parallel-task

Only to be triggered by explicit /parallel-task commands.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a clear, actionable orchestration workflow with strong sequencing and validation checkpoints. Its main weakness is moderate verbosity from duplicated guidance and large inline templates that could be externalized.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and avoids explaining basics, but repeats validation/update guidance across Step 3, Step 4, and the prompt template, so it could be tightened.	2 / 3
Actionability	It provides a concrete, parameterized task-prompt template plus exact rules (e.g. 'NEVER PUSH. ONLY COMMIT', 'Stage only files for this task') and explicit validation requirements, giving copy-ready actionable guidance.	3 / 3
Workflow Clarity	Steps 1-5 are clearly sequenced with explicit validation checkpoints (RED->GREEN or documented alternatives), retry/escalation feedback loops, and per-wave commit gating before proceeding.	3 / 3
Progressive Disclosure	There are no bundle files and sections are well-organized, but two large inline templates (task prompt, execution summary) consume ~50 lines that could be split into referenced files, leaving it somewhat monolithic.	2 / 3
	Total	10 / 12 Passed

Description

22%

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 functions as a pure trigger guard but fails to describe what the skill does, leaving users and the model without capability context. It is distinct yet severely incomplete and non-specific.

Suggestions

State the skill's concrete actions, e.g. 'Parses plan files and orchestrates subagents in dependency-ordered parallel waves to execute development plans.'

Keep the explicit trigger but add a natural-language "Use when..." clause covering phrases like 'parallel tasks', 'run a plan in parallel', or 'execute plan tasks concurrently'.

Mention both the what (orchestrate parallel subagents per a plan) and the when (explicit /parallel-task invocation) to satisfy completeness.

Dimension	Reasoning	Score
Specificity	The description only states a trigger ("Only to be triggered by explicit /parallel-task commands") and names no concrete capabilities, matching the vague/no-actions anchor.	1 / 3
Completeness	It gives an explicit "when" trigger but entirely omits "what" the skill does, so it is missing one of the two required answers.	1 / 3
Trigger Term Quality	It includes one relevant natural term ("/parallel-task") that users would say, but offers no variations or broader coverage, fitting the partial-keywords anchor.	2 / 3
Distinctiveness Conflict Risk	The dedicated slash-command trigger is fairly distinct, but the description provides no capability niche, so overlap risk is only partially reduced.	2 / 3
	Total	6 / 12 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: am-will/codex-skills
Commit: e343715

Reviewed: 14 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.