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.
90
88%
Does it follow best practices?
Impact
92%
2.87xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific concrete actions, names the tool used, includes a comprehensive 'Use when' clause with natural trigger phrases, and is clearly scoped to a distinct niche (Joel's email via a specific CLI). It serves as a strong example of a well-crafted skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scan, categorize, archive noise, surface actionable items, and draft replies. Also names the specific tool ('joelclaw email CLI'). | 3 / 3 |
Completeness | Clearly answers both 'what' (triage email inboxes, scan, categorize, archive, surface actionable items, draft replies) and 'when' (explicit 'Use when:' clause with extensive trigger phrases and a catch-all for email inbox review or cleanup). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'check my email', 'scan inbox', 'triage email', 'what needs a reply', 'clean up inbox', 'archive junk', 'email summary', 'anything important in email'. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it's scoped to a specific person's email (Joel's), a specific CLI tool (joelclaw), and a specific domain (email triage/inbox management). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent CLI documentation and a well-structured triage workflow including appropriate safety mechanisms (dry-runs, draft-then-approve). The main weakness is that it's a long monolithic document where the API reference section could be extracted to a separate file, and some categorization guidance is slightly verbose for Claude's capabilities. The domain-specific knowledge (Front API quirks, Joel's inboxes, VIP contacts) is exactly the kind of content that belongs in a skill.
Suggestions
Extract the Front Search API Reference section into a separate FRONT_SEARCH_REFERENCE.md file and link to it from the main skill, reducing the main file's token footprint.
Trim the 'Categorize using inference' bullet descriptions — Claude can infer what 'Reply needed' vs 'Archive' means from the signal heuristics alone without the explanatory sentences.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and contains genuinely useful reference material Claude wouldn't know (CLI syntax, Front API quirks, entity IDs). However, some sections are verbose — the 'Categorize using inference' bullet descriptions, the 'Signals for Archive' heuristics, and the repeated emphasis on 'use judgment' add moderate bloat. The Front Search API reference section is thorough but could be tighter. | 2 / 3 |
Actionability | Excellent actionability throughout — every CLI command is copy-paste ready with real flags and examples, jq extraction patterns are executable, the triage workflow has concrete steps with specific commands, and archive operations show both single and bulk patterns with dry-run safety. The output shape documentation enables immediate parsing. | 3 / 3 |
Workflow Clarity | The 4-step triage workflow is clearly sequenced (load → categorize → present → execute) with explicit validation checkpoints: dry-run before bulk archive, read before deciding on ambiguous items, draft-then-approve for replies. Rate limiting guidance and eventual consistency warnings serve as important operational checkpoints. The feedback loop of dry-run → verify → confirm for destructive bulk operations is well-articulated. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a monolithic file with no references to supporting documents. The Front Search API reference section (valid statuses, date filters, recipient filters, entity filters, negation notes) could be split into a separate reference file. For a skill of this length (~200+ lines), some content decomposition would improve navigability. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- joelhooks/joelclaw
- Commit
03f0a59
- 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.