CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

telegram-mini-app

You build apps where 800M+ Telegram users already are. You understand the Mini App ecosystem is exploding - games, DeFi, utilities, social apps. You know TON blockchain and how to monetize with crypto. You design for the Telegram UX paradigm, not traditional web.

Quality

61%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/telegram-mini-app/SKILL.md

The canonical home for this skill is telegram-mini-app in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 mostly real, copy-paste-ready code across setup, wallet connection, and monetization patterns, with genuinely useful anti-patterns. However, mis-nested code fences break the examples' rendering, the Sharp Edges table references sections (including the high-severity initData validation) that are missing entirely, and there is redundant filler (duplicated role text, Capabilities list, boilerplate 'When to Use').

Suggestions

Fix the mis-nested code fences: the Patterns sections open ```javascript fences that wrap inner ```html/```jsx blocks, breaking markdown rendering; use correct top-level fences per example.

Add the missing sections the Sharp Edges table promises - especially '## Validating initData' (server-side HMAC validation of initData), the highest-severity item, plus TON Connect mobile fixes, performance, and MainButton usage.

Name the bot library in the Bot Integration example (e.g., 'telegraf') and remove the duplicated role paragraph, redundant Capabilities list, and the filler 'When to Use' section.

Split the TON Connect and Monetization patterns into reference files (e.g., references/ton-connect.md, references/monetization.md) and link them from a leaner SKILL.md overview.

DimensionReasoningScore

Conciseness

Mostly code-driven and efficient, but the role paragraph repeats the frontmatter description verbatim, the 8-item Capabilities list duplicates what the Patterns sections demonstrate, and the 'When to Use' section is empty filler ('This skill is applicable to execute the workflow or actions described in the overview.').

3 / 5

Actionability

Mostly concrete, real code (HTML setup, React hook, TON Connect, Stars invoice, referral share), but the code fences are mis-nested (outer ```javascript fences wrap ```html/```jsx blocks, breaking rendering), the Bot Integration example never names its library, and the Sharp Edges table references sections like '## Validating initData' that do not exist - the single most important security step is promised but never shown.

3 / 5

Workflow Clarity

The Patterns imply a rough sequence (setup -> connect wallet -> monetize) and each pattern has a 'When to use' line, but there are no validation checkpoints anywhere: the TON transaction and payment flows proceed with no verification steps, and the promised initData validation section (the highest-severity sharp edge) is absent.

3 / 5

Progressive Disclosure

Section headers organize the ~285-line body reasonably, but there are no bundle files: the TON Connect integration and monetization details are inlined content that belongs in separate reference files, and the Sharp Edges table's links point to non-existent sections, leaving navigation partially broken.

3 / 5

Total

12

/

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 identifies a distinct niche (Telegram Mini Apps + TON) with good natural trigger keywords, but it is written entirely in second person, leans on marketing language instead of concrete actions, and completely lacks a 'when to use' trigger clause. It reads as a persona statement rather than a capability description.

Suggestions

Rewrite in third person with concrete actions, e.g., 'Builds Telegram Mini Apps: integrates the Telegram Web App API, connects TON wallets via TON Connect, implements Stars/crypto payments, and designs mobile-first Telegram UX.'

Add an explicit trigger clause: 'Use when building Telegram Mini Apps, TON/TON Connect integrations, or in-app Telegram payments.'

Remove marketing padding ('800M+ users', 'ecosystem is exploding') that adds no trigger value.

DimensionReasoningScore

Specificity

The description names the domain (Telegram Mini Apps, TON) and 2-3 actions ('build apps', 'monetize with crypto', 'design for the Telegram UX paradigm'), but the actions are generic and framed in marketing language ('800M+ Telegram users', 'ecosystem is exploding'). The entire description is written in second person ('You build', 'You understand', 'You know', 'You design'), which the rubric penalizes by reducing the specificity score by 1.

2 / 5

Completeness

There is a discernible 'what' (build and monetize Telegram Mini Apps with TON), but the 'when' is entirely absent - no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say: 'Telegram', 'Mini App', 'TON blockchain', 'DeFi', 'crypto', 'games', 'social apps'. A few natural terms are missing (e.g., 'Telegram bot', 'Stars', 'payments', 'wallet'), keeping it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Telegram Mini Apps with TON blockchain is a clear niche with distinct triggers and minimal conflict risk; only minor overlap with the closely related telegram-bot-builder skill mentioned in the body.

4 / 5

Total

13

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/telegram-mini-app/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.