cmux-workspace

Work inside the current cmux workspace and terminal. Use for cmux workspace, current workspace, caller surface, panes, surfaces, socket targeting, and non-interfering cmux automation.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/cmux-workspace/SKILL.md

Quality

Content

86%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 a well-organized, executable reference with concrete bash commands, clear default-scoping rules, and explicit validation/report-and-stop feedback for risky focus and move operations. Progressive disclosure is handled cleanly via a single real references file.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command examples with brief, purposeful prose, assuming Claude's competence (e.g., the focus/layout distinction is non-obvious domain knowledge); not a 5 because a few explanatory sentences ("Treat layout and focus as separate concerns") could be trimmed.	4 / 5
Actionability	Commands are concrete and copy-paste ready with proper env-var expansion ("${CMUX_WORKSPACE_ID:-}"), covering the common cases across creation, sending, moving, and sidebar state; matches the fully-executable anchor.	5 / 5
Workflow Clarity	Sequences include validation checkpoints and feedback loops ("Inspect first with cmux identify --json ... then", "report the bug and stop rather than working around it", "Never call focus-pane ... to recover; report the failure and stop"); not a 5 because the workflow is distributed across sections rather than one explicitly numbered process with consolidated validation.	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to the real references/commands.md and a sibling skill, with the bulk command list appropriately split out; matches the clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

71%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 third-person, distinct, and provides an explicit Use-for trigger clause covering multiple concrete capability areas. It is held back from the top tier by trigger terms that lean technical rather than natural user phrasing.

Suggestions

Rewrite the Use-for list to lead with natural user phrases (e.g., "cmux workspace, current workspace, panes and surfaces") and demote jargon like "caller surface" and "socket targeting".

Add a synonym or two for the most common need (e.g., mention "cmux tab" since the body notes the UI calls workspaces tabs).

Dimension	Reasoning	Score
Specificity	Names the cmux domain and lists several concrete capabilities ("caller surface, panes, surfaces, socket targeting, and non-interfering cmux automation") rather than vague language, with only minor coverage gaps; not a 5 because the actions are areas/objects more than distinct concrete operations.	4 / 5
Completeness	It states both what ("Work inside the current cmux workspace and terminal") and when (explicit "Use for ..." clause with concrete triggers); not a 5 because the trigger list mixes natural and jargon terms rather than crisp concrete trigger phrases.	4 / 5
Trigger Term Quality	"cmux workspace" and "current workspace" are natural phrases a user might say, but "caller surface", "socket targeting", and "non-interfering cmux automation" lean technical and lack common synonyms; not a 4 because several natural terms are missing.	3 / 5
Distinctiveness Conflict Risk	The "cmux" qualifier carves a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.	5 / 5
	Total	16 / 20 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 suspicious	Warning

	Total	15 / 16 Passed

Repository: basicmachines-co/basic-memory
Path: .agents/skills/cmux-workspace/SKILL.md
Commit: 194afe1

Reviewed: 7 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.