bond
Assesses team fitness and composes agent teams. Use when "set up a team", "team for this", "should I use agents", "design a team", "how many agents", "agent team".
93
91%
Does it follow best practices?
Impact
94%
1.74xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 has strong trigger term coverage and completeness with an explicit 'Use when' clause containing multiple natural phrases. Its main weakness is the somewhat vague capability description — 'assesses team fitness' and 'composes agent teams' could be more specific about what concrete actions are performed (e.g., recommending team size, assigning agent roles, evaluating task suitability).
Suggestions
Expand the capability description with more concrete actions, e.g., 'Evaluates task requirements, recommends team size, assigns agent roles, and configures agent team compositions' instead of the current abstract phrasing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names two actions ('assesses team fitness' and 'composes agent teams') but these are somewhat vague — 'assesses team fitness' is abstract and 'composes agent teams' lacks detail about what composing entails (e.g., selecting roles, configuring capabilities, sizing teams). | 2 / 3 |
Completeness | The description clearly answers both 'what' (assesses team fitness and composes agent teams) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Both components are present and explicit. | 3 / 3 |
Trigger Term Quality | The description includes a good range of natural trigger phrases users would actually say: 'set up a team', 'team for this', 'should I use agents', 'design a team', 'how many agents', 'agent team'. These cover multiple natural phrasings well. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on agent team composition and fitness assessment is a clear niche. The trigger terms are specific to team design/setup in an agent context, making it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent workflow design, strong actionability, and efficient token usage. The six-step workflow with clear decision gates, feedback loops for coupling resolution, and user approval checkpoints is well-crafted. The only minor weakness is that all content lives in a single file, though the skill's length and complexity are borderline for needing external references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient throughout. It assumes Claude's competence, avoids explaining what agents are or how parallelism works, and every section delivers actionable instruction without padding. No unnecessary context or concept explanations. | 3 / 3 |
Actionability | The skill provides highly specific, concrete guidance at every step: exact criteria for fitness assessment (8+ story points, file independence), exact presentation format (Minto pyramid, AskUserQuestion options with labels/descriptions/detail panels), model selection rules (Opus/Sonnet/Haiku by role type), and coupling check methodology. The detail panel template in Step 5 is copy-paste ready. | 3 / 3 |
Workflow Clarity | Six clearly sequenced steps with explicit decision points and branching logic (solo exits at Step 2, coupling handling in Step 4, plan mode vs execution in Step 6). Validation is built in via the coupling check in Step 3, user approval gates at Steps 2 and 5, and the merge/coordinate/redesign feedback loop in Step 4. The workflow handles error recovery through redesign boundaries and role adjustment options. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical flow, but it's entirely self-contained in one file. For a skill of this complexity (~100 lines, 6 steps with branching), some content like the detail panel templates or the coupling resolution patterns could be split into reference files. However, the inline organization is good enough that this is a minor issue. | 2 / 3 |
Total | 11 / 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
- saadshahd/moo.md
- Commit
e876ef5
- 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.