parallel-execution-optimizer

Use when the user wants a task done much faster through parallel work, concurrent agents, batched tool calls, isolated worktrees, or many independent verification lanes without losing correctness.

Quality

84%

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

88%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 tight, well-structured instruction skill: lean prose, a clearly sequenced workflow with validation and feedback loops, and concrete templates for the lane matrix and result reporting. The main gaps are the absence of any bundle references (keeping it just short of the level-5 progressive-disclosure anchor) and the inherent abstractness of its methodology-level guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no padding or explanation of concepts Claude already knows; every section (Core Pattern, Lane Matrix, Execution Rules, Output Shape, Failure Modes) earns its place.	5 / 5
Actionability	Concrete, executable guidance is provided via copy-paste-ready templates (the lane matrix table and the output-shape block) and specific rules (batch reads, isolated worktrees, gates for destructive commands), but as methodology rather than literal commands there are minor gaps in direct executability.	4 / 5
Workflow Clarity	A clear 7-step Core Pattern is sequenced with explicit validation checkpoints (step 6 merge only after evidence, step 7 verification table), a feedback loop (pause dependent lanes and update the matrix on a blocker), and explicit gates for destructive/batch operations, satisfying the destructive-operation validation requirement.	5 / 5
Progressive Disclosure	Content is well-organized into clearly labeled sections with easy navigation and nothing that belongs in a separate file, but at ~65 lines it exceeds the under-50-line simple-skill exception and provides no one-level-deep references that the level-5 anchor highlights.	4 / 5
	Total	18 / 20 Passed

Description

80%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 strong, trigger-rich description that names several concrete parallelism mechanisms and opens with an explicit 'Use when' clause. Its main weakness is structural: the capability statement is embedded inside the trigger clause rather than cleanly separated, and the broad 'task done much faster' framing leaves minor conflict risk.

Suggestions

Lead with a standalone capability clause (e.g. 'Speeds up tasks by running independent work in parallel: concurrent agents, batched tool calls, isolated worktrees, and multiple verification lanes.') before the 'Use when' trigger.

Add a couple of natural synonyms users say, such as 'speed up', 'run at the same time', or 'in parallel', to broaden trigger coverage.

Sharpen the trigger to reduce overlap with generic optimization skills, e.g. 'Use when the user wants to speed up a multi-part task by parallelizing independent work without losing correctness.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete mechanisms — 'parallel work, concurrent agents, batched tool calls, isolated worktrees, or many independent verification lanes' — giving comprehensive coverage of the parallelism domain rather than vague abstractions.	5 / 5
Completeness	It has an explicit 'Use when...' trigger and conveys what the skill does via the enumerated mechanisms, but the 'what' is fused into the 'when' clause rather than stated as a clean standalone capability, so it is not quite the level-5 pattern of separate capability and trigger statements.	4 / 5
Trigger Term Quality	Natural terms like 'much faster', 'parallel work', 'concurrent agents', 'batched tool calls', and 'worktrees' map to phrases users actually say, but a few common synonyms ('speed up', 'at the same time', 'in parallel') are absent.	4 / 5
Distinctiveness Conflict Risk	The niche (parallel execution via concurrent agents, worktrees, batched calls) is distinct with specific triggers, but the broad opening 'the user wants a task done much faster' creates minor overlap risk with general optimization or speed-related skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/parallel-execution-optimizer/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.