CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

77%

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 ./skills/dmux-workflows/SKILL.md

The canonical home for this skill is dmux-workflows in affaan-m/ECC

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 concrete, well-structured skill body with ready-to-use pane prompts, commands, and a useful worktree-isolation pattern. Its weaknesses are implicit workflow checkpoints (no verification that panes completed or that merged branches integrate cleanly) and inlined ECC-helper detail that should live in a reference file.

Suggestions

Add explicit validation checkpoints to the workflows: a step to confirm each pane finished (e.g. inspecting status.md or tmux capture-pane) and a post-merge verification step (run the test suite, resolve conflicts before proceeding) in both the patterns and the worktree section.

Provide an actual install command for dmux instead of 'Install dmux from its repository after reviewing the package' so the Quick Start is fully executable.

Move the ECC Helper section's detailed plan.json examples and seedPaths documentation into a reference file (e.g. references/ecc-helper.md), keeping only a one-line pointer in SKILL.md.

DimensionReasoningScore

Conciseness

The body is efficient — concrete pane prompts, exact key bindings ('n', 'm'), commands, and JSON examples with almost no explanation of concepts Claude already knows; minor trims possible in the second seedPaths JSON example (largely repeats the first) and the 'Complementary Tools' table. Not a 3 because there is no padding or over-explanation to speak of.

4 / 5

Actionability

Mostly executable guidance: copy-paste agent prompts, git worktree commands, 'tmux capture-pane -pt <session>:0.<pane-index>', and a runnable plan.json for the orchestrate-worktrees helper. Not a 5 because installation is left vague ('Install dmux from its repository after reviewing the package') with no actual install command.

4 / 5

Workflow Clarity

Workflow patterns are sequenced with transition notes ('# After Pane 1 completes, merge findings into Pane 2's context'), but checkpoints are implicit and validation is absent: no step to verify a pane has finished, and the worktree flow ends at 'git merge' with no post-merge verification such as running tests or resolving conflicts. Not a 4 because these validation gaps exceed 'minor'.

3 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers, a lean overview, and only one-level-deep pointers (a single external repo link; no nested references). Not a 5 because the ~45-line ECC Helper section with two full JSON plan examples is detail that belongs in a separate reference file rather than the overview SKILL.md.

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 identifies the niche tool (dmux), states both capability and explicit use conditions in third person, and carries good natural trigger terms. Its main gap is modest action specificity — it describes orchestration and coordination patterns without naming the concrete operations the skill actually teaches.

DimensionReasoningScore

Specificity

Names the domain and tool ('Multi-agent orchestration using dmux (tmux pane manager for AI agents)') plus 1-2 actions ('Patterns for parallel agent workflows', 'coordinating'), matching the anchor for domain plus 1-2 concrete actions without comprehensive coverage of concrete operations like pane creation or output merging.

3 / 5

Completeness

Explicitly answers both what ('Multi-agent orchestration using dmux... Patterns for parallel agent workflows') and when ('Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows') with concrete trigger phrases, fitting the top anchor rather than the 4 anchor whose 'when' clause still needs more specificity.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — 'running multiple agent sessions in parallel', 'multi-agent', 'parallel agent workflows' — plus harness names, but misses common variations like 'split this work', 'parallelize', or 'fan out'.

4 / 5

Distinctiveness Conflict Risk

The named tool dmux and tmux framing give it a clear niche with minor overlap risk against generic multi-agent orchestration or team-orchestration skills; not a 5 because 'multi-agent orchestration' alone is broad enough to collide with similar skills.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 3 missing, 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

valeriibeck-star/claude-skills

Path

skills/dmux-workflows/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.