parallel-task

Coordinate plan files by launching multiple parallel subagents for unblocked tasks. Triggers on explicit "/parallel-task" commands.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/parallel-task/SKILL.md

Quality

Content

75%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 content is a lean, actionable orchestration playbook with a clear multi-step workflow, explicit safety boundaries, reusable templates, and a validation checkpoint. Its main limitation is the absence of an explicit per-task validation gate inside the repeat loop and no progressive disclosure via supporting files.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and stays task-focused; the longer sections are the reusable prompt and run-summary templates rather than padding, so it lands at 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean-every-token-earns-its-place anchor at 5.	4 / 5
Actionability	It supplies a copy-paste-ready Task Prompt Template with labeled placeholders, concrete usage examples, and explicit step-by-step instructions, fitting 'mostly executable guidance; concrete code or commands with minor gaps'; the placeholder-filling requirement keeps it just below fully-copy-paste-ready at 5.	4 / 5
Workflow Clarity	Steps 1-6 are clearly sequenced with an explicit repeat loop (Step 5) and a validation checkpoint (Step 6, plus the Safety Boundary 'Do not mark tasks complete until validation... has actually been checked'), matching 'clear sequence with most checkpoints present; minor validation gaps'; per-task validation is only implicit mid-loop rather than an explicit per-task checkpoint, holding it under 5.	4 / 5
Progressive Disclosure	With no bundle files present, all content lives inline in a single well-sectioned SKILL.md (Safety Boundaries, Process steps, templates, examples), which is appropriately placed and easy to navigate, fitting 'good structure; most content appropriately placed; minor organization gaps' rather than the one-level-deep-references anchor at 5 (which requires external files this skill does not use).	4 / 5
	Total	16 / 20 Passed

Description

62%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 cleanly answers what the skill does and when to invoke it via an explicit command trigger, with a clear niche. It is slightly held back by limited action breadth and thin trigger-term synonyms, leaving it solidly mid-to-upper rather than top-tier.

Suggestions

Add 1-2 more concrete capabilities (e.g., 'tracks dependencies, surfaces blockers, and produces a run summary') to lift specificity toward 4-5.

Broaden trigger terms beyond the slash command, e.g. 'Use when the user asks to run a plan in parallel, fan out tasks to subagents, or execute multiple unblocked tasks concurrently.'

Include a natural-language trigger path so the 'when' is not solely reliant on the explicit /parallel-task command.

Dimension	Reasoning	Score
Specificity	"Coordinate plan files by launching multiple parallel subagents for unblocked tasks" names the domain and one concrete action (launching parallel subagents), but does not enumerate the broader set of capabilities, so it stops at the 1-2 concrete actions anchor rather than the several-actions anchor at 4.	3 / 5
Completeness	It states both a clear 'what' (coordinate plan files via parallel subagents for unblocked tasks) and an explicit 'when' (triggers on explicit /parallel-task commands), satisfying the both-present anchor; the 'when' is somewhat narrow (only the slash command), keeping it just below the fully-explicit anchor at 5.	4 / 5
Trigger Term Quality	The phrase "Triggers on explicit "/parallel-task" commands" plus "parallel subagents" and "plan files" provides some relevant keywords, but coverage is thin with no synonyms or natural-language variations a user might say, matching the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor at 4.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to an explicit "/parallel-task" command and the niche of parallel subagent coordination for plan files makes it mostly distinct with only minor overlap risk against generic task/agent skills, fitting the 'mostly distinct; minor overlap risk' anchor rather than the clear-niche-minimal-conflict anchor at 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: jdrhyne/agent-skills
Path: skills/parallel-task/SKILL.md
Commit: 439cd3a

Reviewed: 13 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.