Impact

92%

2.87x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, densely operational skill: executable commands, a sequenced triage workflow with real validation feedback loops, and no padding. The main gap is that the inline Front Search API reference could be split into a separate file for stronger progressive disclosure.

Suggestions

Move the 'Front Search API Reference' section (valid is: statuses, date/recipient/entity filters) into a dedicated references/ file and link to it from the body, keeping only the most-used filters inline.

Add a short 'Quick start / 60-second triage' summary near the top so the core flow is graspable before the detailed API and signal sections.

Consider extracting the 'Signals for Reply Needed' and 'Common Noise Senders' lists into a reference file to keep the SKILL.md body focused on the workflow.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — no generic 'what is email' padding — but the inline Front Search API reference (statuses, date/recipient/entity filters) is sizable and slightly over what the overview needs, leaving minor trim opportunities rather than the every-token-earns-its-place level of 5.

4 / 5

Actionability

Copy-paste-ready commands with concrete flags, combineable examples, exact jq extraction patterns, and a documented output shape — fully executable guidance covering the common triage cases.

5 / 5

Workflow Clarity

The four-step Triage Workflow is clearly sequenced with explicit validation checkpoints: dry-run-by-default on archive-bulk, 'Always dry-run first to verify', 'Read before deciding', and rate-limit guidance — a genuine validate→verify→confirm feedback loop for the destructive/batch operations.

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and no nested references, but the full Front Search API reference is inlined where it could live in a separate reference file (none exist in references/ or scripts/); good structure with a minor organization gap.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: third-person voice, concrete capabilities, and a rich set of natural trigger phrases covering both what the skill does and when to use it. It is concise, specific, and clearly distinguishable.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Scan, categorize, archive noise, surface actionable items, and draft replies' — giving comprehensive coverage of the skill's capabilities, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (triage/scan/categorize/archive/draft replies) and 'when' via a concrete 'Use when:' clause with multiple trigger phrases, matching the score-5 anchor exactly.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases a user would actually say ('check my email', 'scan inbox', 'triage email', 'what needs a reply', 'clean up inbox', 'archive junk', 'email summary', 'anything important in email'), including synonyms and a catch-all clause.

5 / 5

Distinctiveness Conflict Risk

Scoped specifically to the joelclaw email CLI and Front inboxes with distinct email-triage triggers, giving it a clear niche with minimal conflict risk against unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
joelhooks/joelclaw
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.