flow-deliver

Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)

Quality

53%

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-deliver/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 is highly actionable with concrete commands and a well-checkpointed execution contract, but it is severely over-long due to repeated sections, conflicting step-numbering schemes, and an inlined full sample report. No bundle files exist, yet the body relies on unsignaled template placeholders.

Suggestions

De-duplicate the body: keep a single canonical EXECUTION CONTRACT and remove the repeated context-detection, banner, and orchestrate.sh sections under "MANDATORY: Context Detection & Visual Indicators" and "How It Works".

Move the full ~130-line sample validation report (Example 1) into a separate referenced file (e.g. references/example-report.md) and keep only a short pointer inline, resolving the progressive-disclosure gap.

Reconcile the multiple step-numbering schemes (EXECUTION CONTRACT 1-7, How It Works 1-5, Implementation Instructions 1-5) into one numbering, and either supply or remove the {{PREAMBLE}}/{{VISUAL_INDICATORS}}/{{QUALITY_GATES}} template placeholders.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose and heavily padded: the context-detection Step 1, the provider banner, and the orchestrate.sh call each appear multiple times under different headings, and a ~130-line full sample validation report is inlined, fitting the anchor for several unnecessary padded sections.	2 / 5
Actionability	It provides concrete, copy-pasteable bash commands (orchestrate.sh, state-manager.sh, check-providers.sh, gh pr comment) with real paths, matching the anchor for mostly-executable guidance with only minor gaps like [Brief description] placeholders.	4 / 5
Workflow Clarity	There is a clear 7-step EXECUTION CONTRACT with explicit "DO NOT PROCEED TO STEP N" checkpoints and a validation gate in Step 5, matching the anchor for a clear sequence with most checkpoints present, though redundant re-numbered step schemes add minor confusion.	4 / 5
Progressive Disclosure	Section headers give some structure, but content that belongs in separate files (the full example report, repeated banner variants, the subtype table) is inlined in a ~870-line monolith, and {{PREAMBLE}}/{{VISUAL_INDICATORS}}/{{QUALITY_GATES}} placeholders reference template includes that are not present in the bundle, matching the some-structure-but-inline anchor.	3 / 5
	Total	13 / 20 Passed

Description

50%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 a clear third-person statement of what the skill does, but it lacks any explicit "Use when..." trigger guidance and relies on fairly generic verbs and plugin-specific jargon. It is distinguishable but not strongly differentiated from general review skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to validate, score, or review code or documents before shipping, or mentions a deliver-phase review."

Include concrete natural terms users would say, such as "code review", "security audit", "pre-deployment check", and "document review", rather than only "validation, scoring, and review".

Tighten the niche by naming the multi-provider mechanism concretely (e.g. "runs Codex and Antigravity alongside Claude") to reduce overlap with single-model review skills.

Dimension	Reasoning	Score
Specificity	"Multi-AI validation, scoring, and review" names the domain and three actions, but the actions are generic high-level verbs rather than concrete granular capabilities, fitting the anchor that lists domain plus a few non-comprehensive actions.	3 / 5
Completeness	It states a clear "what" (multi-AI validation/scoring/review) but has no "Use when..." clause or equivalent trigger guidance, so per the missing-trigger cap it cannot exceed 3 even though the what is reasonably clear.	3 / 5
Trigger Term Quality	"validation, scoring, and review" are relevant natural keywords, but common user phrasings like "code review" and synonyms/file cues are missing, and "Double Diamond Deliver phase" is jargon, matching the anchor with some keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	"Multi-AI validation... using available external providers (Double Diamond Deliver phase)" is somewhat specific, but "validation, scoring, and review" is broad and could overlap with generic review skills, matching the somewhat-specific-but-overlapable anchor.	3 / 5
	Total	12 / 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 (876 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/flow-deliver/SKILL.md
Commit: 805d58c

Reviewed: 24 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.