agent-challenges

Agent skill for challenges - invoke with $agent-challenges

1.59x

Quality

—

Does it follow best practices?

Impact

99%

1.59x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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

The body's strongest feature is a concrete, executable MCP toolkit, but it is surrounded by verbose descriptive prose, lacks validation checkpoints in its curation workflow, and is a monolithic file that should split reference material out. A stray second YAML frontmatter block at the top of the body is malformed noise.

Suggestions

Trim the responsibilities, quality standards, and gamification features sections to the non-obvious specifics, removing restatements of concepts Claude already knows.

Add explicit validation checkpoints to the curation workflow, e.g. after challenge_submit, confirm validation status before awarding rUv credits or updating the leaderboard.

Move the challenge-category and gamification-feature reference lists into a separate reference file and link to it from SKILL.md, and remove the stray second YAML frontmatter block from the body.

Dimension	Reasoning	Score
Conciseness	The toolkit code block is lean, but surrounding sections (responsibilities, challenge categories, quality standards, gamification features) restate concepts Claude already knows ('Dynamic Scoring', 'Learning Streaks', 'foster a vibrant learning community') and could be tightened, matching the score-2 anchor 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	The challenges toolkit provides concrete, complete MCP calls with realistic parameters (challenges_list, challenge_submit, achievements_list, leaderboard_get) that are copy-paste ready, matching the score-3 anchor for fully executable examples rather than pseudocode.	3 / 3
Workflow Clarity	The 'challenge curation approach' gives a numbered 6-step sequence, but there are no validation checkpoints or feedback loops (e.g. confirm a submission passed validation before rewarding credits), matching the score-2 anchor 'steps listed but validation gaps; checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	The skill is a single ~80-line file organized into sections with no external bundle references; over the 50-line simple-skill threshold, content that could be split (category and gamification reference lists) is inline, matching the score-2 anchor 'some structure but content that should be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

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 extracted frontmatter description is essentially a placeholder: it names no concrete capabilities, lacks any 'Use when' trigger, and is so generic it would conflict with many skills. Note the SKILL.md is malformed with a second YAML block containing a richer description that is not the parsed frontmatter.

Suggestions

Replace the description with concrete actions, e.g. 'Create and validate Flow Nexus coding challenges, manage leaderboards and achievements, and award rUv credits. Use when the user wants coding challenges, practice problems, or competitive programming.'

Add an explicit 'Use when...' trigger clause listing natural user phrases (coding challenges, practice problems, leaderboards, achievements).

Fix the malformed double frontmatter so the richer description in the second YAML block becomes the single valid frontmatter.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for challenges - invoke with $agent-challenges' names no concrete actions at all, only the vague noun 'challenges', matching the score-1 anchor 'Helps with documents' rather than the score-2 anchor that names a domain and some actions.	1 / 3
Completeness	It states neither what the skill concretely does (only 'challenges') nor when Claude should invoke it; there is no 'Use when...' clause, so per the guideline a missing explicit trigger caps completeness at 2 and the weak 'what' pulls it to 1.	1 / 3
Trigger Term Quality	The only keyword is 'challenges', which is overly generic, and the rest is invocation syntax ('$agent-challenges') rather than natural user language; a user needing this skill would more likely say 'coding challenge' or 'practice problem', so coverage is missing common variations.	1 / 3
Distinctiveness Conflict Risk	'Agent skill for challenges' is extremely generic and would overlap with any coding, testing, or task-oriented skill, matching the score-1 anchor 'Helps with code and documents' rather than a clear niche.	1 / 3
	Total	4 / 12 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/claude-flow
Commit: 03d4f84

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.