flow-parallel

Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates

Quality

63%

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 ./.claude/skills/flow-parallel/SKILL.md

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 highly actionable with an exceptionally clear, gated multi-step workflow, but it is monolithic and verbose. Splitting large script templates into reference files and trimming redundant enforcement prose would meaningfully improve it.

Suggestions

Move the large launch.sh template and the python dependency-validation script into separate reference files under scripts/ or references/ and link to them, reducing the inline wall of code.

Trim redundant enforcement language — the repeated 'MANDATORY - CANNOT SKIP' headers, 'DO NOT PROCEED' lines, and the Prohibitions section largely restate the step gates.

Consolidate the four usage examples into a single concise reference, since they demonstrate the same decomposition pattern with diminishing new information.

Dimension	Reasoning	Score
Conciseness	The body is action-oriented rather than explaining concepts Claude already knows, but at ~780 lines it is padded with redundant enforcement language (repeated 'MANDATORY - CANNOT SKIP', 'DO NOT PROCEED TO STEP X', and a Prohibitions section that rehashes the steps) and could be tightened significantly.	2 / 3
Actionability	It provides fully executable bash and python scripts (e.g., the DFS cycle-detection dependency validator, the launch.sh worktree setup, the wave-based monitor loop) with concrete file paths and copy-paste-ready commands.	3 / 3
Workflow Clarity	A clear 7-step sequence with named validation gates (wbs_generated, instructions_written, processes_launched, all_work_packages_complete), explicit 'DO NOT PROCEED' checkpoints, error-handling feedback loops, and a prohibition checklist.	3 / 3
Progressive Disclosure	The single ~780-line SKILL.md has good internal section structure, but no bundle files exist and large blocks that could be split out (the launch.sh template, the python dependency validator) are inlined; the one external reference (skills/blocks/codex-host-adapter.md) is not part of the bundle.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 states a clear purpose and domain but lacks an explicit "when to use" trigger clause and leans on some abstract verbs and jargon. It is solid but not exemplary.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when the user asks to run several independent tasks at once, parallelize a migration, or fix multiple issues simultaneously').

Replace the abstract 'execute' and the jargon 'quality gates' with more concrete, user-facing actions to lift specificity.

Add common keyword variations users would actually say (e.g., 'parallel', 'split up work', 'batch fixes', 'run at the same time').

Dimension	Reasoning	Score
Specificity	The phrase "Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates" names a clear domain (large changes, migrations, multi-issue fixes) and several actions (decompose, execute, parallelize), but the verb "execute" is fairly abstract compared to the granular anchor-3 example.	2 / 3
Completeness	It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like "migrations", "multi-issue fixes", and "in parallel" are reasonable natural keywords, but "quality gates" is jargon and common user variations (e.g., "run tasks in parallel", "split up work") are missing.	2 / 3
Distinctiveness Conflict Risk	The "decompose and execute in parallel with quality gates" niche is fairly specific, but broad terms like "large changes" and "migrations" could still overlap with other orchestration or batch-automation skills.	2 / 3
	Total	8 / 12 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
skill_md_line_count	SKILL.md is long (788 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/flow-parallel/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.