Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying "continue later", "save progress", "session summary", or "pick up where I left off".
94
93%
Does it follow best practices?
Impact
93%
2.06xAverage score across 3 eval scenarios
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 an excellent skill description that clearly communicates what the skill does (generates structured handoff documents with specific content areas) and when to use it (with multiple natural trigger phrases). It uses proper third-person voice, is concise without being vague, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work.' This clearly describes what the skill produces and what it contains. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate a structured handoff document capturing progress, tasks, decisions, and context) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). Both are well-articulated. | 3 / 3 |
Trigger Term Quality | Includes highly natural trigger phrases users would actually say: 'continue later', 'save progress', 'session summary', 'pick up where I left off', and 'ending a session'. These cover common variations of how users express the need to pause and resume work. | 3 / 3 |
Distinctiveness Conflict Risk | This skill occupies a clear niche around session handoff/continuity. The trigger terms are specific to session management and unlikely to conflict with other skills like general documentation or note-taking tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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 skill that provides a clear, actionable template for session handoffs. The output template is particularly strong — it's comprehensive yet structured for quick scanning. The workflow steps could be slightly more explicit about validation (e.g., confirming the handoff document covers all uncommitted work), but overall this is a high-quality skill that respects token budget while delivering concrete guidance.
Suggestions
Add a brief validation step to the workflow, e.g., 'Verify the handoff covers all uncommitted changes and open branches before finalizing' to strengthen workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. The opening line distinguishing handoff from wrap-up is a valuable clarification. Every section earns its place — no unnecessary explanations of what a handoff is or why it matters. | 3 / 3 |
Actionability | Provides concrete bash commands for gathering state, a fully structured output template with specific field examples, and a copy-pasteable resume command format. The guardrails give clear, specific behavioral guidance. | 3 / 3 |
Workflow Clarity | The 5-step workflow is listed but lacks validation checkpoints — there's no step to verify completeness (e.g., confirming all uncommitted changes are accounted for, or that the resume command accurately reflects next steps). For a document generation task this isn't critical, but the steps are somewhat vague (e.g., 'Gather current state from git' could be more explicit about what to check). | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single clear purpose, the content is well-organized with distinct sections (trigger, workflow, commands, output template, guardrails). No external references are needed and the structure supports easy scanning. | 3 / 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.
1de1554
Table of Contents
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.