team-lead-reference

Provides model routing rules, validates delegation prerequisites, supplies cost tracking templates, defines dead-letter queue formats for Team Lead orchestration. Load when assigning tasks to agents, choosing model tiers, starting delegation session, running multi-agent workflow, delegating work, choosing which model to use, or assigning tasks.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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 is a lean, well-structured orchestration reference with concrete tables, a copy-paste delegation envelope, and clear validation/checkpoint-driven workflows. Minor gaps are outward delegation for some procedures and inlined detail that could live in reference files.

Suggestions

Inline the key steps for error recovery and logging rather than only pointing to the orchestration-protocols and observability-logging skills, so the skill is actionable without loading them.

Move the detailed Dead Letter Queue entry spec and Dispute Protocol steps into reference files (e.g. references/dlq-format.md) and summarize them in SKILL.md to improve progressive disclosure.

Tighten vague status actions like 'Fast review' into concrete verification steps (e.g. what to check before accepting output).

Dimension	Reasoning	Score
Conciseness	The body is dense and table-driven with no padding or explanation of concepts Claude already knows; every line (tier tables, scoring factors, checklists) earns its place.	5 / 5
Actionability	Mostly executable guidance with a copy-paste delegation envelope JSON and concrete tables, but some steps delegate outward ('Log via observability-logging skill', 'load orchestration-protocols skill') and a few status actions ('Fast review') are slightly abstract.	4 / 5
Workflow Clarity	A clear 7-step delegation sequence is backed by explicit validation checkpoints (5-point pre-delegation checklist, status handling table) plus feedback loops (DLQ, dispute protocol) for error recovery.	5 / 5
Progressive Disclosure	Good structure with clearly signaled one-level references to other skills and .opencastle files, but no bundle files are present and some detailed material (DLQ entry spec, dispute steps) is inlined rather than split into reference files.	4 / 5
	Total	18 / 20 Passed

Description

100%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 is a strong, third-person statement that concisely names four concrete capabilities and provides an explicit, synonym-rich 'Load when' trigger clause. It answers both what and when with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists four concrete, distinct actions ('Provides model routing rules, validates delegation prerequisites, supplies cost tracking templates, defines dead-letter queue formats'), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (four named actions for Team Lead orchestration) and 'when' (a 'Load when...' clause with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Trigger list covers natural phrases a user would say ('assigning tasks to agents', 'delegating work', 'choosing model tiers', 'running multi-agent workflow') including synonyms, satisfying comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	The 'Team Lead orchestration' niche and specific delegation/model-routing triggers make it clearly distinguishable with minimal conflict risk against other skills.	5 / 5
	Total	20 / 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: monkilabs/opencastle
Path: src/orchestrator/skills/team-lead-reference/SKILL.md
Commit: f297837

Reviewed: 6 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.