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 ./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 Execution Contract itself is exemplary — enforced step ordering, cost transparency, and validation gates — but the surrounding ~400 lines duplicate it nearly verbatim while mixing 'grasp' and 'define' terminology. The skill would be dramatically stronger at roughly half its length with a single canonical workflow description.

Suggestions

Collapse the three restatements of the workflow (Execution Contract, 'How It Works' Stages A-D, 'Implementation Instructions') into one canonical sequence; the duplicated sections account for hundreds of lines of pure repetition.

Move the two full worked examples and the banner/problem-definition templates into references/ files and link to them one level deep, keeping SKILL.md as an overview.

Standardize terminology — pick 'define' or 'grasp' consistently, fix the duplicated Antigravity entry in 'What This Workflow Does', and align file naming (grasp-synthesis-*.md) with the chosen term.

Dimension	Reasoning	Score
Conciseness	The 7-step workflow is stated three times (Execution Contract, 'How It Works' Stages A-D, and 'Implementation Instructions'), the banner template appears twice, and the entire second half of the file restates the first half — heavy padding, though it does not explain concepts Claude already knows. This is 'noticeably verbose with several unnecessary padded sections' rather than the concept-explaining severity of anchor 1.	2 / 5
Actionability	Provides concrete, near-executable bash throughout: 'octo-state.sh update_state --phase 2 --position "Definition"', the check-providers.sh status-filtering pipeline, 'find ~/.claude-octopus/results -name "grasp-synthesis-*.md" -mmin -10' verification, and a full output template. Minor gaps — placeholder assignments like 'user_flow="[Answer from question 1]"' and '{{PREAMBLE}}' — keep it just short of copy-paste ready.	4 / 5
Workflow Clarity	Clear numbered sequence with explicit blocking gates ('DO NOT PROCEED TO STEP 2 until banner displayed'), a dedicated verification step (Step 5 synthesis check), and an error-handling section with recovery guidance. Falls short of anchor 5 due to naming incoherence — 'grasp' and 'define' are used interchangeably and 'What This Workflow Does' lists Antigravity CLI twice with different icons and roles.	4 / 5
Progressive Disclosure	The body has good section headers but inlines large content that belongs in separate files (two full worked examples, banner templates, the problem-definition output format) with no bundle files of its own. References to skills/blocks/*.md point to plugin-installed files outside this skill, so navigation relies on the plugin layout rather than a well-signaled one-level-deep reference 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 answers both what and when with an unusually good explicit exclusion clause, but its capabilities are stated abstractly and its triggers are command tokens rather than natural user phrasing. It sits comfortably at 'solid but improvable' rather than exemplary.

Suggestions

List the concrete outputs in the description, e.g. 'Multi-AI requirements scoping that synthesizes core requirements, technical constraints, edge cases, and out-of-scope items from external providers'.

Add natural trigger phrases users would actually say — 'define requirements', 'clarify scope', 'what is the scope of X' — alongside the command tokens.

Briefly name the deliverable (a problem-definition document with a requirements checklist) so the 'what' is concrete rather than mechanism-only.

Dimension	Reasoning	Score
Specificity	Names the domain ('requirements scoping') and the mechanism ('multi-AI... external providers') but stops short of listing concrete deliverables such as problem definitions, requirement checklists, or edge-case analysis. It names one core action rather than the several specific actions required for a 4.	3 / 5
Completeness	Both parts are present: 'what' ('Multi-AI requirements scoping using available external providers') and an explicit trigger clause ('Priority triggers: octo define, octo scope...'), plus negative guidance. Not a 5 because the 'when' relies on command names rather than concrete natural-language trigger phrases.	4 / 5
Trigger Term Quality	'octo define, octo scope, co-define, co-scope' are command tokens; 'define' and 'scope' are words users would naturally say, but common phrasings like 'define requirements', 'clarify scope', or 'problem definition' are absent. Some relevant keywords with missing synonyms fits anchor 3.	3 / 5
Distinctiveness Conflict Risk	The explicit exclusion list ('DO NOT use for implementation, research, review/validation, or built-in commands') and phase-specific niche (Double Diamond Define) make it mostly distinct. Not a 5 because it can still overlap with sibling flow-* skills in the same plugin that also mention scoping or requirements.	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 (739 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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