CtrlK
BlogDocsLog inGet started
Tessl Logo

get-prediction-markets

Retrieve active prediction-market contracts (Polymarket) with live yes-price probabilities, volume, and close dates, filterable by category or keyword. Use when the user asks what the market odds are on a geopolitical, economic, or election outcome.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An exemplary single-purpose API skill body: fully executable example with auth, a params table, a real response shape, explicit error and degradation handling, a content-safety note, and clear "when NOT to use" disambiguation — all with essentially zero padding. The only structural question is that at ~81 lines it could trim or split sample/edge-case detail, keeping it just below the top progressive-disclosure anchor.

Suggestions

Tighten the body toward the ~50-line simple-skill threshold (e.g. compress the sample response to the fields the jq projection uses) to earn full marks on structure alone.

Optionally split the auth details (key issuance URL, header vs. bearer distinction) into a short referenced section so the main flow is endpoint-first.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout — auth header format, endpoint, params table, a compact response example, one curl example, and terse error/degradation notes, with no explanation of concepts Claude already knows (no "what is an API/REST" padding). Matches anchor 5 ("every token earns its place"); anchor 4 would require visible over-explanation to trim, which is absent.

5 / 5

Actionability

The worked example is fully executable and copy-paste ready — a complete curl with the required X-WorldMonitor-Key header, URL-encoded query param, and a jq projection — alongside a concrete endpoint URL, params table, and a real response sample. Matches anchor 5 ("copy-paste ready... covers the common cases"); there is no pseudocode or missing key detail that would drop it to 4.

5 / 5

Workflow Clarity

This is a simple single-purpose skill whose single action is unambiguous (authenticated GET, then project the markets array), and it includes explicit checkpoints: error handling for 401 and 429 ("retry with backoff") and a degradation contract distinguishing "no data" from "no active markets". Under the rubric's simple-skill guidance this matches anchor 5; the operation is read-only, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

Sections are well organized (Authentication, Endpoint, Parameters, Response shape, Worked example, Errors, When NOT to use, References) with clearly signaled one-level-deep external references (OpenAPI operation, auth matrix), and nothing is buried or nested. However, the body runs ~81 lines — above the under-50-line simple-skill threshold that would let well-organized sections alone earn a 5 — so this sits at anchor 4 ("good structure; minor organization gaps") rather than 5.

4 / 5

Total

19

/

20

Passed

Description

92%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.

A strong description: concrete, comprehensive statement of what is returned (yes-price probabilities, volume, close dates, filtering) paired with an explicit third-person "Use when..." trigger clause grounded in natural user phrasing. Its only weakness is trigger synonym coverage — it misses everyday variants like "betting odds" or "chances of" that users might say.

Suggestions

Broaden the trigger clause with common synonyms, e.g. "Use when the user asks about market odds, betting odds, or the implied probability/chances of a geopolitical, economic, or election outcome."

Consider mentioning related-but-distinct capabilities in the description (e.g. pointing to forecasts) to further reduce overlap risk with sibling skills.

DimensionReasoningScore

Specificity

"Retrieve active prediction-market contracts (Polymarket) with live yes-price probabilities, volume, and close dates, filterable by category or keyword" lists multiple concrete actions with comprehensive field-level coverage of what is returned. Anchor 5 fits; score 4 would require identifiable coverage gaps, and none are present.

5 / 5

Completeness

It explicitly answers both questions: the "what" (retrieve contracts with yes-price probabilities, volume, close dates, category/keyword filtering) and the "when" ("Use when the user asks what the market odds are on a geopolitical, economic, or election outcome") with a concrete trigger phrase. This matches anchor 5; anchor 4 would require a less explicit "when" clause.

5 / 5

Trigger Term Quality

Natural phrases like "what the market odds are", "geopolitical, economic, or election outcome", and the named source "Polymarket" give good keyword coverage, but common user synonyms such as "betting odds", "chances of X", or "probability of" are missing. This matches anchor 4 ("a few natural terms missing") rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"Prediction-market contracts (Polymarket)" with "market odds" triggers carves out a clear, distinct niche unlikely to fire for adjacent skills (e.g. model-generated forecasts). Matches anchor 5 ("clear niche with distinct triggers; minimal conflict risk"); it is not merely "mostly distinct" as in anchor 4.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
koala73/worldmonitor
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.