cherry-pr-test

Test Cherry Studio PRs by checking out the branch, launching the Electron app in debug mode, and running interactive UI tests via CDP.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/cherry-pr-test/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and clearly sequenced with validation checkpoints, but it carries redundant blocks (duplicated kill logic and migration wizard) and is a long single file with no progressive disclosure structure. Trimming duplication and splitting the report template or troubleshooting into references would lift the weaker dimensions.

Suggestions

De-duplicate the process-kill command block and the V2 migration-wizard explanation (reference one canonical copy from the other) to improve conciseness.

Extract the report template and/or troubleshooting into reference files (e.g. REPORT_TEMPLATE.md, TROUBLESHOOTING.md) referenced one level deep, keeping SKILL.md a lean overview.

Tighten the opening, which restates the description, to reduce token cost without losing clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands and no concept-explaining padding, but the process-kill block and migration-wizard explanation are duplicated across phases and troubleshooting, adding avoidable tokens.	2 / 3
Actionability	Guidance is fully executable and copy-paste ready — concrete `gh`, `lsof`, `pnpm debug`, and `agent-browser` commands plus a complete report template, with no pseudocode.	3 / 3
Workflow Clarity	Phases are clearly sequenced with explicit validation checkpoints (port-listen wait loop, `agent-browser tab` verification, graceful-then-SIGKILL escalation) and troubleshooting feedback loops for destructive cleanup.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~270-line document; it is well-organized into sections but is a fairly large monolithic file rather than a lean overview pointing to one-level references.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, distinctive, and uses natural trigger terms, but it omits an explicit 'when to use' clause, which caps completeness at 2. Adding a 'Use when...' sentence would round it out.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to test or review a Cherry Studio pull request before merging.'

Mention the natural request phrasings users would actually say (e.g. 'test this PR', 'review this Cherry Studio PR') to strengthen the when-to-invoke guidance.

Optionally note the expected argument (PR number/URL) in the description so invocation intent is unambiguous.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'checking out the branch', 'launching the Electron app in debug mode', 'running interactive UI tests via CDP' — rather than vague language.	3 / 3
Completeness	Clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause, so the 'when' is only implied rather than stated.	2 / 3
Trigger Term Quality	Natural terms a user would say are covered ('Test Cherry Studio PRs', 'PRs', 'UI tests', 'Electron', 'CDP'), well beyond jargon-only or generic phrasing.	3 / 3
Distinctiveness Conflict Risk	The niche is distinct — Cherry Studio PRs, Electron debug mode, CDP — making it unlikely to trigger for an unrelated skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: CherryHQ/cherry-studio
Path: .agents/skills/cherry-pr-test/SKILL.md
Commit: f7139a2

Reviewed: about 13 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.