inbox-triage

Runs a full inbox triage using the knowledge base created by the 'inbox-setup' skill. Light-intake by design (most invocations skip questions and run with KB-default preferences); asks at most 2 grill-me override questions when invocation is outside normal cadence or includes category-skip intent. Searches recent emails, classifies them via the user's taxonomy, researches new senders, generates recommendations, drafts replies (NEVER sends), delivers a report in the user's preferred format, and updates the knowledge base with learnings. Designed to run on a recurring schedule (1-3x daily) or on demand. Use when the user wants their inbox processed, in any variation (e.g., 'triage my inbox', 'inbox triage', 'check my email', 'run email triage', 'process my inbox', 'what's new in my email', 'handle my email', 'email triage'). Requires the inbox-setup skill to have been run first.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

85%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.

The body is a well-organized, actionable triage workflow with a clear step sequence, strong validation feedback loops, and appropriately offloaded detail to one-level-deep reference files. Its only weakness is mild redundancy around the NEVER-SEND restatements and some script output contracts being implied rather than fully shown.

Suggestions

Consolidate the NEVER-SEND rule to one authoritative callout plus the validator reference; remove the redundant 'Stated again here' / 'Stated multiple times' meta-commentary to tighten conciseness.

For each script invocation, show the expected return shape or a one-line output contract so the workflow is fully copy-paste executable rather than implying behavior.

Inline the cadence-to-window mapping's fallback behavior when email-taxonomy.md S1.Q5 is absent, so Step 1 doesn't depend on an unstated lookup failure mode.

Dimension	Reasoning	Score
Conciseness	Efficient and well-structured with tables and tight steps, but the NEVER-SEND rule is stated ~5 times with meta-commentary ('Stated multiple times in this skill body', 'Stated again here') that could be trimmed; fits the 'efficient, minor over-explanation' anchor slightly above the 3 midpoint.	4 / 5
Actionability	Gives concrete script invocations (e.g. 'scripts/search_window_calculator.py --cadence <CADENCE> --now <ISO>'), exact KB file paths, and decision tables; minor gaps in that full CLI output contracts aren't all shown inline, placing it at 'mostly executable, minor gaps'.	4 / 5
Workflow Clarity	A clear 10-step sequence (Steps 0-10) with fail-fast prerequisite checks, a post-run draft_safety_validator.py enforcement checkpoint, an error-handling table, and an empty-inbox branch — an explicit validation feedback loop for the batch/destructive-adjacent operation.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references (kb_file_contract.md, triage_decision_framework.md, drafts_only_safety.md — all present in references/) and a role table for three scripts; content is appropriately split with easy navigation.	5 / 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.

The description is comprehensive and well-structured: it states concrete actions, an extensive set of natural trigger phrases, explicit what-and-when guidance, and a clear niche tied to a paired skill. No vagueness, over-claims, or voice issues are present.

Dimension	Reasoning	Score
Specificity	Lists a full concrete action pipeline — 'Searches recent emails, classifies them via the user's taxonomy, researches new senders, generates recommendations, drafts replies (NEVER sends), delivers a report...and updates the knowledge base' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (full triage pipeline) and 'when' ('Use when the user wants their inbox processed, in any variation...'), with concrete trigger phrases — the clearest anchor.	5 / 5
Trigger Term Quality	Provides eight natural user phrases ('triage my inbox', 'check my email', 'process my inbox', 'what's new in my email', etc.), comprehensive coverage including synonyms as in the top anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (recurring inbox triage consuming the inbox-setup KB), distinct trigger vocabulary, and an explicit pairing requirement that minimizes conflict with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: productivity/email/skills/inbox-triage/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours ago

Table of Contents

Discovery Implementation Validation

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.