flow-discover

Multi-AI research using available external providers (Double Diamond Discover phase)

Quality

42%

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-discover/SKILL.md

Quality

Content

35%

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

The skill's enforced execution contract is concrete and well-checkpointed, but the body is severely bloated and self-contradictory, with a duplicate workflow section, repeated banners, and unresolved template placeholders that hurt token efficiency, clarity, and organization.

Suggestions

Delete the redundant '# Discover Workflow - Discovery Phase' / 'How It Works' Steps 1-4 section that duplicates and contradicts the EXECUTION CONTRACT; keep a single authoritative sequence.

Remove the repeated banners and duplicated context-detection indicator lists, and externalize the large Dev/Knowledge presentation report templates into a reference file or drop them.

Resolve or remove the {{PREAMBLE}} and {{VISUAL_INDICATORS}} template placeholders so the rendered SKILL.md is self-contained and unambiguous.

Dimension	Reasoning	Score
Conciseness	The ~820-line body is padded with redundancy: the EXECUTION CONTRACT Steps 1-7 are repeated as a separate 'How It Works' Steps 1-4 with contradictory content, banners appear 3+ times, and the context-detection indicator lists are duplicated verbatim.	1 / 3
Actionability	Provides concrete, executable bash commands and an explicit Agent-tool invocation template, but mixes in non-executable presentation templates with unfilled placeholders and contradicts itself on whether orchestrate.sh or Claude performs synthesis.	2 / 3
Workflow Clarity	The contract has explicit blocking checkpoints and validation gates (minimum-2-results, synthesis-file existence check with exit 1), but the duplicate contradictory 'How It Works' sequence undermines clarity about the authoritative workflow.	2 / 3
Progressive Disclosure	The body is sectioned with headers, but it is a monolithic ~820 lines with large inline report templates, repeated banners, and unresolved template placeholders ({{PREAMBLE}}, {{VISUAL_INDICATORS}}) that should be split or removed.	2 / 3
	Total	7 / 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 is in third person and names a clear domain, but it is single-action, jargon-heavy, and lacks an explicit 'Use when' trigger clause, leaving it at the midpoint across all dimensions.

Suggestions

Add an explicit 'Use when' clause naming natural triggers, e.g. 'Use when the user wants multi-source research, exploration, or comparing approaches across AI providers.'

List concrete actions the skill performs (e.g. 'dispatch parallel provider probes, synthesize perspectives into a ranked findings report') to lift specificity.

Replace plugin jargon ('Double Diamond Discover phase') with user-facing terms like 'exploratory research' to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and action ('Multi-AI research using available external providers') but lists only one action with a parenthetical phase label rather than multiple specific concrete actions.	2 / 3
Completeness	States what the skill does but provides no 'Use when...' clause or explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Includes the natural term 'research' but pads it with plugin/process jargon ('Multi-AI', 'external providers', 'Double Diamond Discover phase') users would not say, and misses common variations like 'explore' or 'investigate'.	2 / 3
Distinctiveness Conflict Risk	The Double Diamond Discover framing gives it a niche, but the bare word 'research' could still overlap with other research skills and no distinct trigger is given.	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 (825 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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