A tight, well-structured instruction body: exact output location with a timestamped filename template, a six-section document skeleton, and a rules section covering dedup-via-reference, sensitive-data redaction, argument handling, and a short-conversation bail-out. The only meaningful gap is the lack of a small worked example of the handoff document.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean and assumes Claude's competence: no concept explanations, no padding, every line is an instruction, a template, or a rule. It matches the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Guidance is concrete: an exact output path template ("$TMPDIR/handoff-YYYY-MM-DD-HHMM.md（用实际时间戳替换）"), a numbered six-section document structure with content hints per section, and a precise bail-out threshold ("少于 3 轮实质交流"). It stops short of a worked example of the output document, which keeps it at 'mostly executable guidance with minor gaps' rather than the copy-paste-ready score-5 anchor.	4 / 5
Workflow Clarity	The sequence is unambiguous for a simple single-purpose skill: gate on conversation length (bail out if < 3 substantive turns), compose the six-section document, save to the timestamped path, and report the full path to the user. The gating checkpoint is explicit, but the execution order must be assembled from the section layout (output location, structure, rules) rather than read as an explicit step list — minor gap, so score 4 rather than 5.	4 / 5
Progressive Disclosure	A simple skill under 50 lines with no external references needed; per the rubric's simple-skills note, well-organized sections suffice. Sections (输出位置 / 文档结构 / 规则) are clearly headed and no bundle files exist to reference, so structure is appropriate with no inlined content that belongs elsewhere.	5 / 5
	Total	18 / 20 Passed

Description

73%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 concise, bilingual description that clearly states what it produces (a handoff document), for whom (the next agent), and how it is invoked (manually via /handoff). Its main weakness is the absence of an explicit 'use when' situation — the trigger guidance is limited to the invocation instruction — and only a single action verb.

Suggestions

Add an explicit trigger clause, e.g., 'Use when a session is ending or context is running out and work must continue in a new session' — this would lift completeness to the score-5 anchor.

Mention 1-2 more concrete aspects of the action (e.g., 'summarize completed work, current state, and next steps') to strengthen specificity beyond the single 'compress' verb.

Include a few more natural synonyms users might say, such as 'session summary' or 'context handoff', to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action — "将当前对话压缩为交接文档" (compress the current conversation into a handoff document) — with a clear output artifact and beneficiary ("供下一个 agent 接续工作"). It does not list several distinct actions, so it matches "names domain and 1-2 concrete actions, but not comprehensive" rather than the score-4 anchor requiring multiple specific actions.	3 / 5
Completeness	The 'what' is fully explicit (compress conversation into a handoff brief for the next agent), and 'when' is addressed by "手动调用 /handoff" (manually invoke /handoff), which is equivalent explicit trigger guidance given the skill is user-invoked only (disable-model-invocation). The 'when' is present but could be more situational (e.g., 'use when a session is ending and work must continue in a new session'), so it fits the score-4 anchor rather than the score-5 anchor with concrete trigger phrases.	4 / 5
Trigger Term Quality	Good natural keyword coverage in two languages: "交接文档", "handoff document", "session handoff brief", plus the explicit invocation "/handoff" — several synonyms a user would naturally say. A few common variations are missing (e.g., "summarize session", "context handoff", "session summary"), which keeps it below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Session handoff for agent continuation is a clear niche with distinct triggers (handoff/交接/session handoff brief) and virtually no overlap with other skill domains, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: feiskyer/claude-code-settings
Path: skills/handoff/SKILL.md
Commit: 95dab59

Reviewed: 8 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.