Turn an idea, tweet, or task into a skill in the Paperclip skills catalog (packages/skills-catalog). Use when asked to FIND or MAKE a skill and publish it as a bundled/optional catalog skill: research prior art, reference or author it, add examples, regenerate the manifest, open a PR.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required Step 0 workflow runs `xc` searches and thread lookups on X, and Step 1 runs GitHub code/repo searches and a web search, so outsider-authored posts, repos, and pages reach the agent only after it actively searches or fetches them, not through a feed an outsider can post into.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The catalog-ref path makes the manifest builder fetch files from a GitHub repository at build time and install them as shipped skill material, and the example repo `mvanhorn/last30days-skill` is an individual-owned, unofficial source; the commit pin is an immutable identifier, but it does not establish first-party publisher provenance, so the tier is medium.
paperclipai/paperclip
41a3520
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.