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

78%

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

72%

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

The body is concise and well-organized for a simple orchestration skill, but its workflow lacks executable dispatch detail and validation checkpoints, leaving actionability and workflow clarity at the mid level.

Suggestions

Add a concrete AgentFleet dispatch example (e.g., a minimal @Coordinator/@Fleet call showing how to invoke the Research, Strategy, Finance, and Writer agents) so the guidance is executable rather than directional.

Insert explicit validation checkpoints in the workflow, such as confirming each agent returned data before synthesis and a retry/flag step when research is incomplete or cached.

Specify how Strategy and Finance outputs are merged into the GO/NO-GO briefing, including where the quantitative Finance data must appear in the final report.

Dimension	Reasoning	Score
Conciseness	The ~28-line body stays lean, names the A2A/AgentFleet specifics it needs without padding, and assumes Claude's competence rather than explaining generic concepts, matching the lean-and-efficient anchor; not 2 because there is no unnecessary explanation or fluff to trim.	3 / 3
Actionability	Steps name agents and order ("Dispatch research to the Research Agent", "Run Strategy and Finance agents in parallel") but never show the actual AgentFleet dispatch mechanism or any executable call, so key operational details are missing per the incomplete-guidance anchor; not 3 because there is no copy-paste-ready invocation, not 1 because the guidance is concrete at the task level rather than purely descriptive.	2 / 3
Workflow Clarity	A clear numbered sequence with a parallel step is present, but there are no explicit validation checkpoints or feedback loops for confirming agent outputs or handling incomplete data, matching the anchor for listed steps with missing checkpoints; not 3 because validation is only implicitly touched in Guardrails, not 1 because the sequence is explicit.	2 / 3
Progressive Disclosure	The body is under 50 lines with no external references needed and is cleanly sectioned into Skills and Guardrails, matching the scoring-note allowance for simple skills to score 3 on well-organized sections; not 2 because there is no monolithic wall or misplaced inline content.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 third-person, clearly distinguishing the skill's niche while covering both capability and trigger. Its main weakness is a single, somewhat generic trigger phrase that limits keyword coverage a user would naturally say.

Dimension	Reasoning	Score
Specificity	"dispatches research, strategy, finance, and writer specialists" and "synthesizes their findings into a GO/NO-GO investment briefing" list multiple concrete actions, matching the anchor for listing several specific actions; not 2 because it goes beyond naming just a domain and a couple actions.	3 / 3
Completeness	It explicitly states both what it does (dispatch and synthesize specialists into a briefing) and when to use it ("Use for multi-agent advisory workflows"), satisfying the anchor requiring both an explicit what and an explicit trigger; not 2 because a 'Use for...' trigger clause is present rather than missing or merely implied.	3 / 3
Trigger Term Quality	The single trigger phrase "multi-agent advisory workflows" plus jargon like "A2A" covers only one relevant path and misses common user variations, matching the anchor for some keywords but missing common alternatives; not 3 because coverage is narrow and leans technical, not 1 because it does carry a usable keyword.	2 / 3
Distinctiveness Conflict Risk	"GO/NO-GO investment briefing" and "multi-agent advisory workflows" carve a clear startup-advisory orchestration niche with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor; not 2 because it is more specific than a generic 'works with X' formulation.	3 / 3
	Total	11 / 12 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: 86693b6

Reviewed: about 1 hour 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.