team-lead-reference
Provides model routing rules, validates delegation prerequisites, supplies cost tracking templates, and defines dead-letter queue formats for Team Lead orchestration. Load when assigning tasks to agents, choosing model tiers, starting a delegation session, running a multi-agent workflow, delegating work, choosing which model to use, or assigning tasks.
77
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is a strong skill description that clearly articulates specific capabilities (model routing, delegation validation, cost tracking, dead-letter queues) and provides explicit trigger guidance via a comprehensive 'Load when...' clause. The description is well-targeted to a distinct orchestration/delegation domain with good natural language trigger terms. It uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'model routing rules', 'validates delegation prerequisites', 'supplies cost tracking templates', and 'defines dead-letter queue formats'. These are distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (model routing rules, delegation prerequisites, cost tracking templates, dead-letter queue formats) and 'when' with an explicit 'Load when...' clause listing seven specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'assigning tasks to agents', 'choosing model tiers', 'delegation session', 'multi-agent workflow', 'delegating work', 'choosing which model to use'. Good coverage of both technical and natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Targets a very specific niche: Team Lead orchestration with model routing, delegation, and multi-agent workflows. The combination of agent delegation, model tier selection, and dead-letter queues creates a distinct identity unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 well-crafted orchestration reference skill that efficiently packs a complex multi-agent delegation workflow into scannable tables and concise instructions. Its strengths are exceptional conciseness (heavy use of tables), strong actionability (concrete JSON template, specific checklists, scoring rubrics), and clear workflow sequencing with validation checkpoints. The main weakness is that progressive disclosure could be improved—some detailed sections (DLQ format, Dispute Protocol) might benefit from being in separate referenced files, and the referenced bundle files aren't available to verify.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is dense and efficient, using tables extensively to compress information. It assumes Claude's competence throughout—no explanations of basic concepts, no filler. Every section delivers actionable reference material without padding. | 3 / 3 |
Actionability | Provides concrete artifacts: a JSON delegation envelope template, specific checklists with numbered items, exact file paths for logging, precise scoring criteria with examples, and clear routing rules. The guidance is specific enough to execute immediately. | 3 / 3 |
Workflow Clarity | The delegation sequence is clearly numbered 1-7 with explicit steps. Validation checkpoints are built in (pre-delegation 5-point checklist, status handling table with specific actions per outcome, DLQ for failures). The Deepen-Plan Protocol includes a before/after table showing expected transformation, and error recovery paths are defined. | 3 / 3 |
Progressive Disclosure | References to external files like agent-registry.md, orchestration-protocols skill, observability-logging skill, and session-checkpoints skill are present and clearly signaled. However, no bundle files are provided to verify these references exist, and some content (like the full Dispute Protocol and DLQ format) could potentially be split into separate reference files to keep the main skill leaner. | 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
- monkilabs/opencastle
- Commit
cc13aaf
- 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.