paperclip-page

Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host. Use when asked to deploy, host, or share a persistent page, viewer, prototype, report, or static site without here.now.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%

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

A concise, highly actionable skill body with clear workflows and validation for an external publishing operation. Its only notable weakness is a referenced `README.md` path that is not present in the bundle, slightly weakening navigation.

Suggestions

Either add the referenced `README.md` (operator setup, AWS policy examples, credential rotation) to the bundle or remove the trailing reference so no navigation path 404s.

Mention or link `scripts/publish.test.mjs` if it is meant to be part of the skill's verification story, since it exists in the bundle but is not surfaced from the body.

After the dry-run step, make the validate-then-fix-then-retry loop explicit (e.g., "If dry-run reports problems, fix the source and re-run dry-run before publishing") rather than leaving it implied.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (it never explains what S3/CloudFront or S3 syncing are); every section earns its place, fitting the efficient anchor rather than the padded level 2.	3 / 3
Actionability	Provides copy-paste-ready, real executable commands (`scripts/publish.sh <dir> --dry-run`, the full publish invocation) backed by an existing bundle script, with specific flags explained, matching the fully-executable anchor.	3 / 3
Workflow Clarity	A numbered 5-step sequence includes an explicit dry-run validation checkpoint, the update path requires ownership-proof validation, and a Troubleshooting section gives error-recovery feedback, so it is not capped at 2 for missing validation on a batch/external operation.	3 / 3
Progressive Disclosure	Sections are well organized and the `scripts/publish.sh` reference is real and one level deep, but the body also points to a `README.md` "next to this skill" that does not exist in the bundle, leaving a broken navigation reference; this keeps it at the structured-but-imperfect level 2 rather than the clean one-level-deep level 3.	2 / 3
	Total	11 / 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, well-formed description that states concrete capabilities, gives a broad natural trigger clause, and is clearly distinguished by its branded niche. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ("Publish static HTML pages and asset folders") with a named target ("Paperclip S3/CloudFront page host"), matching the multi-specific-action anchor rather than the domain-only level 2.	3 / 3
Completeness	Explicitly answers what (publish static HTML/asset folders to the page host) and when (the "Use when..." trigger clause), so it is not capped at 2 by the missing-trigger guideline.	3 / 3
Trigger Term Quality	"Use when asked to deploy, host, or share a persistent page, viewer, prototype, report, or static site" gives broad natural-language coverage a user would actually say, satisfying the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The branded Paperclip niche plus the "without here.now" disambiguator make it a clear, distinct trigger unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: paperclipai/paperclip
Path: .agents/skills/paperclip-page/SKILL.md
Commit: 81f47e7

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.