claude-handoff

把当前对话交接给一个全新的 background agent，让它立即接手工作。

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/in-progress/claude-handoff/SKILL.md

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary lean instruction file: an exact executable command, concrete flag examples, and precise inclusion/exclusion rules for the handoff summary, with zero filler. The only minor gap is that the summary-writing requirements are distributed rather than sequenced as a checklist, and the sensitive-information scrub is stated as a rule rather than a verify-before-launch checkpoint.

Dimension	Reasoning	Score
Conciseness	The ~10-line body is lean and every sentence carries non-obvious operational guidance (exact command, flags, exclusions, sanitization rule, argument handling). Nothing explains concepts Claude already knows, matching anchor 5; not 4 because there are essentially no padded or trimmable passages.	5 / 5
Actionability	Provides a copy-paste-ready command template (`claude --bg --name "<descriptive name>" "<handoff summary>"`), a concrete flag example (`--name "Fix login bug"`), the management command (`claude agents`), and a conditional rule for arguments. Matches anchor 5; the only non-assembled parts are placeholders that are inherently task-specific.	5 / 5
Workflow Clarity	The sequence (write summary → don't save → launch background agent → handle user arguments) is clear, but the summary-composition requirements are scattered across separate paragraphs with no ordered checklist, and there is no pre-launch verification step confirming sensitive information was scrubbed. Fits anchor 4 ('clear sequence, minor validation gaps'); not 5 because a checkpoint for the sanitization rule is implicit.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ exist) and no need for external references; each paragraph addresses one concern, so the simple-skill exception applies and structure earns a 5. Not 4 because nothing that belongs in a separate file is inlined and nothing is buried.	5 / 5
	Total	19 / 20 Passed

Description

53%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.

The description states a single concrete capability clearly and in an appropriately short form, but it omits any 'when to use' trigger guidance and most of the skill's actual capabilities (summary writing, naming, suggested-skills section). It is distinguishable from other skills yet would benefit from trigger phrases and slightly fuller coverage of what the skill does.

Suggestions

Add an explicit trigger clause, e.g. 'Use when handing off or transitioning the current conversation to another agent, or when the user mentions handoff/交接 or continuing work in a new session.'

Mention the core sub-actions so coverage is comprehensive: writing a handoff summary, launching a named background agent, and passing along suggested skills.

Include natural synonyms such as 'handoff summary', 'continue work', and 'take over' so the description matches phrases users would actually say.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("交接给一个全新的 background agent", "立即接手工作") but stops at a single capability — summary writing, naming, and skill suggestions from the body are not mentioned. Not 4 because coverage is not 'several specific actions'; not 2 because the action named is concrete, not generic.	3 / 5
Completeness	Has a clear 'what' (hand the conversation to a new background agent that takes over immediately) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because 'when' is entirely absent, not 2 because the 'what' is clear and specific.	3 / 5
Trigger Term Quality	Contains some relevant natural terms ("交接" handoff, "background agent", "接手" take over) but misses common variations and synonyms such as "handoff summary", "continue work", or "launch/spawn agent". Fits anchor 3 rather than 4, which expects good coverage with only a few terms missing.	3 / 5
Distinctiveness Conflict Risk	The niche (launching a background agent to continue the current conversation) is mostly distinct with only minor overlap risk against agent/session-management skills. Not 5 because there are no explicit distinct trigger phrases, and clearly not 2-3 since the described action is specific rather than broad.	4 / 5
	Total	13 / 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: vinvcn/mattpocock-skills-zh-CN
Path: skills/in-progress/claude-handoff/SKILL.md
Commit: 3f92a83

Reviewed: 4 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.