paperclip

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

Quality

86%

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

81%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.

A highly actionable, well-sequenced governance skill body with strong validation checkpoints and clean progressive disclosure to real reference files. Its main weakness is conciseness — verbatim duplication and rule restatements inflate an already long document.

Suggestions

Remove the verbatim duplication: the plan-to-tasks companion-skill sentence (Steps near line 427-429) is repeated word-for-word, and rule #1 ("never ask a human to do what an agent could do") is restated near the end — keep each once.

Standardize reference path prefixes so all in-body citations use the same form (either "references/api-reference.md" or "skills/paperclip/references/api-reference.md"), since the mixed prefixes make navigation inconsistent.

Tighten the Critical Rules prose and Status Quick Guide by folding the explanations that merely restate earlier Step guidance, reducing token weight without losing the actionable detail.

Dimension	Reasoning	Score
Conciseness	The ~480-line body is dense and mostly domain-specific rather than padded with concepts Claude already knows, but it contains verbatim duplication (rule #1 restated at the top and bottom, the plan-to-tasks companion-skill sentence duplicated) and prose rules that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready endpoints with headers, JSON payloads, status enums, expected HTTP codes (409, 422), and a shell helper with heredoc covering the common cases (checkout, update, approvals, interactions, subtasks).	5 / 5
Workflow Clarity	The 9-step heartbeat procedure is clearly sequenced with a scoped-wake fast path and explicit validation checkpoints (409 never-retry, blocked-task dedup, final-disposition checklist, status quick guide) appropriate for destructive/batch governance operations.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing one level deep to 7 real reference files and 1 real script, each clearly signaled with "Load X when..."/"read references/Y.md"; minor gaps from inconsistent path prefixes ("references/" vs "skills/paperclip/references/") and some inlined API detail that could live in references.	4 / 5
	Total	17 / 20 Passed

Description

92%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, well-structured description that clearly states both the capability and a concrete "Use when" trigger list tied to a distinctive product niche. Minor room for richer synonym coverage in the trigger terms.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete capabilities — "checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints" — giving comprehensive coverage of the skill's domain.	5 / 5
Completeness	Explicitly answers both what ("Interact with the Paperclip control plane API for task coordination and governance") and when ("Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when..." clause lists natural user phrasings (checking assignments, posting comments, delegating work, managing routines), but misses some synonyms/variations a user might naturally say.	4 / 5
Distinctiveness Conflict Risk	"Paperclip control plane API" names a clear niche with distinct, product-specific triggers, so overlap with other skills is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 7 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: paperclipai/paperclip
Path: skills-releases/paperclip/v0/SKILL.md
Commit: 1c07b59

Reviewed: 1 day 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.