flow-develop

Multi-AI implementation using available external providers (Double Diamond Develop phase)

Quality

41%

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

47%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers a clear, well-gated multi-step workflow with strong validation checkpoints, but it is far too verbose and self-duplicating, with monolithic inline content and unresolved template placeholders instead of clean file references.

Suggestions

Collapse the duplicated EXECUTION CONTRACT and 'Develop Workflow' sections into a single canonical sequence; remove the repeated banner variants and re-explained context-detection steps to cut the body roughly in half.

Resolve or remove the template placeholders ({{PREAMBLE}}, ${codex_status}, <user's implementation request>) so the remaining commands are directly executable, and fix the \n literal usage in the enrichment block.

Split the large inline reference material (subtype table, examples, checklists) into actual bundle files under references/ and link to them one level deep, instead of keeping everything in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~780-line body is verbose and heavily duplicated — the 7-step EXECUTION CONTRACT and a second 'Develop Workflow' section re-explain the same steps, banners, and context detection — and re-states concepts Claude already knows; pervasive padding matches the verbose anchor.	1 / 3
Actionability	Substantial real, executable bash commands and Agent() invocations are present, but many are templated with unresolved placeholders (${codex_status}, <user's implementation request>, ${prompt}) and the enrichment block uses \n literals in a way that is not directly executable, leaving key details missing.	2 / 3
Workflow Clarity	Steps 1-7 are explicitly numbered and mandatory with blocking validation checkpoints ('DO NOT PROCEED'), a validation gate that exits on failure, an error-handling section, and checklists — clear sequencing with feedback loops for recovery.	3 / 3
Progressive Disclosure	No bundle files exist, yet all content sits in one monolithic file with template placeholders ({{PREAMBLE}}, {{VISUAL_INDICATORS}}, {{QUALITY_GATES}}) pointing to includes that are not provided; section structure exists but content that should be split is inline.	2 / 3
	Total	8 / 12 Passed

Description

35%

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 is a terse domain label with process jargon rather than a clear, user-facing trigger statement. It conveys a rough 'what' but omits any 'when to use' guidance and leans on internal vocabulary users would not naturally say.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. building a feature, creating an API, implementing complex logic) so the 'when' is stated, not implied.

Replace jargon ('Double Diamond Develop phase', 'external providers') with plain terms users actually say, and add concrete actions (generates multiple implementation approaches, synthesizes them into a plan).

Expand to list several distinct concrete actions to raise specificity and reduce overlap with generic implementation skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Multi-AI implementation') plus a single vague action ('implementation') but does not list multiple concrete actions like generating approaches, synthesizing, or creating code; not comprehensive enough for a 3.	2 / 3
Completeness	States a weak 'what' but provides no 'Use when...' trigger clause, so 'when' is entirely missing; per the guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Dominant terms are process jargon a user would rarely say ('Double Diamond Develop phase', 'external providers'); natural trigger phrases like 'build a feature', 'create an API', or 'implement' are absent.	1 / 3
Distinctiveness Conflict Risk	Tied to a specific plugin workflow so conflict risk is moderate, but it is terse and could overlap with other implementation/coding skills, and lacks distinct trigger phrases.	2 / 3
	Total	7 / 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 (787 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/flow-develop/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.