paperzilla

Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs.

Quality

88%

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

87%

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

A tight, actionable CLI reference that is well-organized and copy-paste ready, scoring well on conciseness, actionability, and progressive disclosure. It reads as a command catalog rather than a guided workflow, which caps workflow clarity.

Suggestions

Add a short sequenced example for a common multi-step task (e.g., list project -> browse feed -> read paper -> summarize) with an explicit verify/retry checkpoint for `pz rec --markdown` while markdown is being prepared.

Note the verification step for `pz feedback clear` so destructive feedback actions are confirmed before running.

Dimension	Reasoning	Score
Conciseness	Lean CLI reference with no concept explanations Claude already knows; every command and flag earns its place, with only minor intro redundancy against the description.	3 / 3
Actionability	Fully executable `pz` commands with concrete flags and copy-paste-ready examples (e.g., `pz feed <project-id> --must-read --since 2026-03-01 --limit 5`).	3 / 3
Workflow Clarity	Commands are listed as a catalog rather than sequenced into a workflow, and there are no validation/verification checkpoints for multi-step fetch-and-summarize flows or the potentially destructive `pz feedback clear`.	2 / 3
Progressive Disclosure	No bundle files exist; the body is organized into clear, navigable sections (Install, Update, Auth, CLI reference) with one-level external URL references and no nested file hops.	3 / 3
	Total	11 / 12 Passed

Description

90%

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, complete description with explicit what/when triggers and natural trigger terms, anchored to a clear Paperzilla niche. Its only real weakness is the second-person 'Chat with your agent' opening, which violates the required third-person voice and caps specificity.

Suggestions

Rewrite the opening in third person (e.g., 'Chats with the agent about ...') to recover the specificity point lost to the voice penalty.

Lead with the concrete actions rather than the conversational framing so the capability list reads as the primary clause.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs') which would merit a 3, but the second-person phrasing 'Chat with your agent' triggers the rubric's -1 voice penalty.	2 / 3
Completeness	Explicitly states both what it does ('Chat ... about projects, recommendations, and canonical papers in Paperzilla') and when to use it ('Use when users ask for ...'), with explicit triggers.	3 / 3
Trigger Term Quality	'recommendations', 'canonical paper details', 'feedback', 'feed export', and 'Atom feed URLs' are natural terms a user would say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The Paperzilla-specific niche and distinct recommendation/paper/feed triggers make it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/paperzilla/SKILL.md
Commit: 757b63b

Reviewed: about 11 hours 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.