agent-challenges

Agent skill for challenges - invoke with $agent-challenges

1.59x

Quality

56%

Does it follow best practices?

Impact

99%

1.59x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-challenges/SKILL.md

Quality

Content

53%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 pairs a genuinely concrete MCP toolkit with a large amount of persona/aspirational padding, and its curation workflow lacks any validation or feedback checkpoints. It is a self-contained single-file skill with decent sectioning, but reads more like a marketing persona prompt than an operational skill.

Suggestions

Cut the 'Quality standards', 'Gamification features', and closing-paragraph padding — keep only operational guidance Claude cannot infer, which would roughly halve the body.

Add validation checkpoints to the curation workflow, e.g. verify submission results and re-check challenge status after challenge_submit, and how to react when validation fails.

Fix the malformed duplicate frontmatter (the stray outer '---' block) so the parsed frontmatter is unambiguous, and consider moving the category and gamification feature lists into a references/ file if the skill grows.

Dimension	Reasoning	Score
Conciseness	The 'Quality standards' section ('Meaningful achievement systems that recognize diverse skills...') and the closing paragraph ('...create inclusive learning environments that support users at all skill levels while maintaining competitive excitement') are pure aspirational padding, and the 'Gamification features' bullets are largely feature marketing — several padded sections, matching anchor 2 rather than 3.	2 / 5
Actionability	The toolkit block provides four concrete MCP calls with typed parameters (challenges_list, challenge_submit, achievements_list, leaderboard_get), which is mostly executable guidance; minor gaps (placeholder IDs, no output handling) keep it below fully copy-paste-ready.	4 / 5
Workflow Clarity	The 'challenge curation approach' gives a numbered 6-step sequence (Skill Assessment through Community Engagement) but includes no validation checkpoints or error-recovery loops around submission grading, matching anchor 3.	3 / 5
Progressive Disclosure	The body is a single well-sectioned file (~75 lines) with no nested or dangling references (no references/, scripts/, or assets/ exist); structure is good and content is appropriately inline at this size, though the category and gamification lists could live in a reference file.	4 / 5
	Total	13 / 20 Passed

Description

58%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 states a clear niche and several concrete capabilities, but it lacks any 'when to use' trigger guidance and has thin natural-language keyword coverage. The file also contains a duplicated, conflicting frontmatter block (an outer 'agent-challenges' wrapper with the vague description 'Agent skill for challenges - invoke with $agent-challenges'), which is itself a defect.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases, e.g. 'Use when the user asks about coding challenges, practice problems, competitions, leaderboards, badges, or achievements'.

Remove the duplicate outer frontmatter block and keep a single, consistent name/description pair so the effective description is unambiguous.

Include user-facing synonyms (katas, practice problems, competitions, badges) alongside 'Flow Nexus' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'challenge creation, solution validation, leaderboards, and achievement systems' — but omits the credit-reward and learning-pathway responsibilities the body claims, so it matches 'several specific actions with minor gaps' rather than the comprehensive anchor.	4 / 5
Completeness	The 'what' is clear (manages challenges, validation, leaderboards, achievements) but there is no 'Use when...' or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords are present ('coding challenges', 'gamification', 'leaderboards') but common user phrasings like 'practice problems', 'badges', or 'competition' are missing, and 'Flow Nexus' is platform jargon rather than a natural trigger term.	3 / 5
Distinctiveness Conflict Risk	The gamification/leaderboard niche and 'within Flow Nexus' scoping make it mostly distinct from generic skills, with only minor overlap risk against general coding-practice or education skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-challenges/SKILL.md
Commit: b14c79e

Reviewed: 3 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.