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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/paperzilla/SKILL.md

Quality

Content

76%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 lean, highly actionable CLI reference with excellent concrete commands and clear organization. Its main gaps are the absence of any validation/verification guidance for feedback-altering operations and minor redundancy between the description and the 'What you can ask' section.

Suggestions

Add a brief verification step around feedback changes (e.g. re-run `pz feed` or `pz rec` after `pz feedback`/`pz feedback clear`) to introduce a checkpoint and lift workflow clarity.

Trim or collapse the 'What you can ask' section since it duplicates the trigger phrases already in the frontmatter description.

Consider moving the full CLI reference into a bundled reference file (e.g. references/cli-reference.md) and keeping SKILL.md as an overview, which would push progressive disclosure toward the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly command- and flag-focused and does not explain concepts Claude already knows, but the 'What you can ask' section re-lists capabilities already in the description and the intro line ('This is the core Paperzilla skill...') could be trimmed, leaving minor over-explanation rather than padding.	4 / 5
Actionability	Commands are fully executable and copy-paste ready throughout — `brew install paperzilla-ai/tap/pz`, `pz feed <project-id> --must-read --since 2026-03-01 --limit 5`, `pz paper <paper-id> --markdown`, `pz feedback <project-paper-id> upvote` — with flags and worked examples covering the common cases.	5 / 5
Workflow Clarity	There is a loose install -> login -> use sequence and commands are well organized by category, but this is a command catalog rather than a sequenced workflow, with no validation checkpoints and no guidance for the mildly destructive `pz feedback clear` operation, matching the 'sequence present but checkpoints missing' anchor.	3 / 5
Progressive Disclosure	Clear section headers (Install, Update, Authentication, CLI reference, Output and automation, Configuration, References) and a final References block pointing one level deep to external docs give good navigation; no bundle files exist so the CLI reference is inline, which is appropriate for a CLI tool but keeps it just short of the top anchor.	4 / 5
	Total	16 / 20 Passed

Description

82%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, well-structured description that clearly states both capability and trigger conditions tied to a distinct product niche. The only notable issue is second-person voice ('your agent'), which caps the specificity score per the rubric.

Suggestions

Rewrite in third person to avoid the voice penalty, e.g. 'Chats with the agent about projects, recommendations, and canonical papers in Paperzilla.'

Replace the generic lead verb 'Chat... about' with concrete action verbs (e.g. 'Fetches', 'Summarizes', 'Exports') to lift specificity toward 4-5.

Add a couple of natural synonyms (e.g. 'research papers', plain 'papers') to round out trigger-term coverage toward the top anchor.

Dimension	Reasoning	Score
Specificity	The description lists several specific capabilities ('recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs'), which would anchor at 4, but the lead verb 'Chat with your agent about' is generic rather than a concrete action verb and the second-person phrasing ('your agent') triggers the -1 voice penalty, bringing it to 3.	3 / 5
Completeness	It explicitly answers both 'what' (chat about projects, recommendations, and canonical papers in Paperzilla) and 'when' via a clear 'Use when users ask for...' clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases users would actually say are well covered ('project recommendations', 'canonical paper details', 'markdown-based summaries', 'recommendation feedback', 'feed export', 'Atom feed URLs'), though a few common synonyms (e.g. plain 'papers', 'research papers') are absent.	4 / 5
Distinctiveness Conflict Risk	Tightly bound to a named product (Paperzilla) with niche-specific triggers (canonical papers, Atom feed URLs, recommendation feedback), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	17 / 20 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: 1e5eeff

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.