Validate agent handoff packets and resume readiness using schema, freshness, and replay checks. Use when tasks pause/resume across sessions, agents, or humans — including when a user wants to continue where they left off, hand off to another agent, resume a previous task, or pick up an interrupted workflow. Includes explicit untrusted-content/prompt-injection guardrails for third-party inputs.
100
100%
Does it follow best practices?
Impact
100%
1.31xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 an excellent skill description that clearly articulates specific validation capabilities (schema, freshness, replay checks) while providing comprehensive trigger guidance for when to use it. The description effectively covers multiple user scenarios in natural language and carves out a distinct niche around agent handoffs and session continuity that won't conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Validate agent handoff packets', 'resume readiness', 'schema, freshness, and replay checks', and 'untrusted-content/prompt-injection guardrails'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (validate handoff packets, schema/freshness/replay checks, guardrails) AND when with explicit 'Use when...' clause covering multiple trigger scenarios (pause/resume, cross-session, agent handoffs, interrupted workflows). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'pause/resume', 'continue where they left off', 'hand off to another agent', 'resume a previous task', 'pick up an interrupted workflow'. These match how users naturally describe these scenarios. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focusing specifically on agent handoff validation and session continuity. The combination of 'handoff packets', 'schema validation', 'replay checks', and 'prompt-injection guardrails' creates a clear, unique domain unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%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 that efficiently communicates a complete handoff validation workflow. It excels at providing concrete, actionable guidance with executable code, clear examples of both valid and invalid states, and explicit validation checkpoints. The untrusted content guardrails section adds valuable safety constraints without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting only necessary information without explaining concepts Claude already knows. Field lists, examples, and workflow steps are direct and purposeful. | 3 / 3 |
Actionability | Provides executable Python code for freshness checking, concrete JSON examples (both valid and invalid), specific field requirements, and copy-paste ready output formats with clear pass/fail indicators. | 3 / 3 |
Workflow Clarity | Clear sequential workflow with explicit validation checkpoints (schema → freshness → resume_token → replay check → classification). Includes classification outcomes and recovery steps for each failure mode. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (fields, examples, workflow, output format, guardrails). Content is appropriately sized for a single file without needing external references, and sections are logically ordered for discovery. | 3 / 3 |
Total | 12 / 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.
Reviewed
Table of Contents