flow-define

Multi-AI requirements scoping using available external providers (Double Diamond Define phase). Priority triggers: octo define, octo scope, co-define, co-scope. DO NOT use for implementation, research, review/validation, or built-in commands.

Quality

82%

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

Quality

Content

77%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 body is highly actionable with an exceptionally clear, checkpointed multi-step workflow and concrete commands. Its weaknesses are heavy content duplication across three restatements of the same workflow and references to bundle files that are not present in the skill package.

Suggestions

Consolidate the three restatements of the 7-step workflow (Execution Contract, "Define Workflow - Define Phase", and Implementation Instructions) into a single authoritative sequence to remove duplication.

Move the two full example problem-definition outputs (Example 1 and Example 2) into a separate references file and link to it, keeping only a brief example inline.

Either provide the referenced skills/blocks/*.md files in a references/ directory or replace the dangling references with self-contained guidance so progressive disclosure is one level deep.

Dimension	Reasoning	Score
Conciseness	The ~730-line body restates the same 7-step workflow three times (Execution Contract, Define Workflow section, Implementation Instructions) and inlines two full example outputs; mostly actionable but with substantial duplication that could be tightened.	3 / 5
Actionability	Concrete, copy-paste-ready bash commands with real script paths, specific AskUserQuestion prompts with enumerated options, and a complete problem-definition output template covering common cases.	5 / 5
Workflow Clarity	A clearly numbered 7-step sequence with explicit blocking checkpoints ("DO NOT PROCEED TO STEP N until..."), a validation step (Step 5 verifies the synthesis file, exit 1 on failure), and a feedback loop for error recovery.	5 / 5
Progressive Disclosure	Has section structure, but referenced bundle files (skills/blocks/*.md) do not exist in the actual bundle (no references/, scripts/, or assets/ directories), and content that should be split (duplicate workflow descriptions, full example outputs) is inlined.	3 / 5
	Total	16 / 20 Passed

Description

87%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 is strong: it states the concrete purpose, gives explicit priority triggers for when-to-use, and excludes adjacent domains to reduce conflict. Minor improvement would be adding a couple more plain-language capability verbs beyond the command-name triggers.

Dimension	Reasoning	Score
Specificity	Names the domain and several specific actions ("Multi-AI requirements scoping", "Double Diamond Define phase") plus explicit trigger variants and exclusions; minor gaps versus a fully comprehensive capability list anchor 5.	4 / 5
Completeness	Clearly answers both what (Multi-AI requirements scoping, Define phase) and when (priority triggers) plus when-not (DO NOT use for...), with concrete trigger phrases matching the anchor 5 example.	5 / 5
Trigger Term Quality	Explicit natural trigger phrases ("octo define, octo scope, co-define, co-scope") give good keyword coverage with synonyms, though the terms are command-names rather than fully natural-language phrasings.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Define phase requirements scoping) with distinct command triggers and explicit exclusions, yielding minimal conflict risk with other skills.	5 / 5
	Total	18 / 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 (739 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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