flow-parallel

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

Quality

61%

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

70%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 skill is a thorough, well-sequenced execution contract with excellent workflow clarity and strong actionability. Its weaknesses are monolithic structure (no reference files despite the length) and enforcement-language padding that inflates token cost.

Suggestions

Extract stable templates (launch.sh, the dependency-validation Python, the wave monitor loop) into scripts/ reference files and point to them from the body to improve progressive disclosure and cut inline tokens.

Consolidate the per-step 'DO NOT PROCEED' refrain and the Prohibitions section into a single concise guardrails block to remove repetitive padding.

Replace reliance on assumed external scripts (check-providers.sh, orchestrate.sh, agent-registry.sh) with either bundled copies or explicit existence-check guidance so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The core guidance is efficient (concrete bash/Python, no concept explanations Claude already knows), but the repeated 'MANDATORY/CANNOT SKIP/DO NOT PROCEED' refrain and a Prohibitions section that rehashes inline constraints add noticeable padding that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready WBS, launch.sh, dependency-validation, and monitoring scripts covering common cases; minor gaps come from template placeholders and reliance on external plugin scripts whose existence is assumed.	4 / 5
Workflow Clarity	A clearly numbered 7-step sequence with explicit validation gates between every step, error-handling feedback loops (retry failed WPs), and a quality spot-check checklist — this is a batch operation that DOES have validation, so the batch cap does not apply.	5 / 5
Progressive Disclosure	Headers and step sections give good structure, but the ~790-line body is monolithic with no bundle files; reusable templates (launch.sh, dependency validator, monitor loop) that could live in scripts/ references are inlined instead.	3 / 5
	Total	15 / 20 Passed

Description

53%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 names a recognizable domain, but it lacks an explicit 'when to use' trigger clause and its action verbs are somewhat generic. Adding a 'Use when ...' clause with synonyms would lift completeness and trigger quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to parallelize large refactors, batch migrations, or fix multiple issues at once.'

Add natural synonyms users say ('parallelize', 'batch', 'split this into work packages') to broaden trigger-term coverage.

Replace the generic verbs with more concrete actions ('decompose into work packages, launch independent workers, validate quality gates, aggregate results').

Dimension	Reasoning	Score
Specificity	Names the domain ('large changes, migrations, or multi-issue fixes') and two concrete actions ('Decompose and execute ... in parallel with quality gates'), but the verbs remain somewhat generic rather than enumerating comprehensive concrete actions.	3 / 5
Completeness	It has a clear 'what' (decompose and execute compound tasks in parallel with quality gates) but no explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes relevant natural terms like 'migrations' and 'multi-issue fixes', but misses common synonyms (e.g. 'parallelize', 'batch', 'refactor') and relies on fairly generic phrasing like 'large changes'.	3 / 5
Distinctiveness Conflict Risk	The combination of parallel decomposition with quality gates carves a mostly-distinct niche with only minor overlap risk against related code-modification skills.	4 / 5
	Total	13 / 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
skill_md_line_count	SKILL.md is long (809 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/flow-parallel/SKILL.md
Commit: 6a1fd2b

Reviewed: 3 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.