Name: inbox-triage
Rating: 68.8 (1 reviews)
Author: alirezarezvani

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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is inbox-triage in alirezarezvani/claude-skills

Quality

Content

73%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 well-structured, safety-conscious procedural skill with a clear step sequence, explicit validation, and good reference signaling. Its main weaknesses are noticeable repetition of the NEVER-SEND/safety rules across sections and referenced bundle files that do not exist on disk.

Suggestions

Consolidate the repeated NEVER-SEND statements: state the rule once in 'DRAFTS ONLY — Never Send' and reference it from Critical Rules and Anti-Patterns rather than restating it verbatim three times.

Ship the referenced bundle files (references/kb_file_contract.md, references/drafts_only_safety.md, references/triage_decision_framework.md, and the three scripts) so the signaled navigation actually resolves.

Replace the pseudocode date-math block in Step 1 with the concrete script invocation and its expected output format to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and procedural without explaining concepts Claude already knows, but the NEVER-SEND rule, Critical Rules, and Anti-Patterns sections restate one another noticeably; the body could be tightened by consolidating these repeated safety statements.	3 / 5
Actionability	Provides concrete, executable guidance — specific script invocations ('scripts/search_window_calculator.py --cadence <CADENCE> --now <ISO>'), file paths, and tabular provider mappings — but the date-math block is pseudocode-style and the referenced scripts' exact call signatures are not always given.	4 / 5
Workflow Clarity	Clear 10-step sequence (Step 0–10) with explicit validation checkpoints (fail-fast on missing KB files, post-run draft_safety_validator scan), a feedback-oriented error-handling table, and checklists (Critical Rules, Anti-Patterns) for a batch/recurring operation.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references (kb_file_contract.md, drafts_only_safety.md, triage_decision_framework.md) with a dedicated References section and a scripts table, but the referenced references/ and scripts/ bundle files are not present in the skill package, so navigation cannot be verified.	4 / 5
	Total	16 / 20 Passed

Description

96%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.

A strong, concrete description that clearly states capabilities, trigger phrases, and prerequisites with comprehensive coverage. It is somewhat verbose for a description field (the light-intake/grill-me detail is implementation depth better suited to the body), but nothing is vague or over-claimed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' — with comprehensive coverage and no significant gaps.	5 / 5
Completeness	Explicitly answers both what (full triage pipeline: search, classify, research, recommend, draft, report, update KB) and when ('Use when the user wants their inbox processed, in any variation' plus concrete trigger phrases).	5 / 5
Trigger Term Quality	Provides comprehensive natural-phrase coverage with synonyms — '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' — all phrases a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (recurring inbox triage) with explicit pairing ('Requires the inbox-setup skill to have been run first'), but the broad 'in any variation' net and shared 'inbox' namespace with the paired inbox-setup skill carry minor overlap risk.	4 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 19 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: ~3 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.