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

83%

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

73%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 highly actionable and clearly sequenced with strong validation feedback loops, and it uses progressive disclosure to offload detail to reference files. Its main weakness is severe verbosity — rules are restated repeatedly and Claude-inferable concepts are over-explained, inflating the token budget well past what earns its place.

Suggestions

Collapse the repeatedly restated execution-contract rules (writes-first/summary-last, recover-instantly, execute-never-narrate) into a single concise checklist instead of multiple long paragraphs each re-explaining the same anti-failure posture.

Move reference-grade detail — full interaction payload schemas, the hot-routes endpoint table, and the status quick guide — into the existing references/ files so SKILL.md stays a lean overview.

Fix or remove the broken reference to scripts/paperclip-issue-update.sh (the file is absent from scripts/); either add the script or point to the present paperclip-upload-artifact.sh / the jq --arg pattern.

Dimension	Reasoning	Score
Conciseness	The ~600-line body is noticeably verbose — rules are restated multiple times in long paragraph form (e.g., the closing-status-PATCH rule is one ~800-word paragraph) and it explains behaviors Claude can infer ("shell state does not persist between tool calls"), putting it below the "mostly efficient" midpoint.	2 / 5
Actionability	Provides copy-paste-ready curl commands with exact headers, request bodies, idempotency-key formats, and worked examples covering checkout, attachments, and interaction POSTs chained with the closing PATCH — fully executable across the common cases.	5 / 5
Workflow Clarity	The 9-step heartbeat procedure is clearly sequenced with explicit validation checkpoints (close-time audit, verify-2xx-echoes, pre-send grep check) and error-recovery feedback loops (409 handling, compact-resend-on-empty), plus the fixed four-step approval recipe.	5 / 5
Progressive Disclosure	It points to one-level-deep, clearly signaled reference files (api-reference, artifacts, cases, etc.), but inlines reference-grade detail (full interaction payloads, endpoint table, status guide) that belongs in references, and references a missing helper script (paperclip-issue-update.sh).	4 / 5
	Total	16 / 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.

The description is clear, specific, and complete — it names the domain, enumerates concrete actions, and provides an explicit "Use when…" trigger clause covering the skill's main behaviors. Its only weakness is that the trigger set is product-scoped action verbs rather than a broad synonym/extension set.

Dimension	Reasoning	Score
Specificity	Names the domain ("Paperclip control plane API") and lists six concrete actions — checking assignments, updating issue status, posting comments, delegating work, managing routines, calling API endpoints — for comprehensive coverage matching the anchor-5 example.	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	Trigger verbs (checking assignments, updating issue status, posting comments, delegating work, managing routines) are natural coordination phrases with good coverage, but the set is product-scoped action verbs rather than the broad synonym/extension set an anchor-5 example lists, so it sits just below the top anchor.	4 / 5
Distinctiveness Conflict Risk	Product-anchored to a specific control-plane API with a distinct task-coordination/governance niche and specific triggers, giving minimal conflict risk with unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (624 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 13 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: paperclipai/paperclip
Path: skills-releases/paperclip/v7-roster/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.