dynamic-workflow

Create, review, run, inspect, pause, resume, and cancel durable JavaScript workflows that coordinate multiple headless Codex agents. Use for dynamic fan-out and fan-in, per-item analysis, multi-stage agent pipelines, loops or branches driven by worker results, long background runs, and ports of Claude Code dynamic workflows. Do not use for a small linear task that one Codex turn can handle directly.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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 well-structured, actionable overview that offloads detail to real referenced files and includes strong validation checkpoints for a complex, safety-sensitive workflow skill. Its main weakness is mild repetition of the callback-handling guidance that could be tightened.

Suggestions

Reconcile the near-duplicate callback guidance: the "Do not call wait, poll status, start a watcher" rule appears in both the armed-notification branch and the post-launch behavior list — consolidate into one canonical statement.

Condense the app-server generation / lifecycle explanation, which is covered twice (in the codex-dynamic setup paragraph and the restart/recovery section), into a single short note with a pointer to details.

Render the four post-launch response branches (armed / missing-armed / not-required / no-run-id) as a compact numbered checklist rather than separate prose bullets so the decision flow is scannable.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful with no padding of basic concepts, but callback-classification and armed-notification guidance is restated near-verbatim across sections and could be reconciled, keeping it just below the lean level-5 anchor.	4 / 5
Actionability	Provides copy-paste shell commands, a complete example workflow with a real JSON schema, exact flags, and a numbered resume checklist; minor gaps (placeholders like <run-id> and the prose-only codex-dynamic/server setup) keep it below fully-copy-paste level 5.	4 / 5
Workflow Clarity	Sequencing is explicit with validation checkpoints (validate before launch, 6-step resume-after-edit, context-capacity → chunk → validate → resume) and a cancel-and-verify feedback loop for failed callbacks, but the multi-branch callback handling is spread across prose rather than one tight checklist.	4 / 5
Progressive Disclosure	The body is a concise overview that clearly signals two real one-level-deep references present on disk — references/workflow-api.md and assets/workflow-template.js — keeping the bulk API detail offloaded while the motivating example stays inline, matching the well-signaled navigation anchor.	5 / 5
	Total	17 / 20 Passed

Description

100%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 specific, trigger-rich, and complete, clearly stating both what the skill does and when to use it while carving out an explicit negative boundary. It is a strong, low-conflict trigger description.

Dimension	Reasoning	Score
Specificity	Lists seven concrete verbs (Create, review, run, inspect, pause, resume, cancel) plus concrete mechanisms ("durable JavaScript workflows", "headless Codex agents"), matching the comprehensive-coverage anchor rather than the minor-gaps level 4.	5 / 5
Completeness	Explicitly answers both what (create/run/manage durable JS workflows coordinating headless Codex agents) and when (a six-item "Use for..." trigger list) and adds a negative boundary, exceeding the concrete what-and-when anchor.	5 / 5
Trigger Term Quality	Natural phrases a user would say are well covered — "dynamic fan-out and fan-in", "per-item analysis", "multi-stage agent pipelines", "long background runs", "ports of Claude Code dynamic workflows" — matching the comprehensive-natural-terms anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (durable JS workflow runtime over codex exec) with distinct triggers and an explicit "Do not use for a small linear task" disambiguator, minimizing overlap risk with other skills.	5 / 5
	Total	20 / 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: pchalasani/claude-code-tools
Path: plugins/dynamic-workflow/skills/dynamic-workflow/SKILL.md
Commit: c35a135

Reviewed: about 13 hours 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.