CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-challenges

Agent skill for challenges - invoke with $agent-challenges

67

1.59x
Quality

48%

Does it follow best practices?

Impact

99%

1.59x

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-challenges/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

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

The content is actionable thanks to concrete MCP tool-call examples, but it is held back by verbose descriptive catalogs and a workflow that lacks validation checkpoints. Splitting reference material out and tightening the catalogs would improve it.

Suggestions

Add explicit validation/feedback steps to the workflow, e.g. verify a submission passed before awarding rUv credits or unlocking achievements, with a retry path on failure.

Trim the challenge-category, gamification-feature, and quality-standards catalogs to the non-obvious specifics Claude wouldn't already infer.

Move the detailed category and gamification references into separate files (e.g. CATEGORIES.md, GAMIFICATION.md) and link them from the overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids basic-concept padding, but the cataloged lists of challenge categories, gamification features, and quality standards largely restate knowledge Claude already has and could be tightened.

2 / 3

Actionability

The toolkit provides concrete, copy-paste-ready MCP tool calls (challenges_list, challenge_submit, achievements_list, leaderboard_get) with parameter examples that are directly executable.

3 / 3

Workflow Clarity

The six-step curation approach is clearly sequenced, but there are no validation checkpoints or feedback loops for batch/reward operations like leaderboard updates and achievement awards, capping the score at 2.

2 / 3

Progressive Disclosure

The body is well-sectioned with clear headers, but at ~75 lines with no bundle files or referenced materials it keeps inline content (full category and feature catalogs) that could be split into separate reference files.

2 / 3

Total

9

/

12

Passed

Description

32%Weight 40%Scale 1-3

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 too vague to effectively trigger or distinguish the skill: it names no concrete actions and provides no 'when to use' guidance. It should state what the skill does and the natural situations that call for it.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Creates and validates coding challenges, manages leaderboards, and awards achievement badges within Flow Nexus'.

Add an explicit 'Use when...' clause with natural trigger terms like 'coding challenges', 'leaderboard', 'submit solution', or 'achievement badges'.

Replace the '$agent-challenges' invocation token with user-facing language that conveys the skill's distinct niche.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for challenges' names a domain but lists no concrete actions (no 'creates', 'validates', or 'manages'), and 'invoke with $agent-challenges' is invocation syntax rather than a capability, matching the vague-language anchor.

1 / 3

Completeness

It states a domain ('Agent skill for challenges') but has no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 2; the 'what' is also weak.

2 / 3

Trigger Term Quality

'challenges' is a relevant natural keyword, but the description leans on the literal token '$agent-challenges' and omits common variations users would say ('coding challenges', 'leaderboard', 'submit solution').

2 / 3

Distinctiveness Conflict Risk

'Agent skill for challenges' is very generic and does not convey the actual niche (Flow Nexus gamified coding challenges), so it could conflict with many skills.

1 / 3

Total

6

/

12

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/claude-flow
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.