control-cli

Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.

Quality

84%

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

Quality

Content

85%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 content is executable and well-structured: concrete tmux/PTY/profiling recipes, a clear numbered harness loop, and tight guardrails with no padded concept explanations. The main gap is the absence of explicit validation checkpoints in the harness loop, which keeps workflow clarity just below maximum.

Suggestions

Add an explicit validation checkpoint in the Harness Loop (e.g. step 6 could mandate asserting a concrete screen pattern before sending the next action, with a retry/abort on mismatch).

Make the 'wait for a concrete screen pattern' step enforce a fallback (timeout + abort) so hangs are caught deterministically rather than relying on the deadline only in the PTY recipe.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence (no explanations of what tmux or a PTY is), though a few phrasings like 'Keep it temporary unless the user asks to add a reusable test' and the explanatory guardrail list could be trimmed slightly.	4 / 5
Actionability	Provides copy-paste-ready, executable bash and Python examples (tmux session block, PTY probe with select loop, Node inspector invocation) covering the common harness cases with concrete commands and code.	5 / 5
Workflow Clarity	The 'Harness Loop' gives an explicit 8-step sequence and guardrails cover cleanup, but the loop lacks explicit validation checkpoints for risky operations (e.g. verifying the screen pattern captured matches expected before proceeding is implied, not enforced), keeping it just below the top anchor.	4 / 5
Progressive Disclosure	For a self-contained skill under 50 lines of prose with no external bundle files, content is well-organized into clear sections (What It Is Used For, Harness Loop, Options, recipes, Guardrails), satisfying the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

83%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 states concrete capabilities and provides an explicit 'Use for ...' trigger clause covering natural scenarios. It is tight and free of fluff, with only minor gaps in synonym coverage and some overlap risk with general profiling/debugging skills.

Suggestions

Add a couple of natural synonyms or tool names users might say (e.g. 'tmux', 'PTY', 'terminal recording') to broaden trigger-term coverage.

Tighten distinctiveness by emphasizing 'without external services' or 'local-only' earlier to reduce overlap with general debugging/profiling skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('drive, inspect, and profile an interactive CLI or TUI') plus concrete use cases (startup regressions, memory leaks, hangs, prompt flows), with only minor coverage gaps around which specific profiling artifacts are produced.	4 / 5
Completeness	It explicitly answers 'what' ('Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services') and 'when' with a concrete 'Use for ...' clause enumerating trigger scenarios, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'CLI UX checks', 'startup regressions', 'memory leaks', 'hangs', and 'prompt flows' that a user would actually say, though it misses common synonyms and explicit tool-name triggers like 'tmux' or 'pty'.	4 / 5
Distinctiveness Conflict Risk	The niche (local harness for interactive CLI/TUI testing without external services) is fairly distinct, but 'CLI UX checks' and 'startup regressions' could overlap with general debugging or profiling skills, leaving minor conflict risk.	4 / 5
	Total	17 / 20 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: cursor/plugins
Path: cursor-team-kit/skills/control-cli/SKILL.md
Commit: 51a96e0

Reviewed: 2 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.