Use when capturing session state before switching context, ending a session, or manually preserving progress — creates a structured handoff document in docs/handoffs/ so a future session can resume seamlessly
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-constructed description that clearly communicates when to use the skill and what it produces. Its main weakness is that it could be more specific about the concrete actions involved (e.g., what state is captured, what the document structure looks like). The trigger terms and completeness are strong, making it easy for Claude to select appropriately.
Suggestions
Add more specific concrete actions beyond 'creates a structured handoff document' — e.g., 'captures current task status, open questions, file changes, and next steps into a structured handoff document'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (session state/handoff documents) and describes the core action (creates a structured handoff document), but doesn't list multiple specific concrete actions beyond that single output. It mentions triggers like 'capturing session state' and 'preserving progress' but doesn't detail what the document contains or what specific steps are performed. | 2 / 3 |
Completeness | Explicitly answers both what ('creates a structured handoff document in docs/handoffs/') and when ('when capturing session state before switching context, ending a session, or manually preserving progress') with a clear 'Use when' clause at the start. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'switching context', 'ending a session', 'preserving progress', 'handoff', 'resume'. These cover the main scenarios a user would describe when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the concept of session handoff documents in a specific directory (docs/handoffs/) is a clear niche. The triggers around context switching and session preservation are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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, highly actionable skill with a clear multi-step workflow and a complete, copy-paste-ready template. Its main weakness is moderate verbosity — the Cross-Agent Handoff section over-explains the value proposition, and some contextual sections could be trimmed. The progressive disclosure is adequate but could benefit from splitting supplementary content (compaction hooks, cross-agent patterns) into separate files.
Suggestions
Trim the 'Cross-Agent Handoff' section to just the use-case bullet list — remove the 'Why this works' paragraph and introductory sentence, as Claude can infer interoperability from the markdown-file format.
Consider moving the 'Automatic Compaction Handoff' section to a separate reference file (e.g., COMPACTION-HOOKS.md) since it describes a different trigger mechanism and adds length without aiding the manual workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some sections that could be tightened. The 'Cross-Agent Handoff' section with its extensive use cases and the 'Why this works' explanation are somewhat verbose — Claude can infer cross-agent compatibility from the fact that it's a markdown file. The 'When to Use' / 'Don't use when' section and the 'Automatic Compaction Handoff' section add useful but slightly padded context. | 2 / 3 |
Actionability | The skill provides fully concrete, executable guidance: specific bash commands for gathering state, an exact markdown template with frontmatter, clear topic slug guidelines with good/bad examples, and a specific output path pattern. Every step tells Claude exactly what to do and produce. | 3 / 3 |
Workflow Clarity | The 5-step process is clearly sequenced with explicit actions at each stage. Step 1 gathers mechanical state, Step 2 generates the topic, Step 3 writes the document using a complete template, Step 4 fills all sections with specific guidance per section, and Step 5 confirms with a structured summary. The workflow is linear and unambiguous with a clear confirmation checkpoint at the end. | 3 / 3 |
Progressive Disclosure | The skill references companion skills (handoff-resume, handoff-list, compound, finishing-a-development-branch) and mentions hooks/scripts, but all content is inline in a single file. The Cross-Agent Handoff section and Automatic Compaction Handoff section could be split into separate reference documents. However, no bundle files are provided, so there's no external structure to leverage — the inline approach is reasonable but the document is long enough that splitting would help. | 2 / 3 |
Total | 10 / 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.
c037ce3
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.