CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 well-engineered operational skill body: dense, concrete, safety-aware, with real validation checkpoints and an error-recovery troubleshooting map. Weaknesses are minor — a trimmable AWS credential-precedence explanation, inconsistent script path forms, and a `README.md` reference that does not exist in the bundle.

DimensionReasoningScore

Conciseness

The body is lean and project-specific — requirements, env vars, workflow, update rules, safety, and troubleshooting with no padding or textbook explanation. The one paragraph explaining AWS SDK credential precedence ("static env keys take precedence over `AWS_PROFILE` in every AWS SDK...") restates general AWS knowledge Claude already has and could be trimmed to a sentence, which keeps it at the 4 anchor rather than the 5 anchor's every-token-earns-its-place.

4 / 5

Actionability

Concrete, runnable commands throughout: `scripts/publish.sh <dir> --dry-run`, copy-paste bash blocks for publish and `--update`, exact env var names, slug rules, and named error messages with fixes. Minor gap: the workflow refers to `scripts/publish.sh` while the bash examples use `.agents/skills/paperclip-page/scripts/publish.sh`, and there is no example of verifying the returned URL — mostly executable with small gaps, the 4 anchor.

4 / 5

Workflow Clarity

The workflow is clearly sequenced with an explicit validation checkpoint (step 1 inspect for public-only content, step 2 `--dry-run` to validate structure and preview the URL), and the update path adds a state-file ownership gate plus a troubleshooting section that maps each failure message to a recovery action — matching the 5 anchor's validation, feedback, and error-recovery loop pattern for a remote-mutating batch operation.

5 / 5

Progressive Disclosure

Well-organized sections with the operational detail correctly delegated to `scripts/publish.sh` (present in the bundle) and operator setup pointed to `README.md`. However, that referenced `README.md` is not present in the skill bundle, and the publish script path is stated inconsistently — good structure with minor organization gaps, the 4 anchor rather than the 5 anchor's fully verifiable one-level-deep references.

4 / 5

Total

17

/

20

Passed

Description

83%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, terse, explicit about both what it does and when to use it, with a distinct niche and good natural trigger terms. The only gaps are a few missing trigger synonyms (e.g., "publish", "put online", "get a URL") and a single-action capability list.

DimensionReasoningScore

Specificity

"Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host" names concrete actions (publish static HTML pages, publish asset folders) with a specific target host, but the action list is narrow — a single publish capability rather than the multiple comprehensive actions of the 5 anchor. It sits above the 3 anchor because two distinct actions plus a named destination are specified with no filler.

4 / 5

Completeness

The what is explicit and concrete ("Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host") and the when is explicit with concrete trigger phrases ("Use when asked to deploy, host, or share a persistent page, viewer, prototype, report, or static site"). This matches the 5 anchor's structure of clear what + explicit when with trigger phrases; nothing below fits better.

5 / 5

Trigger Term Quality

"deploy, host, or share a persistent page, viewer, prototype, report, or static site" gives good natural-verb-plus-noun coverage. It misses a few common variations users would say ("publish", "put online", "get a URL/link", specific file terms), so it falls short of the 5 anchor's comprehensive synonym coverage but is clearly above the 3 anchor's missing-variations profile.

4 / 5

Distinctiveness Conflict Risk

"Paperclip S3/CloudFront page host" carves a clear niche and most triggers (persistent page, static site, viewer) are distinct, but generic verbs like "deploy"/"host" overlap with general deployment and hosting skills. Mostly distinct with minor overlap risk — the 4 anchor — rather than the 5 anchor's minimal-conflict profile.

4 / 5

Total

17

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.