flow-develop

Multi-AI implementation using available external providers (Double Diamond Develop phase). DO NOT use for simple code edits, reading/reviewing code, built-in commands, or trivial single-file changes.

Quality

52%

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-develop/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 is rich in concrete, executable workflow guidance with strong validation gates and checklists, but it is severely over-long and self-duplicating, with conflicting step numbering that undermines an otherwise clear sequence. Progressive disclosure is undercut by inlining content that should live in separate reference files.

Suggestions

De-duplicate the body: keep a single canonical EXECUTION CONTRACT and remove the repeated context-detection block and the four near-identical banner copies, consolidating into one banner template.

Move the long worked examples (authentication system, API endpoint), the dev-subtype supplement table, and the banner templates into separate reference files linked one level deep from a leaner overview.

Reconcile the two conflicting step-numbering schemes into one sequence so the validation checkpoints are unambiguous.

Dimension	Reasoning	Score
Conciseness	The ~800-line body duplicates entire blocks — the context-detection step appears twice (EXECUTION CONTRACT Step 1 and the later 'Develop Workflow' Step 1) and the provider banner is shown four times with conflicting content — matching 'Noticeably verbose; several unnecessary explanations or padded sections'; not 1 because genuine actionable content is present underneath the padding, and not 3 because the duplication is pervasive rather than occasional.	2 / 5
Actionability	It provides concrete executable commands (orchestrate.sh, state-manager.sh, octo-state.sh, check-providers.sh, the BM25 search.py invocation, git tag checkpoint) matching 'Mostly executable guidance; concrete code or commands with minor gaps'; not 5 because several commands use unresolved placeholders like '${codex_status}', '${agy_status}', and '<user\'s implementation request>'.	4 / 5
Workflow Clarity	The EXECUTION CONTRACT defines a clearly sequenced 7-step mandatory flow with explicit validation gates (Step 5 synthesis verification), blocking checkpoints, per-step error handling, and before/after checklists, fitting 'Clear sequence with most checkpoints present; minor validation gaps'; not 5 because the duplicated, conflicting step numbering (two parallel 'Step 1/2/3' sequences) muddies the canonical sequence.	4 / 5
Progressive Disclosure	Template placeholders ({{PREAMBLE}}, {{VISUAL_INDICATORS}}, {{QUALITY_GATES}}) and references to external plugin scripts provide some deferred content, but the SKILL.md itself is an 800-line monolith with duplicated banners and long examples inlined that belong in separate files, matching 'Some structure ... content that should be separate is inline'; not 4 because the inlining is substantial and navigation to detail is not cleanly one-level.	3 / 5
	Total	13 / 20 Passed

Description

48%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 cleanly states what the skill does and carves out a distinct multi-AI niche, but it lacks a positive 'Use when...' trigger clause and natural user-facing action phrases, relying on negative exclusions to imply scope. Specificity is held back by generic action language.

Suggestions

Add an explicit positive trigger clause, e.g. 'Use when the user asks to build, implement, develop, or create a feature requiring multi-provider analysis.'

Replace the generic word 'implementation' with a few concrete actions (e.g. 'generates parallel implementation approaches from multiple AI providers and synthesizes them').

Include natural user trigger phrases like 'build', 'implement', 'develop a feature' so the description matches what users actually say.

Dimension	Reasoning	Score
Specificity	The phrase 'Multi-AI implementation using available external providers' names the domain but the action ('implementation') is generic with no enumerated concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because it lists no specific concrete actions, and stays above 1 because the domain is clearly named.	2 / 5
Completeness	The 'what' is clear ('Multi-AI implementation using available external providers (Double Diamond Develop phase)') but there is no positive 'Use when...' clause — only a negative 'DO NOT use for...' exclusion, so per the judging guideline a missing explicit trigger clause caps completeness at 3; it is not 4 because the 'when' is only weakly implied via exclusion rather than stated.	3 / 5
Trigger Term Quality	It contains relevant keywords like 'implementation', 'code edits', 'reviewing code', and 'built-in commands', but it omits the natural action phrases a user would actually say ('build X', 'implement a feature', 'develop'), fitting 'Some relevant keywords but missing common variations or synonyms'; not 2 because it has more than one or two generic keywords, and not 4 because the core natural trigger phrases are absent.	3 / 5
Distinctiveness Conflict Risk	The qualifiers 'Multi-AI', 'available external providers', and 'Double Diamond Develop phase' give it a clear niche mostly distinct from ordinary coding skills, matching 'Mostly distinct; minor overlap risk with closely related skills'; not 5 because 'implementation' is still broad enough to risk overlap with general implementation skills.	4 / 5
	Total	12 / 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 (843 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-develop/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.