perplexity-research

Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query).

Quality

74%

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-research/SKILL.md

Quality

Content

61%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 body provides concrete, actionable guidance with a clear invocation sequence and good structure, but it carries redundant conformance-test filler and lacks the validation/verification checkpoints that a mutating, cron-driven research skill should have. Conciseness is the main weakness, with workflow clarity capped by the missing feedback loops.

Suggestions

Remove the trailing 'Contract' and 'Output Format' sections that explicitly exist only for the conformance test, folding any essential guarantees into the existing body sections to cut redundancy.

Add a validation checkpoint in the invocation workflow (e.g. verify every output claim has a citation URL before calling `gbrain put`, and retry the Perplexity call on API error) to satisfy the batch/mutating-operation feedback-loop requirement.

Tighten explanatory padding like 'The key insight: Perplexity doesn't just search...' and the 'What this does' block, which restates the frontmatter description.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes padding such as "The key insight: Perplexity doesn't just search — it reads and synthesizes..." and two trailing "Contract"/"Output Format" sections that self-identify as existing only "for the conformance test", plus overlap with the frontmatter description; it could be tightened.	3 / 5
Actionability	Concrete bash commands (`gbrain get`, a real `curl` to the Perplexity API with model `sonar-pro`), an inline query template, and a cost table give mostly executable guidance, but the invocation uses commented pseudocode templates and hand-waves `gbrain put` as "via the put_page operation".	4 / 5
Workflow Clarity	The five-step invocation sequence is listed, but the skill is mutating (writes pages) and includes batch/cron patterns ("Deal / company monitoring (cron)") with no validation checkpoints or error-recovery loops (e.g. verify citations before writing, retry on API failure), so per the batch/destruction cap it cannot exceed 3.	3 / 5
Progressive Disclosure	The skill is a single well-organized file with clear section headers and one-level-deep external cross-links (`conventions/quality.md`, `conventions/brain-first.md`, sibling `skills/*/SKILL.md`); no bundle files exist so structure is appropriately self-contained, with only minor organization gaps.	4 / 5
	Total	14 / 20 Passed

Description

87%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 strong: it clearly states what the skill does, when to use it, and where it differs from neighboring tools via explicit exclusions. Trigger terms and specificity are good rather than comprehensive, leaving minor room for additional synonyms and concrete action coverage.

Dimension	Reasoning	Score
Specificity	"Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows" lists several concrete actions (send context, cited web search, return delta) plus multiple use cases, with only minor coverage gaps; not a 5 because the action set is not fully comprehensive.	4 / 5
Completeness	It explicitly answers both what ("Brain-augmented web research... searches the web with citations and returns what is NEW") and when ("Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas"), with concrete trigger phrases and explicit exclusions.	5 / 5
Trigger Term Quality	"Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas" provides good natural keyword coverage users would say, but is missing some common synonyms/variations that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Perplexity delta research) with explicit disambiguation — "NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query)" — giving minimal conflict risk with adjacent tools.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/perplexity-research/SKILL.md
Commit: 055ac6c

Reviewed: about 2 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.