polymarket

Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.

Quality

63%

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 ./configs/microservice/bff-service/configs/agent-skills/clawhub/polymarket-trade/SKILL.md

Quality

Content

71%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 is highly actionable with copy-paste-ready commands and sensible cron examples, but it leans repetitive across Quick Start, setup, and Commands sections, and its progressive disclosure is middling: a large inlined command catalogue with weak signaling of the bundled script. Paper-trading/batch operations lack explicit validation checkpoints, capping workflow clarity just below 5.

Suggestions

De-duplicate commands that appear across Quick Start, 'After Install', and Commands sections to tighten token usage.

Move the full per-subcommand flag catalogue into a references file and keep SKILL.md as a concise overview with a clear pointer, improving progressive disclosure.

Add a brief validation/verification step for paper-trading and watchlist-alert flows (e.g. run `portfolio` after `buy` to confirm, or `watch list` to confirm an alert was added).

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient and command-driven, but the Quick Start, 'After Install' setup, and Commands sections repeat many of the same invocations (e.g. trending/movers/calendar appear multiple times), and the API/Output Features sections restate facts Claude can infer, so it could be tightened.	3 / 5
Actionability	Nearly every command is a fully executable `python3 {baseDir}/scripts/polymarket.py ...` invocation with concrete arguments and flags covering the common cases (trending, search, watch, calendar, movers, digest, buy/sell/portfolio).	5 / 5
Workflow Clarity	Multi-step flows like watchlist setup and cron scheduling are clearly sequenced with concrete commands and example cron lines; minor gap is that batch/destructive-ish operations (buy/sell, digest) lack explicit validation or verification checkpoints, though they are low-risk paper operations.	4 / 5
Progressive Disclosure	Structure is present with organized sections (Quick Start, Commands, Cron, API) and the bulk of logic lives in scripts/polymarket.py, but the body inlines a large command catalogue that could be a reference file, references are only implied (scripts/polymarket.py mentioned once in Security), and there is no clear navigation/signaling to the script's subcommands.	3 / 5
	Total	15 / 20 Passed

Description

56%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 clear and reasonably specific about market-query capabilities but lacks an explicit 'Use when...' trigger clause, capping completeness at 3. Coverage also understates the skill (no watchlist, alerts, calendar, or paper trading mentioned).

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about prediction-market odds, trending Polymarket events, or price movements.'

Broaden coverage to reflect actual capabilities: mention watchlists/alerts, resolution calendar, and paper trading.

Include common synonyms ('prediction markets', 'betting odds', 'probabilities') to improve natural trigger matching.

Dimension	Reasoning	Score
Specificity	Phrases like 'Check odds', 'find trending markets', 'search events', 'track price movements' name the domain plus several concrete actions, but coverage is generic verbs over a single surface (e.g. no mention of watchlists, alerts, calendar, or paper trading that the skill actually supports).	3 / 5
Completeness	It clearly answers 'what' (query markets, check odds, etc.) but has no explicit 'Use when...' or 'when should Claude use it' clause, which the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms users would say are present ('odds', 'trending markets', 'search events', 'price movements'), giving good keyword coverage, though common synonyms like 'prediction markets', 'betting', or 'probability' beyond the brand are thin.	4 / 5
Distinctiveness Conflict Risk	The Polymarket domain and concrete market-data actions make it mostly distinct with only minor overlap risk against generic finance/news skills; not a full 5 because the verbs ('find', 'search', 'track') are somewhat common.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/polymarket-trade/SKILL.md
Commit: 030c20b

Reviewed: 9 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.