universal-agent-handoff

Create complete, portable handoffs from Manus to another agent or Manus instance. Use when transferring an in-progress task, project, workflow, research effort, or operational context and the recipient needs both a concise execution prompt and a structured repository of supporting documents, custom skills, decisions, rules, and artifacts.

Quality

80%

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

Quality

Content

77%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 content is well-organized, concise, and features a clear validated workflow with concrete commands. Its main weakness is progressive disclosure: many referenced template and test paths do not exist in the provided bundle.

Suggestions

Include the referenced templates/ files (handoff-prompt.md, handoff-repository-structure.md, incomplete-tasks-open-decisions-checklist.md, validate-handoff-ci.yml, receiving-agent-quick-start-checklist.md, receiving-agent-startup-task-list.md, domain-customization-guide.md) in the bundle, or remove the references from the body.

Add the referenced tests/ directory (including test_secret_masking_patterns.py) so the stated regression-test command is runnable, or note that tests live elsewhere.

Tighten the sprawling reference-listing sentence in the Quality checks section into a short bulleted list to reduce repetition and improve scannability.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining basic concepts, but the long reference-listing sentence in the Quality checks section is sprawling and repeats validate_handoff_zip.py, leaving minor trim opportunities.	4 / 5
Actionability	Provides concrete, executable commands (e.g. `python -m unittest discover -s tests -p 'test_*.py' -v`, named scripts) and specific path/structure guidance, but several referenced template outlines are absent from the bundle, leaving minor gaps in copy-paste completeness.	4 / 5
Workflow Clarity	The 8-step Required workflow is clearly sequenced with explicit validation checkpoints and feedback loops (continuity check, 'resolve every failure before delivery', regression tests), matching the top anchor for batch packaging operations.	5 / 5
Progressive Disclosure	Structure and one-level-deep signaling for the existing references/ and scripts/ files are good, but the body references seven templates/ files and a tests/ directory that are not present in the bundle, so a substantial fraction of navigated paths are broken.	3 / 5
	Total	16 / 20 Passed

Description

83%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 strong description that clearly states both the capability and an explicit, trigger-rich 'Use when' clause. It is specific and distinctive, with only minor gaps in action variety and keyword synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete deliverables ("concise execution prompt" and "structured repository of supporting documents, custom skills, decisions, rules, and artifacts"), but the core verb is a single umbrella action ("Create complete, portable handoffs") rather than multiple distinct actions.	4 / 5
Completeness	Explicitly answers both what ("Create complete, portable handoffs... prompt and... repository") and when ("Use when transferring an in-progress task...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ("transferring an in-progress task, project, workflow, research effort, or operational context" and "Manus") with good synonym coverage, but lacks file-extension or shorthand variants that would round out the keyword set.	4 / 5
Distinctiveness Conflict Risk	The Manus-to-agent handoff niche with a prompt-plus-repository deliverable is mostly distinct, but the broad notion of transferring tasks/projects carries minor overlap with general task-management or handoff skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pvnkmnk/AgenticSelfHostSkills
Path: skills/universal-agent-handoff/SKILL.md
Commit: 0f62e6b

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.