CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

An example-driven, highly actionable skill body: executable commands, complete typed configs, and concrete troubleshooting give Claude everything needed to run terminal screenshot scenarios immediately. The only real improvements are trimming minor redundancy and adding an explicit verification step for batch runs.

DimensionReasoningScore

Conciseness

The body is dense and code-forward — tables, config examples, and a full type reference — with almost no re-teaching of concepts Claude already knows. Minor trimmable padding remains (the one-line "Integration with PR Review" section repeats the intro, and the ffmpeg install prose is slightly conversational), keeping it below level 5.

4 / 5

Actionability

Guidance is fully executable: copy-paste install and run commands ("npx tsx integration-tests/terminal-capture/run.ts ..."), complete satisfies-annotated scenario configs covering the common cases (input, menu selection, tab completion, streaming, batch), the full FlowStep/ScenarioConfig interfaces, and troubleshooting entries with explicit cause→solution pairs.

5 / 5

Workflow Clarity

The Quick Start is clearly sequenced (write scenario → run single/batch → check output) and the output file table plus the Troubleshooting section's cause/solution pairs provide verification and error-recovery checkpoints. A minor gap keeps it below level 5: batch directory runs have no explicit post-run verification step.

4 / 5

Progressive Disclosure

The body is well-sectioned with clear headers, and everything is one level deep with no buried references; the core-file listing gives good navigation into the codebase. No references/ bundle exists, and at ~280 lines the inline "Full ScenarioConfig Type" section is a defensible but notable candidate for splitting into a reference file — good structure with a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

78%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: explicit third-person 'what' plus an explicit and concrete 'Applies when' trigger clause with natural keyword triggers. The main weakness is that it names only one capability (screenshot testing) rather than enumerating several concrete actions, and a couple of its trigger terms are generic enough to overlap with adjacent testing skills.

DimensionReasoningScore

Specificity

"Automates terminal UI screenshot testing for CLI commands" names the domain and a single concrete action; the remainder of the description lists trigger contexts rather than additional capabilities. It exceeds the level-2 anchor (which names only a domain with generic action) but stops short of listing several specific actions needed for level 4.

3 / 5

Completeness

It explicitly answers both questions: "Automates terminal UI screenshot testing for CLI commands" (what) and "Applies when reviewing PRs that affect CLI output, testing slash commands..., or when 'terminal screenshot'... is mentioned" (when), with concrete trigger phrases — matching the level-5 anchor structure.

5 / 5

Trigger Term Quality

Natural trigger phrases are present and would plausibly be said by a user — "'terminal screenshot'", "'CLI test'", "'visual test'", "'terminal-capture'", plus concrete slash commands (/about, /context, /auth, /export). A few natural synonyms (e.g. "screenshot", "record terminal", "capture CLI output") are missing, keeping it below level 5.

4 / 5

Distinctiveness Conflict Risk

The terminal-UI screenshot niche with named slash commands and the 'terminal-capture' keyword is mostly distinct from other skills. However, the generic trigger terms "'CLI test'" and "'visual test'" could also fire for web visual-regression or general CLI-testing skills, a minor overlap risk that keeps it below level 5.

4 / 5

Total

16

/

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

QwenLM/qwen-code

Path

.qwen/skills/terminal-capture/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.