create-agent-adapter

Create or modify Paperclip agent adapters across server, UI, and CLI surfaces. Use when adding support for a new CLI agent, API agent, custom process, or adapter package.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

A highly actionable, well-sequenced guide with concrete code contracts and validation checkpoints, weakened mainly by a monolithic single-file structure with no progressive disclosure and some explanatory prose that could be trimmed.

Suggestions

Split the large reference material (Section 2 types, Section 7 skills injection, Section 8 security) into separate referenced files under ./references/ and link to them one level deep so SKILL.md stays a concise overview.

Trim explanatory prose in Section 5 ('An agent working on an issue may be woken dozens of times...') and Section 7 down to instruction-only guidance to improve token efficiency.

Consider moving the TranscriptEntry kinds table (Section 9) and server-utils helper table (Section 6) into a reference doc, keeping SKILL.md focused on the creation workflow.

Dimension	Reasoning	Score
Conciseness	The bulk is genuinely Paperclip-specific reference Claude does not know (interfaces, helper tables, code), but prose passages such as the Section 5 session-management rationale and Section 7 skills-injection narrative are explanatory padding that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	Provides copy-paste-ready package.json exports, index.ts metadata, registry registration snippets, build-config, and a concrete helpers table with signatures — fully executable guidance, the level-3 anchor, not the pseudocode level-2.	3 / 3
Workflow Clarity	Section 3 sequences package creation through server/UI/CLI with explicit validation checkpoints (the testEnvironment contract in 2.1, the Testing section 10), and Sections 4 and 11 provide checklists with feedback loops, matching the level-3 anchor.	3 / 3
Progressive Disclosure	The skill is a single ~700-line file organized into clear numbered sections, but content that should be split (the types reference, security guide, skills-injection guide) is all inline with no bundle files or one-level-deep references, fitting the level-2 'content that should be separate is inline' rather than a monolithic level-1.	2 / 3
	Total	10 / 12 Passed

Description

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.

A tight, third-person description that states concrete capabilities and an explicit 'Use when' trigger covering the natural request phrasings. It is specific, complete, and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Create or modify') across named surfaces ('server, UI, and CLI'), matching the 'lists multiple specific concrete actions' anchor rather than the single-action level 2.	3 / 3
Completeness	Explicitly answers both what ('Create or modify Paperclip agent adapters...') and when ('Use when adding support for a new CLI agent, API agent, custom process, or adapter package.'), the level-3 anchor; not the level-2 'what without when'.	3 / 3
Trigger Term Quality	The 'Use when' clause surfaces natural phrases a user would say ('new CLI agent', 'API agent', 'custom process', 'adapter package'), giving good coverage rather than just the generic level-2 'Works with X'.	3 / 3
Distinctiveness Conflict Risk	The 'Paperclip agent adapters' niche with its distinct CLI/API/process triggers is unlikely to collide with other skills, matching the clear-niche anchor rather than the overlapping level-2.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (717 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: .agents/skills/create-agent-adapter/SKILL.md
Commit: f2f168f

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.