subagent-contract

Global contract for all specialist subagents — enforces role boundaries, scope discipline, and DONE/BLOCKED status signaling. Use when loading any agent that should operate as a bounded specialist following supervisor delegation patterns.

1.28x

Quality

72%

Does it follow best practices?

Impact

96%

1.28x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/subagent-contract/SKILL.md

Quality

Discovery

75%

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 effectively communicates its specialized purpose for agent orchestration with a clear 'Use when' clause. However, it relies heavily on technical jargon ('scope discipline', 'supervisor delegation patterns') that may not match natural user language, and the capabilities described are somewhat abstract rather than listing concrete actions the skill enables.

Suggestions

Add more natural trigger terms users might say, such as 'agent rules', 'multi-agent', 'agent coordination', or 'agent handoff'

Replace abstract concepts with concrete actions, e.g., 'Defines task boundaries, prevents scope creep, requires explicit completion signals (DONE/BLOCKED)'

Dimension	Reasoning	Score
Specificity	Names the domain (specialist subagents, role boundaries, scope discipline) and some actions (enforces, signaling), but uses abstract concepts rather than concrete actions. 'Enforces role boundaries' and 'scope discipline' are somewhat vague compared to listing specific operations.	2 / 3
Completeness	Clearly answers both what ('enforces role boundaries, scope discipline, and DONE/BLOCKED status signaling') and when ('Use when loading any agent that should operate as a bounded specialist following supervisor delegation patterns'). Has explicit 'Use when' clause with trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'subagents', 'specialist', 'supervisor delegation', 'DONE/BLOCKED status', but these are technical jargon. Missing natural user phrases - users might say 'agent rules', 'agent behavior', or 'multi-agent coordination' which aren't present.	2 / 3
Distinctiveness Conflict Risk	Very specific niche targeting subagent contracts and supervisor delegation patterns. The combination of 'specialist subagents', 'role boundaries', 'DONE/BLOCKED status signaling', and 'supervisor delegation' creates a distinct fingerprint unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Implementation

70%

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-structured contract skill that clearly defines behavioral boundaries and status signaling requirements for specialist agents. Its main weakness is the lack of concrete output examples showing what DONE and BLOCKED responses should actually look like, and some redundancy in restating the same principles across sections. The workflow and progressive disclosure are strong.

Suggestions

Add concrete examples of DONE and BLOCKED status responses showing the exact format expected (e.g., a sample DONE response with deliverables, a sample BLOCKED response with specific missing inputs)

Consolidate redundant content - scope discipline rules appear in multiple sections (Role Contract, Work Rules, Scope Discipline, Anti-Patterns) and could be unified

Consider removing the XML-style tags (<contract>, <rules>, etc.) as they add token overhead without clear benefit - standard markdown headers already provide structure

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some redundancy - the same concepts (scope discipline, no assumptions, BLOCKED signaling) are repeated across multiple sections. The XML-style tags add structure but also token overhead.	2 / 3
Actionability	Provides clear behavioral rules and checklists, but lacks concrete examples of actual DONE/BLOCKED output formats. The guidance is specific about what to do conceptually but doesn't show executable examples of the status signals in practice.	2 / 3
Workflow Clarity	Clear sequence for agent behavior: receive task → restate/acknowledge → identify scope → execute → signal status. Explicit validation checklists before DONE and BLOCKED signals provide good checkpoints. The Contract Enforcement section provides a clear 6-step workflow.	3 / 3
Progressive Disclosure	Appropriately structured with a clear reference to the detailed workflow diagram at the top. Sections are well-organized with clear headers. The skill serves as an overview/contract with one-level-deep reference to the orchestration documentation.	3 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: Jamie-BitFlight/claude_skills
Commit: 5667e97

Reviewed: 26 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.