terminal-capture

Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

92%

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

A dense, highly actionable code skill with executable examples, clear sequencing, and concrete error-recovery guidance; it earns top marks on conciseness, actionability, and workflow clarity. The only weakness is progressive disclosure: it is a long single-file skill that keeps its full type reference inline rather than splitting it into a referenced file.

Suggestions

Move the 'Full ScenarioConfig Type' and detailed FlowStep field reference into a separate REFERENCE.md and link to it, keeping SKILL.md as a lean overview with quick-start and examples.

Add a brief explicit verification step in the Quick Start (e.g., 'confirm the expected screenshot files exist under screenshots/{name}/ and are non-blank') to make the output checkpoint a stated action rather than an implied one.

Dedupe the FlowStep field definitions, which currently appear both inline in 'FlowStep API' and again in 'Full ScenarioConfig Type'.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely code, tables, and API documentation with no filler explaining concepts Claude already knows (e.g., no preamble on what a PTY or terminal is); it assumes competence and every section is dense with actionable specifics.	3 / 3
Actionability	It provides copy-paste-ready install commands, complete executable TypeScript scenario configs, an explicit list of supported key names, a screenshot output table, and concrete troubleshooting fixes — fully executable with no pseudocode.	3 / 3
Workflow Clarity	The Quick Start is clearly sequenced (write config → run → output), and the output table enumerates expected screenshot files as an explicit verification checkpoint, with a troubleshooting section providing error-cause-solution recovery loops for the fragile PTY/Playwright stack.	3 / 3
Progressive Disclosure	Sections are well-organized (Prerequisites, Architecture, Quick Start, FlowStep API, Examples, Troubleshooting) and not a wall of text, but at ~270 lines everything is inline with no one-level-deep reference split — the full ScenarioConfig type and detailed API reference could live in a separate reference file rather than inline.	2 / 3
	Total	11 / 12 Passed

Description

90%

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, third-person description that clearly states the capability and provides explicit, natural trigger terms covering PR review, slash-command testing, and visual documentation. The only soft spot is specificity, since the skill is essentially a single action rather than a list of multiple concrete actions.

Dimension	Reasoning	Score
Specificity	It names the concrete action ("Automates terminal UI screenshot testing for CLI commands") but this is a single-capability tool rather than the multiple distinct concrete actions (extract/fill/merge) the level-3 anchor requires; it lists several use contexts but only one real capability verb.	2 / 3
Completeness	It explicitly answers both what ("Automates terminal UI screenshot testing for CLI commands") and when ("Applies when reviewing PRs..., testing slash commands..., generating visual documentation, or when 'terminal screenshot'... is mentioned"), with an explicit "Applies when" trigger clause.	3 / 3
Trigger Term Quality	It includes natural phrases users would say — "terminal screenshot", "CLI test", "visual test", "terminal-capture" — plus concrete slash commands (/about, /context, /auth, /export) and "reviewing PRs that affect CLI output".	3 / 3
Distinctiveness Conflict Risk	The niche (terminal UI screenshot capture for CLI/slash-command review) is narrow and the triggers ("terminal screenshot", "terminal-capture", specific slash commands) are distinctive, making collision with other skills unlikely.	3 / 3
	Total	11 / 12 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: QwenLM/qwen-code
Path: .qwen/skills/terminal-capture/SKILL.md
Commit: 8878264

Reviewed: 5 days 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.