agent-challenges
Agent skill for challenges - invoke with $agent-challenges
40
7%
Does it follow best practices?
Impact
99%
1.59xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-challenges/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no concrete actions, no trigger guidance, and no specificity about what domain or task it covers. The word 'challenges' is too vague to enable Claude to make an informed selection among multiple skills.
Suggestions
Specify what the skill actually does by listing concrete actions (e.g., 'Solves coding challenges, generates test cases, and explains algorithmic solutions').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks about coding puzzles, competitive programming, algorithm challenges, or LeetCode-style problems').
Clarify the domain to reduce conflict risk — define what type of 'challenges' this skill handles to distinguish it from other potentially overlapping skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for challenges' is extremely vague — it doesn't describe what the skill does, what kind of challenges, or what actions it performs. | 1 / 3 |
Completeness | Neither the 'what' nor the 'when' is meaningfully addressed. There is no explanation of what the skill does or when Claude should select it. | 1 / 3 |
Trigger Term Quality | The only keyword is 'challenges,' which is overly generic and not a natural term users would use. The invocation command '$agent-challenges' is technical syntax, not a natural trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | 'Challenges' is extremely broad and could overlap with any number of skills — coding challenges, math challenges, trivia, debugging, etc. There is nothing to distinguish this skill from others. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a product description or persona prompt than an actionable skill file. While it includes some useful MCP tool call examples, the majority of the content is verbose descriptions of concepts, categories, and features that don't teach Claude how to do anything specific. The skill would benefit enormously from being stripped down to concrete tool usage workflows with validation steps.
Suggestions
Remove the extensive category lists, quality standards, and gamification feature descriptions — these are descriptive padding that don't help Claude execute tasks. Focus on the 4 MCP tool calls and when/how to use each one.
Add concrete workflows with validation: e.g., 'When a user submits a solution: 1. Call challenge_submit, 2. Check response for errors, 3. If passed, call achievements_list to check for new unlocks, 4. Report results with specific feedback format.'
Replace vague steps like 'Evaluate user's current skill level' with concrete instructions: e.g., 'Call challenges_list with the user's last completed difficulty level to find appropriate next challenges.'
Either create bundle reference files for detailed category/feature information or remove those sections entirely to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already knows (what gamification is, what algorithms are, what challenge categories exist). The quality standards, gamification features, and challenge categories sections are padded descriptions that don't provide actionable guidance. Much of this reads like a product marketing document rather than a skill instruction. | 1 / 3 |
Actionability | The MCP tool calls provide some concrete, executable guidance with specific function signatures and parameters. However, the tool calls use placeholder values without explaining when/how to use them in practice, and the rest of the skill is abstract descriptions ('Evaluate user's current skill level') rather than concrete instructions. | 2 / 3 |
Workflow Clarity | The 'challenge curation approach' lists steps but they are vague and abstract (e.g., 'Evaluate user's current skill level and learning objectives') with no concrete sequence, validation checkpoints, or error handling. There's no clear workflow for how to actually process a challenge submission end-to-end. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no clear separation of overview vs. detailed content. All categories, features, and standards are inlined despite being lengthy lists that could be organized into separate reference files. | 1 / 3 |
Total | 5 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/claude-flow
- Commit
d29d87f
- 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.