Name: perplexity
Rating: 61.6 (1 reviews)
Author: membranedev

perplexity

Perplexity integration. Manage data, records, and automate workflows. Use when the user wants to interact with Perplexity data.

Quality

72%

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/perplexity/SKILL.md

Quality

Content

82%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.

The content is highly actionable with executable commands and a well-sequenced connection workflow that includes validation checkpoints, losing points only for minor verbosity and slightly inconsistent step numbering.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient CLI-specific guidance Claude would not already know, with only minor over-explanation such as the opening 'Perplexity is an AI-powered search engine...' sentence that could be trimmed.	4 / 5
Actionability	It provides copy-paste-ready commands for every phase (install, login, connection ensure, action list/run, request) plus a concrete flags table for proxy requests, covering the common cases fully.	5 / 5
Workflow Clarity	The connect-to-ready flow is clearly sequenced with explicit state checks and a feedback loop (poll after CLIENT_ACTION_REQUIRED), but the 'Step 2' / '1b' numbering is slightly confusing and some checkpoints are implicit.	4 / 5
Progressive Disclosure	As a single self-contained file with no bundle, it is well organized into clearly labeled sections (install, auth, connect, search, run, proxy, best practices); only minor reorganization of the proxy flags table would improve it.	4 / 5
	Total	17 / 20 Passed

Description

62%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.

The description is functional with an explicit trigger clause and a distinct brand anchor, but its action language is generic and it lacks the natural search/answer trigger terms users would actually say.

Suggestions

Replace generic verbs ('Manage data, records, automate workflows') with concrete Perplexity capabilities such as running search queries, continuing conversations, and organizing collections.

Add natural trigger phrases users say, e.g. 'Use when the user asks Perplexity a question, wants sourced answers, or wants to search the web via Perplexity'.

Mention conversation/collection features to better distinguish this from generic data-integration skills.

Dimension	Reasoning	Score
Specificity	Names the domain (Perplexity) plus a couple of actions ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete Perplexity-specific capabilities like search or conversations.	3 / 5
Completeness	It has both a clear 'what' (manage data, records, automate workflows) and an explicit 'when' clause ('Use when the user wants to interact with Perplexity data'), though the 'when' could be more specific about search/answer use cases.	4 / 5
Trigger Term Quality	'Perplexity' is the natural keyword and 'interact with Perplexity data' is a reasonable trigger phrase, but it misses common variations users might say (search, ask Perplexity, Perplexity queries).	3 / 5
Distinctiveness Conflict Risk	The Perplexity brand name gives it a clear niche with minimal conflict risk, though the generic 'manage data, records' phrasing could overlap slightly with other data-integration skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/perplexity/SKILL.md
Commit: f484c82

Reviewed: 5 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.