flow-discover

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

Quality

41%

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

45%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 highly actionable with concrete scripts and a well-gated execution contract, but it is severely verbose due to wholesale duplication of the step sequence and banners, and it fails progressive disclosure by inlining everything in a single 834-line file with no bundle references.

Suggestions

Delete the duplicate 'Discover Workflow' section (lines 352-533) that re-states Step 1-4 and the banners already covered by the EXECUTION CONTRACT; keep one canonical step sequence.

Move the security-framing block, banner templates, and example outputs into files under references/ and link to them, reducing SKILL.md to an overview plus the execution contract.

Resolve or remove the {{PREAMBLE}} and {{VISUAL_INDICATORS}} placeholder tokens and the undefined ${codex_status}/${agy_status} banner variables so the embedded templates are executable as written.

Dimension	Reasoning	Score
Conciseness	The 834-line body is severely padded: the step sequence and banner templates are duplicated across the 'EXECUTION CONTRACT' (lines 79-349) and a second 'Discover Workflow' section (lines 352-533), with the context-detection step and Dev/Knowledge banners repeated verbatim multiple times.	1 / 5
Actionability	It provides concrete, copy-paste-ready bash commands and script paths (orchestrate.sh probe-single, build-fleet.sh, state-manager.sh) plus real Agent invocation templates, with only minor gaps from unresolved placeholders like {{PREAMBLE}}, {{VISUAL_INDICATORS}}, and undefined ${codex_status} variables.	4 / 5
Workflow Clarity	The EXECUTION CONTRACT lays out a clear STEP 1-7 sequence with explicit blocking gates and validation (synthesis-file check, min-2-results threshold, error-recovery rules), but the presence of a second conflicting Step 1-4 structure muddies the canonical flow.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the skill is a monolithic 834-line wall that inlines banner templates, security-framing blocks, and lengthy example outputs that clearly belong in separate reference files.	2 / 5
	Total	11 / 20 Passed

Description

37%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 identifies the skill's domain but relies on a single generic action verb and omits any explicit 'Use when' trigger guidance, leaving Claude without clear invocation criteria. Jargon ('Double Diamond Discover phase') further weakens natural trigger matching.

Suggestions

Replace the generic verb 'research' with 2-3 concrete actions (e.g., 'dispatches parallel background agents across external CLI providers, collects their outputs, and synthesizes a cited research report').

Add an explicit 'Use when...' clause with natural trigger phrases users would say (e.g., 'Use when the user asks to research, compare, or explore a topic across multiple AI providers').

Drop or de-emphasize internal jargon like 'Double Diamond Discover phase' in favor of user-facing language, or keep it only as a parenthetical after the natural terms.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Multi-AI research using available external providers') but the only action stated is the generic verb 'research', with no concrete actions enumerated.	2 / 5
Completeness	It states a clear 'what' (multi-AI research across providers) but provides no 'when' / 'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'Multi-AI research' is a passable natural phrase, but 'Double Diamond Discover phase' and 'external providers' are internal jargon rather than terms users would naturally say, and no synonyms or trigger variants are given.	2 / 5
Distinctiveness Conflict Risk	The 'Double Diamond Discover phase' framing carves a niche, but 'Multi-AI research' is broad enough to overlap with other research-oriented skills and lacks distinct trigger phrases to disambiguate.	3 / 5
	Total	10 / 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 (835 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: 1 day 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.