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

59%

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-define/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 body delivers a well-sequenced, actionable workflow with validation and checklists, but is markedly verbose through heavy duplication and keeps content inlined that would benefit from being split into reference files.

Suggestions

De-duplicate the banner (define once and reference it) and consolidate the orchestrate.sh define invocation to a single canonical location to cut hundreds of lines.

Extract the worked auth example and the Problem Definition Format template into reference files under references/ and link to them one level deep.

Collapse the overlapping 'Execution Contract', 'How It Works', and 'Implementation Instructions' sections into a single sequenced workflow to remove restated content.

Dimension	Reasoning	Score
Conciseness	The ~745-line body duplicates the banner three times, repeats the orchestrate.sh define command ~4 times, and restates the Execution Contract across 'How It Works' and 'Implementation Instructions', plus padded explanatory lines such as 'This is the convergent phase after discovery'.	2 / 5
Actionability	Provides concrete copy-pasteable bash commands, a detailed AskUserQuestion block, and a fully worked example, with only minor gaps from placeholders like '<user clarification request>' and dependence on external plugin scripts.	4 / 5
Workflow Clarity	Seven blocking steps are explicitly sequenced with per-step 'DO NOT PROCEED' gates, a validation step (Step 5 checks the synthesis file), and a checklist, but validation is stop-and-report rather than a fix-and-retry feedback loop.	4 / 5
Progressive Disclosure	No bundle files exist and all referenced paths are external to the skill; the body is a single monolithic file with inlined banners, a large example, and a format template that could be split into reference files, though section headers provide some structure.	3 / 5
	Total	13 / 20 Passed

Description

62%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 purpose and provides explicit trigger guidance plus exclusions, but relies on command-style triggers ('octo define/scope') rather than natural user language and lists few concrete actions.

Suggestions

Add natural-language trigger phrases users actually say, e.g. 'Use when the user asks to define requirements, clarify scope, or specify what a feature must do'.

List 2-3 concrete actions (e.g. 'capture user vision, fan out requirements analysis across providers, synthesize a requirements checklist') to raise specificity.

Include the natural synonyms 'define requirements' and 'clarify scope' alongside the 'octo define/scope' command tokens.

Dimension	Reasoning	Score
Specificity	Names the domain ('requirements scoping') and the multi-AI/external-provider method, but does not enumerate multiple concrete actions, so it sits at the 'domain + 1-2 actions' anchor rather than the 'several specific actions' anchor.	3 / 5
Completeness	Both 'what' (Multi-AI requirements scoping) and 'when' (priority triggers plus an explicit DO-NOT exclusion list) are present, but the triggers are command-style rather than the natural trigger phrases required for a 5.	4 / 5
Trigger Term Quality	Priority triggers ('octo define', 'octo scope', 'co-define', 'co-scope') are largely command tokens rather than natural user phrasings, and common natural variants like 'clarify the scope' or 'what are the requirements' are missing.	3 / 5
Distinctiveness Conflict Risk	The Multi-AI requirements-scoping niche is clear and the DO-NOT list separates it from sibling workflows, leaving only minor overlap risk with general scoping skills.	4 / 5
	Total	14 / 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 (784 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-define/SKILL.md
Commit: 805d58c

Reviewed: 23 hours 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.