Content
57%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is strong on concrete, executable code examples across the core Telegram Mini App workflow, but is undermined by broken nested code fences, missing validation steps for destructive payment/transaction operations, and dangling cross-references in the Sharp Edges table.
Suggestions
Fix the malformed nested code fences in the Mini App Setup, TON Connect, and Monetization sections — the opening ```javascript wrappers contain markdown headers and never close before the inner blocks, breaking rendering.
Add a validation workflow for destructive operations: an initData validation code block (the Sharp Edges table flags it as high severity) and a transaction confirmation/check step before sending TON.
Resolve the dangling Sharp Edges 'Solution' references (e.g. '## Validating initData', '## TON Connect Mobile Issues') into actual sections, or split them into reference files with proper links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly code with little concept over-explanation, but it duplicates the description verbatim, carries generic filler ('Making money from Mini Apps', the placeholder 'When to Use' line), and has malformed nested code fences adding noise, matching 'mostly efficient but could be tightened'. | 3 / 5 |
Actionability | Provides concrete, mostly copy-paste-ready code across the common cases (Telegram WebApp init, useTelegram hook, bot integration, TON Connect provider/manifest, send-transaction with nanoton conversion, Telegram Stars invoice, referral share) with only minor gaps like missing useEffect/useState imports. | 4 / 5 |
Workflow Clarity | Sections are organized with 'When to use' notes, but destructive/batch operations (TON transactions, payments, Stars invoices) have no validation checkpoints, and the Sharp Edges table itself flags 'Not validating initData' as high severity without providing a validation workflow, so the destructive-operations cap applies. | 3 / 5 |
Progressive Disclosure | No bundle files exist and all content is inlined into one SKILL.md with section headers, but material that could be split out (TON Connect deep-dive, monetization, performance) is inline and the Sharp Edges 'Solution' references are dangling headers pointing nowhere, matching 'some structure but not clearly signaled'. | 3 / 5 |
Total | 13 / 20 Passed |