startup-ceo

CEO coordinator that dispatches research, strategy, finance, and writer specialists via A2A and synthesizes their findings into a GO/NO-GO investment briefing. Use for multi-agent advisory workflows.

Quality

66%

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 ./modules/skills/src/main/resources/META-INF/skills/startup-ceo/SKILL.md

Quality

Content

65%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 well-organized and concise for a small orchestration skill, but its workflow lacks integrated validation checkpoints and it gives no executable examples of the A2A/AgentFleet API it relies on. Tightening the redundant Skills section and adding a concrete dispatch example would raise the weakest dimensions.

Suggestions

Add one executable example showing how to dispatch via the AgentFleet API (e.g. a minimal code or command block) so the guidance is copy-paste ready.

Fold the relevant Guardrails into the Workflow as explicit validation checkpoints (e.g. 'After research returns, flag incomplete/cached data before proceeding to Strategy and Finance').

Merge or trim the 'Skills' section, which largely restates the Workflow, to remove redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and mostly efficient, but the 'Skills' section restates capabilities already implied by the Workflow, and 'A2A (Agent-to-Agent)' is mild over-explanation; not a 5 because of this minor redundancy.	4 / 5
Actionability	It names concrete components (@Coordinator, @Fleet annotations, AgentFleet API, Agent Card) and a sequenced dispatch plan, but provides no executable code or command examples showing how to actually invoke the API; matches the 'concrete guidance but incomplete' anchor 3.	3 / 5
Workflow Clarity	The four-step Workflow is clearly sequenced, but this is a batch/parallel multi-agent dispatch with validation only present implicitly in the separate Guardrails section ('Flag when research data is incomplete or cached'), not integrated as explicit checkpoints in the workflow, so the missing-checkpoints cap applies.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and no bundle files present; it is organized into clear intro, Workflow, Skills, and Guardrails sections, satisfying the simple-skill exception for anchor 5.	5 / 5
	Total	15 / 20 Passed

Description

67%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 specific and clearly conveys both capability and a use-when trigger, with a distinct niche. It would benefit from broader natural trigger phrasing and synonyms rather than leaning on internal jargon like A2A.

Suggestions

Add natural trigger synonyms a user might actually say, e.g. 'Use for multi-agent advisory workflows, investment due diligence, or startup evaluation.'

Reduce reliance on product-internal jargon (A2A, AgentFleet) in the description or pair each with a plain-language term.

Expand the 'when' clause to name a couple of concrete triggering scenarios rather than a single category.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('dispatches research, strategy, finance, and writer specialists', 'synthesizes their findings into a GO/NO-GO investment briefing'); falls short of the anchor-5 example only because the action set is specialized rather than broadly comprehensive.	4 / 5
Completeness	Both 'what' (dispatch specialists via A2A and synthesize into a GO/NO-GO briefing) and 'when' ('Use for multi-agent advisory workflows') are explicit; the 'when' is a single short clause that could name more concrete trigger scenarios, matching anchor 4 rather than 5.	4 / 5
Trigger Term Quality	The natural phrase 'Use for multi-agent advisory workflows' is present, but coverage is jargon-heavy (A2A, GO/NO-GO) and misses common synonyms like 'investment decision', 'due diligence', or 'startup evaluation'; not a 4 because several natural terms are absent.	3 / 5
Distinctiveness Conflict Risk	The startup advisory / multi-agent orchestration niche is clearly distinct with specific triggers, but 'multi-agent advisory workflows' could overlap with other general orchestration skills, so it is mostly distinct rather than minimal-conflict anchor 5.	4 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Atmosphere/atmosphere
Path: modules/skills/src/main/resources/META-INF/skills/startup-ceo/SKILL.md
Commit: b600b8a

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.