CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-review

Runs a Greptile CLI review for the current local branch, installing or authenticating the CLI when needed, then summarizes JSON findings for the user. Use when the user wants Greptile feedback before opening a PR, outside a hosted PR review flow, or directly from a local checkout.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 tight, well-structured instruction body: every step is concrete and executable, with explicit error handling, install/auth gating, and a fallback chain for the review command. The single deduction is progressive disclosure, where the flat single-page structure sits just above the simple-skill line. No bundle files exist, so structure is judged on the SKILL.md body alone.

DimensionReasoningScore

Conciseness

Every step is a one-line instruction plus the exact command ('git rev-parse --show-toplevel', 'command -v greptile', 'greptile review --json'), with zero padding and no explanation of concepts Claude already knows. Matches the 'lean and efficient; every token earns its place' anchor; level 4 would require trimmable over-explanation, which is absent.

5 / 5

Actionability

Fully executable, copy-paste-ready commands at every step, including the npm install, the curl shell-installer fallback, and the '--agent' fallback when '--json' fails. Matches the level-5 anchor covering the common cases; not 4 since no key executable detail is missing.

5 / 5

Workflow Clarity

Clear five-step sequence with explicit checkpoints and feedback loops: failure handling at repo check, CLI presence, auth ('Wait for the user to complete the login flow'), a fallback command on usage error, and 'Do not hide the raw command failure if both commands fail' for error recovery. Not a destructive or batch operation, so the level-3 cap does not apply; matches the level-5 anchor.

5 / 5

Progressive Disclosure

Well-organized into five clearly headed sections with nothing that warrants splitting into separate files, and no buried or nested references. Held at 4 rather than 5 because the body (~83 lines) exceeds the under-50-line threshold where flat structure alone earns top marks, and no reference-based organization is demonstrated.

4 / 5

Total

19

/

20

Passed

Description

87%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 description with concrete third-person actions and an explicit 'Use when...' clause containing multiple realistic trigger scenarios. Its clear Greptile-specific niche and explicit contrast with hosted PR review flows minimize conflict risk. The only weakness is modest trigger-term synonym coverage beyond the exact 'Greptile' vocabulary.

DimensionReasoningScore

Specificity

Lists several concrete third-person actions — 'Runs a Greptile CLI review for the current local branch, installing or authenticating the CLI when needed, then summarizes JSON findings' — with only minor gaps (e.g., the git-repo requirement and plain-text fallback are unstated). Not 5 because coverage of the skill's behaviors is not exhaustive; not 3 because it clearly exceeds 1-2 actions.

4 / 5

Completeness

Explicitly answers both: what ('Runs a Greptile CLI review... installing or authenticating the CLI when needed, then summarizes JSON findings') and when ('Use when the user wants Greptile feedback before opening a PR, outside a hosted PR review flow, or directly from a local checkout') with concrete trigger phrases. Matches the level-5 anchor; level 4 would require a less explicit 'when' clause.

5 / 5

Trigger Term Quality

Contains natural phrases users would actually say: 'Greptile feedback before opening a PR', 'outside a hosted PR review flow', 'directly from a local checkout'. Not 5 because a few natural variants (e.g., 'AI code review', 'review my diff', 'pre-PR check') are missing.

4 / 5

Distinctiveness Conflict Risk

Clearly niched to the Greptile CLI and explicitly distinguishes itself from 'a hosted PR review flow', giving it distinct triggers with minimal conflict risk against generic code-review skills. Matches the level-5 anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

alvinunreal/oh-my-opencode-slim

Path

.agents/skills/cli-review/SKILL.md

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.