CtrlK
BlogDocsLog inGet started
Tessl Logo

predexon

Use this skill — NOT browser or web_fetch — for ALL Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow, UMA oracle, and prediction market data. Provides structured API at localhost:8402/v1/pm/* for markets, cross-venue search, leaderboard, smart money, wallet analytics, wallet identity & clustering, UMA resolution status, and odds.

66

Quality

81%

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

78%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.

A highly actionable, well-structured API reference with concrete endpoints, params, response schemas, and example interaction sequences. Its weaknesses are minor redundancy in the header/notes and a monolithic single-file structure with the large endpoint table inlined rather than split into a reference file.

Suggestions

Remove the duplicated payment note and repeated venue list (the header and Notes section both state 'Payment is automatic — deducted from the user's BlockRun wallet'), and drop the bolded IMPORTANT that restates the frontmatter routing directive.

Split the 57-endpoint 'Full Endpoint Reference' table into a separate reference file (e.g. ENDPOINTS.md) and link to it from the body, keeping only the most common endpoints inline to improve progressive disclosure.

Add a short explicit validation/error-recovery loop for the multi-call workflows (e.g. 'If search returns no conditionId, fall back to per-venue endpoints') to lift workflow clarity from sequenced to checkpointed.

DimensionReasoningScore

Conciseness

Dense, reference-style content with no padding of concepts Claude already knows, but minor redundancy exists (venue list and payment note repeated, bolded IMPORTANT restates the frontmatter directive).

4 / 5

Actionability

Copy-paste-ready endpoints with full params and response-field schemas, plus an Example Interactions section mapping user questions to exact multi-call sequences (e.g. search for conditionId, then smart-money), matching the anchor-5 pattern.

5 / 5

Workflow Clarity

Multi-step workflows are explicitly sequenced (find conditionId first, then call smart-money; use cross-venue search before venue-specific endpoints) with error-recovery notes (retry once on 502, payment-failure handling), but there are no formal validation checkpoints or checklists.

4 / 5

Progressive Disclosure

Well-organized with clear section headers, but it is a single monolithic ~315-line file with the full 57-endpoint reference table inlined and no external reference files, fitting the anchor where bulk content that could be split remains inline.

3 / 5

Total

16

/

20

Passed

Description

83%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, specific description that names concrete capabilities and an explicit usage/routing trigger, with clear distinctiveness from browser tools. Its main weakness is relying on platform names over natural user-language trigger phrases, leaving trigger term quality and completeness just short of full marks.

DimensionReasoningScore

Specificity

Lists multiple specific concrete capabilities (markets, cross-venue search, leaderboard, smart money, wallet analytics, wallet identity & clustering, UMA resolution status, odds) with comprehensive coverage, matching the anchor-5 example.

5 / 5

Completeness

Explicitly answers 'what' (structured API capabilities) and 'when' (Use this skill for ALL ... prediction market data, NOT browser/web_fetch), but the trigger guidance is a tool-routing directive rather than concrete paraphrased user trigger phrases.

4 / 5

Trigger Term Quality

Strong keyword coverage via named venues (Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow, UMA oracle), but it leans on platform names rather than the broader natural-language synonyms and user utterances anchor 5 expects.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (prediction market data via structured API) and actively disambiguates from browser/web_fetch, giving it distinct triggers with minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
BlockRunAI/ClawRouter
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.