parallel-task

Execute plan files by launching multiple parallel subagents to complete tasks simultaneously. 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

The canonical home for this skill is parallel-task in jdrhyne/agent-skills

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 body is a well-structured, concise orchestration workflow with concrete templates, a repeat loop, and a final validation step — a solid 4 across all dimensions. It falls short of 5 mainly on workflow detail: dependency/unblocked-task detection criteria and per-batch checkpoints are left implicit.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanation of concepts Claude already knows, and both templates earn their tokens. Minor trimming is possible: the summary bullet list in Step 6 repeats the task-prompt summary items, and 'Use Orchestration Mode' is an undefined one-liner.	4 / 5
Actionability	Concrete, usable guidance throughout: a complete task-prompt template with placeholders, example usage commands, and an execution summary template. Minor gaps remain — how 'unblocked' tasks are determined and where/how completed tasks are marked are not specified.	4 / 5
Workflow Clarity	A clear 6-step sequence with a repeat loop (Step 5 re-reads the plan for newly unblocked tasks) and explicit final validation (Step 6: check final state, perform available tests, address issues), plus an error handling section. Not anchor 5: no explicit criteria for detecting unblocked tasks and no checkpoint between parallel batches.	4 / 5
Progressive Disclosure	No bundle files exist; the process, templates, and examples are appropriately inline and well-sectioned with no nested references. Minor organization gaps remain: inconsistent heading levels ('### Step 5' vs '## Step 6') and the undefined 'Use Orchestration Mode' line.	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 clearly states what the skill does and includes an explicit trigger clause, but coverage of capabilities and natural trigger phrasing is thin. Adding natural-language use cases ('use when running a sprint or plan with multiple independent tasks') and a fuller action list would lift specificity and trigger quality.

Suggestions

Add natural trigger phrases beyond the slash command, e.g. 'Use when the user wants to run a plan, sprint, or multiple independent tasks in parallel.'

Enumerate the concrete operations in the description (parse sprint sections, extract tasks, launch parallel subagents, monitor and re-loop until the plan completes) to improve specificity.

Include synonyms users naturally say, such as 'parallel agents', 'sprint', 'phase', or 'task plan', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('plan files', 'parallel subagents') and 1-2 concrete actions ('Execute plan files', 'launching multiple parallel subagents'), but does not enumerate the several specific operations (parse sprints, extract tasks, monitor, validate) needed for anchor 4.	3 / 5
Completeness	Both 'what' ('Execute plan files by launching multiple parallel subagents') and 'when' ('Triggers on explicit /parallel-task commands') are explicitly present, but the when-clause covers only the command and lacks broader natural-language trigger phrases, so it falls short of anchor 5.	4 / 5
Trigger Term Quality	The only trigger keyword is the slash command '/parallel-task', which is relevant, but common natural variations users would say ('run the plan in parallel', 'multiple agents', 'sprint', 'phase') are missing.	3 / 5
Distinctiveness Conflict Risk	The parallel-subagent plan-execution niche plus a specific command trigger is mostly distinct with only minor overlap risk against generic orchestration/plan-execution skills, matching anchor 4.	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: bap-jorkim/agent-skills-fork-feb-25
Path: skills/parallel-task/SKILL.md
Commit: f4ed46f

Reviewed: 4 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.