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

83%

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

75%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.

A compact, well-structured reference skill with concrete templates, explicit checklists, and feedback loops for Team Lead orchestration. It scores solidly across dimensions but holds at 4 due to a few abstract sections and references pointing outside the local bundle.

Suggestions

Tighten the Deepen-Plan prose into a one-line completion criterion and replace abstract instructions ('Split by domain into parallel Researchers') with a concrete split heuristic or example.

Add an explicit output-validation checkpoint in the Delegation Sequence (e.g., 'Verify agent output satisfies acceptance_criteria before marking Complete') to close the workflow-clarity gap.

Move the specialist registry / model-assignment detail into a local references/ file referenced from SKILL.md, or inline the minimum needed, so progressive disclosure stays one level deep within the bundle.

Dimension	Reasoning	Score
Conciseness	The body is table-driven and dense (routing tiers, complexity scoring, status handling) with little fluff, but a few prose passages like the Deepen-Plan completion explanation ('Deepen is done when no field is still a guess ...') could be trimmed, placing it just below the fully lean 5.	4 / 5
Actionability	Provides concrete, copy-paste-ready artifacts (the JSON delegation envelope, exact DLQ field list, file paths like .opencastle/AGENT-FAILURES.md and .opencastle/DISPUTES.md), but the Deepen-Plan and Error Recovery sections remain high-level ('Split by domain into parallel Researchers', 'load orchestration-protocols skill'), leaving minor gaps versus fully executable guidance.	4 / 5
Workflow Clarity	A clear 7-step Delegation Sequence plus a 5-point Pre-Delegation Policy checklist and a Status Handling table provide explicit checkpoints and feedback loops (Blocked -> upgrade/escalate; never re-dispatch unchanged), but output verification against acceptance criteria is only implied ('Fast review'), a minor validation gap below the explicit-feedback-loop 5.	4 / 5
Progressive Disclosure	Content is split into well-organized sections with one-level-deep, clearly signaled references to agent-registry.md and sibling skills (observability-logging, session-checkpoints, orchestration-protocols); the registry reference points outside the skill bundle rather than to a local reference file, a minor organization gap below the ideal 5.	4 / 5
	Total	16 / 20 Passed

Description

91%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.

A strong, well-structured description that pairs four concrete capabilities with a rich, synonym-covered trigger clause answering both what and when. Minor overlap risk on generic delegation triggers keeps distinctiveness just below maximum.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('Provides model routing rules, validates delegation prerequisites, supplies cost tracking templates, defines dead-letter queue formats') — multiple specific actions with only minor coverage gaps, fitting the 'lists several specific actions; minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both 'what' (the four named orchestration functions) and 'when' ('Load when ...' with concrete trigger phrases), matching the anchor for clearly and explicitly answering both with concrete triggers.	5 / 5
Trigger Term Quality	The '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' clause provides comprehensive natural-term coverage including synonyms (assigning tasks / delegating work; choosing model tiers / choosing which model to use).	5 / 5
Distinctiveness Conflict Risk	The 'Team Lead orchestration' niche plus DLQ/dispute formats are mostly distinct, but generic triggers like 'assigning tasks' and 'delegating work' carry minor overlap risk with sibling orchestration skills, so it sits just below the minimal-conflict 5.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/team-lead-reference/SKILL.md
Commit: fa0c341

Reviewed: 5 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.