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.

63

Quality

76%

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
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.

The body is a tight, actionable catalog of orchestration patterns with concrete commands and a useful troubleshooting section, respecting the reader's competence. Its main weakness is workflow rigor: parallel agent sessions are batch operations on the codebase, yet no explicit post-merge validation checkpoint (test/build) is prescribed, and the ECC orchestration scripts it instructs the reader to run are not part of the skill bundle.

Suggestions

Add an explicit post-merge validation step to the workflow patterns — e.g., 'After merging panes, run the test suite/build and only proceed when green' — to close the feedback loop that batch parallel operations require.

Either bundle scripts/orchestrate-worktrees.js (and its lib/worker-script dependencies) with the skill or state clearly that the ECC Helper section applies only within the ECC repository, so readers outside that repo aren't pointed at a missing script.

Move the ECC Helper detail (the two full plan.json examples) into a references/ file and keep a one-line pointer plus a minimal example in SKILL.md, trimming the duplicated second seedPaths example.

DimensionReasoningScore

Conciseness

Lean and competent throughout — no re-explanation of tmux or multi-agent basics, terse patterns and best practices. Minor trimmable padding: the second seedPaths JSON example largely repeats the first example's structure.

4 / 5

Actionability

Mostly executable guidance: `dmux`, `git worktree add -b feat/auth ../feature-auth HEAD`, `tmux capture-pane -pt <session>:0.<pane-index>`, and `node scripts/orchestrate-worktrees.js plan.json --execute` with complete plan.json examples. Gap: the referenced orchestration scripts do not ship with the skill bundle.

4 / 5

Workflow Clarity

The five patterns give a rough create-panes → merge → integrate sequence and Troubleshooting covers failure modes, but there is no explicit post-merge validation checkpoint (run tests/build before proceeding). Parallel agent sessions are batch operations on the codebase, so the missing validation loop caps this at 3.

3 / 5

Progressive Disclosure

A single well-organized file with clear sections, no deep or broken reference nesting, and all content inline (no bundle files exist). Minor gap: the ~45-line ECC Helper section with two full JSON examples arguably belongs in a separate reference file.

4 / 5

Total

15

/

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.

A strong description: third-person, concrete, and it explicitly pairs capabilities with a 'Use when...' trigger clause naming dmux, tmux, and multiple harnesses. The only improvements are broadening natural trigger synonyms and mentioning the pane-merge/worktree capabilities to sharpen distinctiveness.

DimensionReasoningScore

Specificity

Names the concrete domain ('tmux pane manager for AI agents', 'parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses') with several specific capabilities, but stops short of the comprehensive action list (pane creation/merge, worktree isolation) the body actually covers.

4 / 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, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Good natural-term coverage ('multi-agent', 'parallel agent sessions', 'dmux', 'tmux', 'coordinating multi-agent development workflows') that matches what users would say, though common variations like 'run in parallel' or 'split this work' are absent.

4 / 5

Distinctiveness Conflict Risk

'dmux' carves a clear niche with distinct triggers, but the broad 'multi-agent orchestration' framing has minor overlap risk with built-in subagent/workflow skills; not the minimal-conflict profile of anchor 5.

4 / 5

Total

17

/

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

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

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

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.