Name: inbox-setup
Rating: 64 (1 reviews)
Author: alirezarezvani

inbox-setup

One-time setup skill that builds a personalized inbox triage knowledge base via interactive interview. Interviews the user about their email patterns, business context, reply style, and priorities using grill-me discipline (one question at a time, forcing format where possible, dependency-ordered, each question explains why I'm asking), then generates the knowledge base files that power the companion 'inbox-triage' skill. Run this once before using inbox-triage for the first time. Re-run when business, pricing, or priorities change significantly. Triggers: 'set up my inbox', 'configure inbox triage', 'set up my email system', 'configure email triage', 'build my email knowledge base', 'initialize email management', 'set up inbox triage', 'onboard email triage', or any variation where someone wants to get the email triage system running for the first time.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/inbox-setup/SKILL.md

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

Quality

Content

63%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-sequenced, highly actionable interview script with clear file contracts and a final validation step. Its main weaknesses are redundancy across the Stop Condition / Re-Run / Error Handling / Anti-Patterns sections and bundle references (references/ and scripts/) that point to files not present in the skill.

Suggestions

Provide the referenced `references/` files (kb_file_contract.md, grill_me_section_walk.md, voice_calibration.md) and `scripts/` files (kb_validator.py, section_progress_tracker.py, voice_sample_analyzer.py), or remove the references — currently they are broken links.

Consolidate the overlapping re-run / skip-logic guidance that appears in 'Stop Condition', 'Re-Run Behavior', 'Error Handling', and 'Anti-Patterns To Reject' into a single section to tighten token use.

Add a per-section validation note (not just the final kb_validator run) so each committed file is checked before moving to the next section, strengthening the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete per-section questions, but repeats material across sections: the trigger list reappears as 'Invocation Triggers', grill-me rules are stated twice, and re-run/skip-logic guidance is restated in 'Stop Condition', 'Re-Run Behavior', 'Error Handling', and 'Anti-Patterns To Reject'.	3 / 5
Actionability	Provides copy-paste-ready interview questions (S1.Q1–S8), an explicit file-output table, and named commands like `scripts/kb_validator.py --workspace ${WORKSPACE}` and `scripts/voice_sample_analyzer.py`; the only gap is that the referenced scripts do not exist as bundle files.	4 / 5
Workflow Clarity	The 8-section interview is clearly sequenced with commit-per-section discipline and a final `kb_validator.py` validation checkpoint before handoff, but validation is end-of-flow only rather than a per-section validate-fix-retry loop.	4 / 5
Progressive Disclosure	Structure is well organized with clearly signaled one-level-deep references to `references/kb_file_contract.md`, `grill_me_section_walk.md`, and `voice_calibration.md`, but none of the referenced `references/` or `scripts/` files actually exist, so navigation is broken.	3 / 5
	Total	14 / 20 Passed

Description

90%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 strong: it clearly states what the skill does, when to use it, and provides a thorough list of natural trigger phrases. The only flaw is a first-person voice slip ('why I'm asking') that costs it a specificity point under the voice rule.

Suggestions

Rewrite the parenthetical 'each question explains why I'm asking' in third person (e.g., 'each question explains why it is being asked') to keep the description in consistent third-person voice.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('builds a personalized inbox triage knowledge base via interactive interview', 'Interviews the user about their email patterns, business context, reply style, and priorities', 'generates the knowledge base files'), which would be a 4, but the first-person phrase 'each question explains why I'm asking' triggers the voice penalty, reducing it by one.	3 / 5
Completeness	Explicitly answers both 'what' (interviews the user and generates the KB files powering inbox-triage) and 'when' ('Run this once before using inbox-triage for the first time. Re-run when business, pricing, or priorities change significantly') with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit 'Triggers:' clause enumerates eight natural user phrases ('set up my inbox', 'configure inbox triage', 'set up my email system', etc.) plus an 'any variation' catch-all, giving comprehensive coverage of natural terms and synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (one-time onboarding paired with the companion 'inbox-triage' runtime skill) with distinct setup-oriented triggers, minimizing overlap with other skills.	5 / 5
	Total	18 / 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: 7 missing	Warning
referenced_paths_exist	Referenced path issues: 19 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: ~7 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.