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

86%

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

Quality

Content

81%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 highly actionable, well-sequenced body with strong validation checkpoints and feedback loops for a genuinely complex orchestration skill, plus appropriately externalized API reference and template files. The main weakness is verbosity from restated approval/safety guidance and inlined callback operational detail that could be split out.

Suggestions

Consolidate the repeated approval, danger-full-access, and host-execution guidance into one section and cross-reference it instead of restating it in 'Validate and obtain approval,' 'Run and monitor,' and 'Safety boundaries.'

Move the detailed callback/app-server setup and recovery procedure into a dedicated reference file (e.g. references/callbacks.md), keeping only the launch-time decision rules inline.

Tighten verbose paragraphs in the callback section into imperative bullets to reduce token cost without losing the decision logic.

Dimension	Reasoning	Score
Conciseness	Most content earns its place and it avoids basic-concept explanation, but at 444 lines it restates approval, danger-full-access, and host-execution guidance across multiple sections ("Validate and obtain approval," "Run and monitor," "Safety boundaries"), so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready bash commands ("node \"$RUNNER\" run\|validate\|status\|pause\|resume\|cancel" with exact flags) and a complete executable JavaScript workflow example covering discovery, pipelined audits, and synthesis.	5 / 5
Workflow Clarity	Sequences locate-runner through author, validate, approve, run, callback, and pause/resume/cancel with explicit validation ("node \"$RUNNER\" validate"), approval gates, feedback loops (failure/context-capacity → fix → resume), and a 6-step resume-after-edit checklist.	5 / 5
Progressive Disclosure	API detail is correctly externalized to references/workflow-api.md and a starter template to assets/workflow-template.js, both clearly signaled inline; however, the callback/app-server operational mechanism (~100 lines) is inlined and the body is long, leaving a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

92%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 precise, third-person description that clearly names concrete capabilities and gives explicit use/anti-use triggers, distinguishing it well from related skills. The only soft spot is trigger-term naturalness, which is slightly jargon-leaning and lacks synonyms or file extensions.

Dimension	Reasoning	Score
Specificity	Lists seven concrete lifecycle actions ("Create, review, run, inspect, pause, resume, and cancel") over durable JavaScript workflows coordinating headless Codex agents, giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly states what the skill does and when to use it via a "Use for ..." clause plus a "Do not use for a small linear task" anti-trigger, answering both what and when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural trigger phrases like "dynamic fan-out and fan-in," "multi-stage agent pipelines," "long background runs," and "loops or branches driven by worker results," but leans technical and omits synonyms or file extensions, keeping it below a 5.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined ("durable JavaScript workflows that coordinate multiple headless Codex agents" / "ports of Claude Code dynamic workflows") and the anti-trigger further narrows it, giving minimal conflict risk.	5 / 5
	Total	19 / 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: ee0f309

Reviewed: 3 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.