CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-app-store

Agent skill for app-store - invoke with $agent-app-store

60

2.85x
Quality

39%

Does it follow best practices?

Impact

97%

2.85x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-app-store/SKILL.md

The canonical home for this skill is agent-app-store in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 content provides a genuinely actionable MCP toolkit code block, but surrounds it with verbose capability-advertising prose and lacks any validated procedural workflow for its irreversible publish/deploy operations. Structure is sectioned but monolithic with no reference files.

Suggestions

Trim the app-categories, quality-standards, and marketplace-features lists to the essentials, or move them to a separate reference file, to reduce token padding.

Add an explicit sequenced workflow with validation checkpoints for publishing and deploying (e.g., verify security scan passes before publish, confirm deployment succeeded before reporting done).

Split the detailed API/category material into reference files (e.g. REFERENCES.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

DimensionReasoningScore

Conciseness

The body pads ~80 lines with capability-advertisement lists (8 app categories, 6 quality standards, 6 marketplace features) describing concepts Claude already knows, rather than lean instructions.

2 / 5

Actionability

The toolkit code block gives concrete, copy-paste-ready MCP calls (app_search, app_store_publish_app, template_deploy, app_analytics) with realistic params, covering the main operations with only minor placeholder gaps.

4 / 5

Workflow Clarity

The numbered 'marketplace management approach' is a priorities list, not a sequenced procedure, and there are no validation checkpoints for irreversible operations like publishing or deploying; per the destructive/batch cap this stays at 3.

3 / 5

Progressive Disclosure

The document has clear section headers but is a single monolithic file over 50 lines with inlined category/feature/API content that could be split out, and no external reference files exist or are signaled.

3 / 5

Total

12

/

20

Passed

Description

28%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 a thin meta-label that names the app-store domain but gives no concrete capabilities and no use-when trigger, capping completeness low. It relies on an invocation token rather than natural trigger language.

Suggestions

Rewrite the description to state concrete actions, e.g. "Publish, discover, deploy, and analyze apps in the Flow Nexus marketplace".

Add an explicit 'Use when...' trigger clause naming natural user phrases such as publishing an app, browsing the marketplace, or deploying a template.

Replace the "invoke with $agent-app-store" invocation hint with natural keywords users would actually say (marketplace, app store, publish app, deploy template).

DimensionReasoningScore

Specificity

The phrase "Agent skill for app-store" names the domain but lists no concrete actions (publish, discover, deploy, analytics) — it is a meta-label rather than a capability description.

2 / 5

Completeness

The 'what' is vague ("Agent skill for app-store") and there is no 'when' trigger clause — "invoke with" is an invocation instruction, not a use-when condition, matching the vague-what/no-when anchor.

2 / 5

Trigger Term Quality

Only the bare keyword "app-store" appears; "invoke with $agent-app-store" is an invocation hint, not a natural phrase a user would say, and synonyms like marketplace/publish/template are absent.

2 / 5

Distinctiveness Conflict Risk

It names a specific niche (app store / marketplace) with a distinct invocation token, but the generic phrasing could still overlap with other marketplace-related skills.

3 / 5

Total

9

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
Reviewed

Table of Contents

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.