CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

trading-polymarket

Execute trades on Polymarket using py_clob_client - full API access for market data, orders, positions

52

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./src/skills/bundled/trading-polymarket/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 delivers highly actionable, executable Polymarket trading code, but it is a monolithic ~1080-line reference that duplicates its own method catalog and inlines everything that should live in separate reference files. Workflow guidance lacks explicit validation checkpoints for real-money operations, and token efficiency suffers badly from the double documentation.

Suggestions

Split the method reference tables, WebSocket guide, and on-chain helpers into references/ files (e.g., references/methods.md, references/websockets.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

Remove the duplication between the prose API sections and the "Complete ClobClient Method Reference" tables — keep one canonical form.

Add explicit pre-trade validation steps and fix-and-retry loops (e.g., check balance/allowance → calculate_market_price → post → verify fill status) to the trading workflow, since orders move real money.

DimensionReasoningScore

Conciseness

The ~1080-line body documents the entire 60+-method API twice — once in prose/code sections and again in the "Complete ClobClient Method Reference" tables — plus exhaustive WebSocket and on-chain sections, which is noticeably verbose with substantial duplicated padding. It avoids anchor 1 only because it does not explain concepts Claude already knows; it stays at 2 rather than 3 because the duplication is a major, systematic token waste rather than minor tightening.

2 / 5

Actionability

Nearly all code is concrete and copy-paste executable (client initialization, order placement, cancels, WebSocket auth, eth_call balance checks), matching anchor 4. It falls short of 5 due to minor gaps, e.g., in "Create and Post Orders" the block `result = client.create_market_order(...)` never posts the signed order, so copying it silently places nothing.

4 / 5

Workflow Clarity

The "Complete Trading Example" provides a rough sequence (check position → fetch book → place order) and an error-handling section lists common errors, but there are no explicit pre-trade validation checkpoints or fix-and-retry feedback loops. Since this skill places real-money orders and includes destructive/batch operations (`cancel_all`, market orders), the missing-validation guideline caps workflow clarity at 3.

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the full method catalog, WebSocket guide, and contract tables are all inlined in SKILL.md — content that clearly belongs in separate files. Section headers exist (so not anchor 1), but with no references at all and hundreds of lines of inline API reference, this matches anchor 2 rather than 3.

2 / 5

Total

11

/

20

Passed

Description

70%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 specific, distinctive, and names a clear niche with several concrete capabilities, but it entirely lacks a "when to use" trigger clause, capping its completeness. Adding an explicit trigger sentence (e.g., "Use when the user wants to trade on Polymarket, place prediction-market orders, or check positions") would raise it substantially.

Suggestions

Add an explicit trigger clause such as "Use when the user wants to trade on Polymarket, buy or sell prediction-market shares, or check positions and orderbooks."

Include natural synonyms like "prediction markets" and "buy/sell shares" so the description matches how users phrase trading requests.

Mention additional key capabilities (cancel orders, wallet balances, auto-redeem) to round out the 'what' coverage.

DimensionReasoningScore

Specificity

"Execute trades", "market data, orders, positions" list several concrete actions in the Polymarket domain, matching anchor 4; it is not 5 because coverage has gaps (no cancel, wallet, or redeem capabilities) and not 3 because it goes beyond 1-2 actions.

4 / 5

Completeness

The "what" is clear ("Execute trades on Polymarket using py_clob_client - full API access for market data, orders, positions") but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"Polymarket", "trades", "orders", "positions", "market data" are terms users would naturally say, matching anchor 4's good coverage; it is not 5 because common synonyms like "prediction markets", "buy/sell shares", or "place a bet" are missing.

4 / 5

Distinctiveness Conflict Risk

"Polymarket using py_clob_client" names a clear niche with distinct triggers and minimal conflict risk with any other plausible skill, matching anchor 5 exactly.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1081 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

alsk1992/CloddsBot

Path

src/skills/bundled/trading-polymarket/SKILL.md

Reviewed

Table of Contents

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.