polymarket

Query Polymarket: markets, prices, orderbooks, history.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/research/polymarket/SKILL.md

Quality

Content

50%

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

The body is well-organized and dense with useful Polymarket-specific API knowledge, but it stops short of excellence by omitting executable in-body examples, validation steps, and any reference to the bundled script.

Suggestions

Reference scripts/polymarket.py from the body so Claude knows the helper exists and how to invoke it, closing the progressive-disclosure gap.

Add at least one complete, copy-paste query example (e.g., a curl call to the Gamma public-search endpoint) in the body rather than deferring all examples to the reference file.

Add a brief validation/error-handling note in the workflow for common failure cases (empty price history, missing clobTokenIds) to reach level-3 workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and packed with API-specific detail Claude would not know (hostnames, field encodings, rate limits), but includes minor redundancy such as "Prices ARE probabilities: price 0.65 means the market thinks 65% likely" and "Volume is in USDC (US dollars)" that could be trimmed.	2 / 3
Actionability	Concrete field names, API hosts, and a one-line parsing snippet ("json.loads(market['outcomePrices'])") are present, but the body lacks complete copy-paste executable query examples (curl/Python queries are deferred to the reference file) and the existing scripts/polymarket.py is never invoked.	2 / 3
Workflow Clarity	The Typical Workflow gives a clear sequence (Search, Parse, Present, Deep dive), but there are no explicit validation checkpoints or error-handling guidance (e.g., what to do when a market has no clobTokenIds or empty price history), which the level-3 anchor requires.	2 / 3
Progressive Disclosure	SKILL.md is a well-structured overview that clearly signals the one-level-deep references/api-endpoints.md reference, but the bundled scripts/polymarket.py is never referenced from the body, leaving a navigation gap for an existing resource.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 specific to a distinct platform and enumerates concrete data targets, but it omits an explicit "Use when..." trigger clause and lacks broader natural keyword variations, leaving it solid but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about Polymarket, prediction markets, betting odds, or event probabilities."

Broaden trigger terms to include natural phrasings like "prediction markets", "odds", and "betting" that users actually say.

Consider expanding the single verb into distinct actions (e.g. "Search markets, fetch live prices, read orderbooks, and pull price history") to reach level-3 specificity.

Dimension	Reasoning	Score
Specificity	"Query Polymarket: markets, prices, orderbooks, history" names a concrete platform and several specific data targets, but relies on a single action verb ("Query"), so it enumerates the domain rather than listing multiple distinct concrete actions as the level-3 anchor requires.	2 / 3
Completeness	The description clearly answers "what" (query Polymarket for markets/prices/orderbooks/history) but has no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	"Polymarket", "markets", "prices", and "orderbooks" are natural terms a user would say, but common variations such as "prediction markets", "betting odds", "odds", and "probabilities" are missing, so coverage is partial rather than the broad level-3 set.	2 / 3
Distinctiveness Conflict Risk	Naming a single specific platform ("Polymarket") creates a clear niche with distinct triggers that is unlikely to conflict with other skills, matching the level-3 anchor for a distinct, named domain.	3 / 3
	Total	9 / 12 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: NousResearch/hermes-agent
Path: skills/research/polymarket/SKILL.md
Commit: 74a56b7

Reviewed: 1 day 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.