flow-define

Multi-AI requirements scoping using available external providers (Double Diamond Define phase)

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/flow-define/SKILL.md

Quality

Content

62%

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

The body is exceptionally actionable and well-sequenced with strong validation gates and error handling, but it is severely over-long and repetitive, with the same banners and steps restated multiple times and no progressive disclosure to offload the bulk into reference files.

Suggestions

Collapse the three repeated banner definitions and the duplicated step lists (EXECUTION CONTRACT vs Implementation Instructions) into a single canonical block; remove marketing/emoji padding to cut tokens substantially.

Move the full auth-system worked example and the banner templates into separate reference files (e.g. references/example-output.md, references/banners.md) and link to them one level deep, turning SKILL.md into a lean overview.

Resolve or remove the unresolved {{PREAMBLE}} / {{VISUAL_INDICATORS}} placeholders and the missing skills/blocks/codex-host-adapter.md reference so all cited paths point to real files.

Dimension	Reasoning	Score
Conciseness	The ~716-line body is highly padded: the activation banner is repeated in STEP 1, the 'Visual Indicators Protocol' section, and the 'Visual Indicators' section; the EXECUTION CONTRACT and later 'Implementation Instructions' restate the same steps; and marketing/emoji content ('🐙 CLAUDE OCTOPUS ACTIVATED') inflates the token budget, matching the 'verbose; padded with unnecessary context' anchor.	1 / 3
Actionability	It supplies concrete, copy-paste-ready bash commands with explicit script paths, a fully specified AskUserQuestion block with options, and a validation snippet that checks for the synthesis file and exits on failure — concrete executable guidance rather than vague direction; a few template fields ([Brief description...], $USER_REQUEST) and reliance on external scripts reduce real copy-paste reliability slightly.	3 / 3
Workflow Clarity	The seven numbered STEPs are explicitly sequenced with mandatory blocking gates ('DO NOT PROCEED TO STEP N until ...'), a dedicated validation gate (STEP 5 verifies the synthesis file and exits 1 on failure), and an error-handling section with recovery guidance, satisfying the 'clear sequence with explicit validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~716-line monolith; it has clear section organization but keeps large inline content (a full worked example, repeated banner templates) that should be split out, and it references un-provided includes ({{PREAMBLE}}, {{VISUAL_INDICATORS}}, skills/blocks/codex-host-adapter.md), placing it at 'some structure but could be better organized; references not clearly signaled'.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 correctly uses third person and names a clear domain, but it reads as a method-and-phase label rather than a trigger-rich skill description: it lacks a 'Use when...' clause, leans on jargon ('Double Diamond Define phase', 'Multi-AI'), and does not enumerate multiple concrete actions.

Suggestions

Add an explicit 'Use when ...' trigger clause naming natural user phrasings (e.g. 'Use when defining or scoping requirements, clarifying what a feature must do, or identifying constraints and edge cases').

Replace jargon-laden phrasing with concrete actions a user would recognize, e.g. 'Scopes requirements by debating them across multiple AI providers: defines must-have/should-have needs, technical constraints, edge cases, and out-of-scope items.'

Add common trigger keywords ('define requirements', 'scope', 'clarify requirements', 'constraints', 'edge cases') to improve distinctiveness and trigger match quality.

Dimension	Reasoning	Score
Specificity	Names the domain ('requirements scoping') and a method ('Multi-AI ... using available external providers') but lists only the single action 'scoping' rather than multiple concrete actions (e.g. define requirements, identify constraints, analyze edge cases), so it does not reach the 'lists multiple specific concrete actions' anchor.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing when-clause caps completeness at 2.	2 / 3
Trigger Term Quality	'requirements scoping' is a somewhat natural term, but 'Multi-AI', 'external providers', and 'Double Diamond Define phase' are technical jargon; common user phrasings like 'define requirements', 'scope a feature', or 'clarify what to build' are missing, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The 'Double Diamond Define phase' niche gives it some specificity, but the core 'requirements scoping' framing could overlap with other planning/requirements skills and the jargony triggers are not sharply distinct, so it sits at 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 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 (717 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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