CtrlK
BlogDocsLog inGet started
Tessl Logo

dmux-workflows

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/dmux-workflows/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

A well-organized, actionable skill body that teaches dmux-specific mechanics Claude would not know, with concrete commands and realistic pane-prompt examples. Its main gap is workflow validation: the merge step — the riskiest operation in every pattern — has only advisory best practices rather than explicit verification checkpoints.

Suggestions

Add an explicit validation checkpoint to the merge workflow, e.g. after pressing 'm': review each pane's diff, run the test suite or a build, and only then commit — turning 'Merge strategically' from advice into a sequenced step.

Replace one illustrative pattern with a single concrete end-to-end example (exact prompts typed into panes 1-3, the merge command, and the expected result) so a first-time user can execute the flow verbatim.

Consider moving the five workflow patterns into a references/patterns.md file and keeping one-line summaries plus a link in SKILL.md, which would tighten the overview while keeping patterns discoverable.

DimensionReasoningScore

Conciseness

The body is lean: the 'What is dmux' section covers genuinely novel information and patterns are compact prompt examples. The 'Complementary Tools' table and some pattern commentary could be trimmed, but padding is minor — efficient with minor over-explanation rather than noticeably verbose.

4 / 5

Actionability

Provides executable commands ('dmux', 'npm install -g dmux', git worktree add/merge, package-manager tmux installs), concrete key presses ('n' to create, 'm' to merge), and specific example prompts per pane. It falls short of fully copy-paste-ready because pane prompts are illustrative placeholders, matching anchor 4.

4 / 5

Workflow Clarity

Sequences are clearly listed (start dmux, create panes, merge; worktree add, run, merge), but merging parallel agent output is a batch operation whose only safeguards are advisory ('Merge strategically. Review pane output before merging') with no explicit validation/checkpoint step in the workflow itself. Per the batch-operation guideline this caps workflow clarity at 3.

3 / 5

Progressive Disclosure

No bundle files exist, and the single ~135-line file is well-sectioned (activation, quick start, patterns, best practices, worktrees, troubleshooting) with no nested references and a clearly signaled external repo link. Structure is good with minor gaps — the five workflow patterns could plausibly live in a separate reference file — matching anchor 4.

4 / 5

Total

15

/

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 that clearly states both capability and activation conditions with natural trigger terms and a distinct dmux-specific niche. Its main weakness is capability specificity: it describes orchestration abstractly rather than naming the concrete operations dmux performs.

DimensionReasoningScore

Specificity

Names the domain ('multi-agent orchestration using dmux', 'tmux pane manager for AI agents') and 1-2 capability statements ('Patterns for parallel agent workflows'), but lists no concrete operations such as creating panes or merging output. It is more specific than a bare domain label (2) but does not enumerate several specific actions (4).

3 / 5

Completeness

Explicitly answers both: what ('Multi-agent orchestration using dmux... Patterns for parallel agent workflows across Claude Code, Codex, OpenCode') and when ('Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows'). The when-clause uses concrete trigger phrasing, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('running multiple agent sessions in parallel', 'coordinating multi-agent development workflows', 'multi-agent') plus concrete harness names (Claude Code, Codex, OpenCode). A few natural synonyms like 'spawn agents' or 'fan out' are missing, matching the good-but-not-comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The dmux/tmux pane-manager framing carves a clear niche, but generic 'multi-agent' and 'parallel' trigger terms create minor overlap risk with other orchestration/subagent skills. Mostly distinct with minor overlap, matching anchor 4.

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
ysyecust/everything-claude-code
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.