CtrlK
BlogDocsLog inGet started
Tessl Logo

telegram-reader

Read Telegram channels and groups for financial news and market research with the tdl CLI: list chats and channels, find a channel by name, and export recent messages or a date or ID range. Use this skill whenever the user wants to check their Telegram, see what's new in their channels, read or export messages from a news, crypto, or trading channel or group, or gather market news and signals posted on Telegram. Read-only: it cannot send messages or join or leave channels.

76

Quality

95%

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

88%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 well-structured, highly actionable skill body: correct command sequences, explicit auth/install checkpoints, error-recovery diagnostics, and a clearly signaled one-level reference. The main weaknesses are mild verbosity (duplicated login details, filler notes, non-executable status blocks) and content in the overview that belongs in the reference file.

Suggestions

Move the full login-methods detail (QR/phone/desktop, namespaces) into references/commands.md and keep only a pointer plus the 'interactive only, never handle credentials programmatically' rule in the body — the reference already documents this.

Trim the obvious filler notes ('Login is a one-time operation', 'check their internet connection and try again') and replace the non-executable `!`(...)` status blocks with a plain instruction to run `tdl version` and `tdl chat ls --limit 1`.

Reduce the 7-row platform install table to the default (Homebrew on macOS, install script with sudo confirmation on Linux) and point to commands.md for the remaining platform variants.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands, tables, and code with almost no concept explanation, but includes trimmable filler ('Login is a **one-time** operation', 'ask the user to check their internet connection and try again') and non-executable `!`(...)` status blocks that read as noise. Efficient overall — not the lean 'every token earns its place' level.

4 / 5

Actionability

Fully executable, copy-paste-ready tdl commands throughout — 'tdl chat export -c @channel_name -T last -i 20 --all --with-content -o /tmp/tdl-export.json' — plus concrete flag tables, chat identifier formats, and worked examples covering every common read case.

5 / 5

Workflow Clarity

Steps 1–6 are clearly sequenced (install check → auth check → identify need → execute → present → diagnostics) with explicit validation checkpoints ('TDL_NOT_INSTALLED', 'AUTH_OK', rule 'Check auth first') and an error→fix diagnostics table (FLOOD_WAIT_X → wait and retry) providing feedback loops for error recovery.

5 / 5

Progressive Disclosure

The bundle reference (references/commands.md) is one level deep and clearly signaled ('Read the reference file when you need exact command syntax'), and the body is well sectioned. However, the login methods and namespaces sections duplicate content in commands.md, and the 7-platform install table is reference material inlined in the overview — minor organization gaps rather than a clean split.

4 / 5

Total

18

/

20

Passed

Description

100%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 capabilities, explicit 'Use this skill whenever...' trigger guidance with natural user phrasings, a clearly bounded read-only scope, and distinct Telegram-specific triggers. Concise despite covering what, when, and boundaries.

DimensionReasoningScore

Specificity

The description names the domain ('Read Telegram channels and groups for financial news and market research with the tdl CLI') and lists multiple concrete actions — 'list chats and channels, find a channel by name, and export recent messages or a date or ID range' — giving comprehensive coverage of the skill's read operations.

5 / 5

Completeness

Both questions are answered explicitly: the what is the concrete action list, and the when is 'Use this skill whenever the user wants to check their Telegram...' with concrete trigger phrases. It also adds a scope boundary ('Read-only: it cannot send messages or join or leave channels').

5 / 5

Trigger Term Quality

It covers the natural phrases a user would actually say: 'check their Telegram', 'see what's new in their channels', 'read or export messages from a news, crypto, or trading channel or group', and 'gather market news and signals posted on Telegram' — including synonym variations across the niche.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (reading Telegram via tdl for financial research) with distinct triggers, and the explicit read-only boundary further separates it from messaging or channel-management skills — minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
himself65/finance-skills
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.