flow-develop

Multi-AI implementation using available external providers (Double Diamond Develop phase). DO NOT use for simple code edits, reading/reviewing code, built-in commands, or trivial single-file changes.

Quality

58%

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/flow-develop/SKILL.md

Quality

Content

56%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 highly actionable with strong validation gates and checklists, but it is severely bloated by structural duplication and conflicting dual numbering that hurt conciseness and workflow clarity. Progressive disclosure is only partial because large inlined sections should live in referenced files.

Suggestions

Delete the redundant second 'Develop Workflow - Develop Phase' section and the extra banner/visual-indicator blocks; keep a single canonical step sequence to fix the duplication and the conflicting numbering.

Move the dev-subtype supplement table, the banner templates, and the example implementation plans into referenced reference files (e.g. references/subtypes.md, references/banner.md) and link to them one level deep.

Resolve the template placeholders ({{PREAMBLE}}, {{VISUAL_INDICATORS}}, {{QUALITY_GATES}}) into real included content or explicit file references so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with major structural duplication — the EXECUTION CONTRACT (Steps 1-7) is restated as a second 'Develop Workflow' section (Steps 1-5) and the provider banner appears three times — well below an efficient token budget. It narrowly avoids a 1 because the content is actionable rather than explaining basic concepts.	2 / 5
Actionability	Provides concrete executable bash commands, script paths, TaskCreate/Agent invocation examples, and a detailed implementation-plan template, with only minor gaps from template placeholders (e.g., ${codex_status}, <user's task description>).	4 / 5
Workflow Clarity	Sequenced steps with explicit validation (Step 5 synthesis-file gate), error-handling guidance, and checklists are present, but two conflicting step-numbering schemes (Steps 1-7 vs Steps 1-5 with mismatched meanings) introduce ambiguity that keeps it below 5.	4 / 5
Progressive Disclosure	Section headers and one-level references to plugin block files exist, but content that should be separated (the duplicated workflow, repeated banners) is inlined and template placeholders ({{PREAMBLE}}, {{VISUAL_INDICATORS}}, {{QUALITY_GATES}}) are not clearly signaled as external includes.	3 / 5
	Total	13 / 20 Passed

Description

61%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 usefully excludes adjacent use cases, but it relies on negative triggers rather than an explicit 'Use when...' clause and its action list is thin. It is reasonably distinctive but not comprehensive.

Suggestions

Add an explicit positive 'Use when...' clause (e.g., 'Use when building features or generating implementation approaches that benefit from multi-provider analysis') to lift completeness above 3.

List 1-2 more concrete actions beyond 'implementation' (e.g., 'generates multiple implementation approaches, synthesizes a recommended plan') to raise specificity.

Soften the jargon 'Double Diamond Develop phase' in the lead phrase so the primary trigger reads as something a user would naturally say.

Dimension	Reasoning	Score
Specificity	Names the domain ('Multi-AI implementation') and one concrete mechanism ('using available external providers') but lists no further specific actions, sitting between the minimal 'Processes PDF files' anchor (2) and a fuller action list (4).	3 / 5
Completeness	Provides a clear 'what' but only negative trigger guidance ('DO NOT use for...') with no positive 'Use when...' clause, so per the rubric cap completeness stays at 3.	3 / 5
Trigger Term Quality	Includes several natural terms users would say ('implementation', 'code edits', 'reading/reviewing code', 'single-file changes') though the headline leans on jargon ('Double Diamond Develop phase') and a few synonyms are missing, fitting just above the midpoint.	4 / 5
Distinctiveness Conflict Risk	The explicit exclusion list ('simple code edits, reading/reviewing code, built-in commands, trivial single-file changes') sharply reduces overlap with adjacent edit/review skills, leaving only minor overlap with general build/feature skills.	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
skill_md_line_count	SKILL.md is long (794 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/flow-develop/SKILL.md
Commit: 805d58c

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.