paperclip-board

Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.

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

78%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.

Highly actionable content: executable curl recipes with full JSON bodies, well-sequenced workflows with approval and freshness checkpoints, and concrete presentation templates. The main weakness is structure — a 620-line single-file skill with a redundant endpoint table that should be split into one-level-deep reference files.

Suggestions

Move the 'Key Endpoints Reference' table into a references/api.md file and link to it from a short 'Key Endpoints' section, removing the duplication with the inline curl examples that already demonstrate each endpoint in context.

Split presentation templates (dashboard, task, agent, cost, approval formats) and the Link Format catalog into a references/presentations.md so the SKILL.md body focuses on workflows and decision rules.

Add explicit error-recovery guidance for the write paths — e.g., what to do when a PATCH/PUT fails, when a document PUT hits a stale baseRevisionId, or when an expected approval does not appear — to close the workflow validation gaps.

Dimension	Reasoning	Score
Conciseness	Lean, competent prose with no explanations of concepts Claude already knows, but the 35-row 'Key Endpoints Reference' table fully duplicates every endpoint already demonstrated with inline curl examples, and presentation templates could be trimmed. Matches anchor 4 (efficient with minor trimming possible), not 5 due to this real duplication; not 3 since nothing is padded or concept-teaching.	4 / 5
Actionability	Every section provides copy-paste-ready 'curl -sS' commands with complete JSON bodies, env-var-based URLs, discovery endpoints (/llms/agent-configuration.txt), and concrete output templates. Matches anchor 5: fully executable, covering the common cases.	5 / 5
Workflow Clarity	Onboarding is cleanly sequenced (Steps 1-4), session startup is a numbered checklist, escalation updates have an explicit board-approval checkpoint before writes, and write-path freshness plus baseRevisionId act as validation checkpoints. Matches anchor 4 rather than 5 because explicit error-recovery feedback loops (handling failed requests, missing approvals, retry behavior) are absent.	4 / 5
Progressive Disclosure	No bundle files exist; this is a 620-line monolith whose Key Endpoints Reference table, Link Format catalog, and presentation templates clearly belong in separate reference files. Section headers give good internal structure (above anchor 2), but all reference-type content is inline with no external files — matching anchor 3 ('content that should be separate is inline') rather than 4 (nothing is placed in separate files).	3 / 5
	Total	16 / 20 Passed

Description

87%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: third-person voice, concrete capability areas, an explicit 'Use when...' trigger clause with natural terms, and a clearly distinct niche. Minor room to broaden trigger coverage with synonyms like 'hire agents' or 'budget/spend'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Manage a Paperclip company as a board member via chat') and lists several concrete capability areas — 'onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review' — matching anchor 4 with minor gaps (e.g., agent hiring and prompt editing are not named). Not 5 because the capability list is area-nouns rather than comprehensive concrete actions; not 3 because it goes well beyond 1-2 actions.	4 / 5
Completeness	Explicitly answers both: what ('Manage a Paperclip company as a board member via chat') and when ('Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane'). Matches anchor 5 exactly — clear what plus concrete 'Use when' trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('onboarding', 'approvals', 'task monitoring', 'cost oversight', 'work product review', 'Paperclip control plane') — good coverage per anchor 4, but a few natural variants are missing ('hire agents', 'budget/spend', 'team setup'). Not 5 because there is no synonym-level or fuller variation coverage.	4 / 5
Distinctiveness Conflict Risk	Highly niche triggers ('Paperclip', 'board member', 'Paperclip control plane') with no overlap with generic skill domains — clear niche with distinct triggers and minimal conflict risk, matching anchor 5.	5 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (620 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: skills/paperclip-board/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.