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

55%

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 delivers genuinely executable orchestration commands with strong mandatory sequencing and validation gates, but it is severely duplicated — the same steps and banners are restated two to three times under different numbering schemes — and it monolithically inlines content that belongs in reference files. The unresolved template placeholders and dangling references to non-bundled files compound the structural debt.

Suggestions

Delete the duplicated "MANDATORY: Context Detection & Visual Indicators" section that restates contract Steps 1-2 and the banner templates verbatim, and consolidate to one step numbering — this alone would remove ~100 lines and lift conciseness toward 4.

Move the subtype/quality-supplement tables, all banner templates, and the worked examples into a references/ file (e.g. references/subtypes.md, references/banners.md) and link them explicitly, resolving the progressive-disclosure gap.

Resolve or remove the {{PREAMBLE}}, {{VISUAL_INDICATORS}}, and {{QUALITY_GATES}} placeholders and the dangling skills/blocks/*.md references, which currently point at files outside the skill bundle and leave the reader with incomplete instructions.

Dimension	Reasoning	Score
Conciseness	Steps 1, 1b, and 2 of the EXECUTION CONTRACT are duplicated nearly verbatim in the later "MANDATORY: Context Detection & Visual Indicators" section, banner templates appear three times in different formats, and ASCII-art diagrams and "WHY:" rationale paragraphs pad the file — several clearly unnecessary padded sections, matching anchor 2.	2 / 5
Actionability	Concrete, executable bash throughout (octo-state.sh update_state, orchestrate.sh develop, the find -mmin -10 synthesis gate) plus an exact implementation-plan format and full agent prompts; placeholder-laden snippets (taskId: "...", <user's implementation request>, underived ${codex_status}) keep it short of copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	The 7-step contract has explicit blocking gates, a validation gate with failure handling (Step 5), and per-step error handling — approaching anchor 5, but a second conflicting step numbering ("How It Works" Steps 1-5, "Implementation Instructions" steps 1-6) and two divergent banner formats create ambiguity about which sequence governs.	4 / 5
Progressive Disclosure	Real, consistent section headers exist, but ~794 lines inline content that belongs in reference files (subtype tables, banner templates, two worked examples, agent prompts), and the referenced paths (skills/blocks/engineering-method-selection.md, {{PREAMBLE}}, {{VISUAL_INDICATORS}}, {{QUALITY_GATES}}) resolve to nothing in this skill's bundle — anchor 3's "content that should be separate is inline".	3 / 5
	Total	13 / 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 names its domain and draws clear negative boundaries, but provides no positive trigger guidance and no concrete capability list. Users searching for help building a feature would not naturally match this description, and adjacent implementation skills remain an overlap risk.

Suggestions

Add a positive trigger clause, e.g. "Use when the user asks to build, implement, or develop a feature or multi-file change" — this converts the exclusion-only trigger into a complete what+when pair and lifts completeness above 3.

List 2-3 concrete capabilities (e.g. "orchestrates Codex and Antigravity CLIs to generate competing implementation approaches, synthesizes them, and quality-gates the result") to raise specificity and trigger-term quality.

Include natural synonyms users say ("build", "implement", "develop", "create") so the skill surfaces for common phrasings, not just the technical term "Multi-AI implementation".

Dimension	Reasoning	Score
Specificity	"Multi-AI implementation using available external providers (Double Diamond Develop phase)" names the domain and a single action mechanism but lists no concrete operations; the exclusion clause adds some concreteness, keeping it above the purely generic anchor 2 but short of anchor 4's several specific actions.	3 / 5
Completeness	The "what" is clearly stated but "when" is given only as exclusions ("DO NOT use for simple code edits, reading/reviewing code...") with no positive "Use when..." clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords like "implementation", "code edits", and "single-file changes" are present, but they appear only in the negative clause — natural positive phrases users would say ("build a feature", "implement X") are missing, matching anchor 3's missing-common-variations profile.	3 / 5
Distinctiveness Conflict Risk	The "Double Diamond Develop phase" framing plus an explicit exclusion list (simple edits, code review, built-in commands) distinguishes it from adjacent skills; it lacks a positive distinct trigger niche needed for 5.	4 / 5
	Total	13 / 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: 0093dab

Reviewed: 5 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.