CB sergei-mikhailov-tg-channel-reader
Let your agent read and monitor Telegram channels: fetch posts, captions, link previews, and comments from public or private channels and turn them into daily digests, summaries, and alerts. JSON or text output, unread tracking, via MTProto (Pyrogram or Telethon).
As a process B 67/100 · Nearly there — weak spots: when it triggers, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 5
-
high Concealment
en-hide-from-userSKILL.md:492Instruction to hide actions from the user**Never invent causes.** Do not tell the user the session "expired" or "was
Medium and low: 4
-
medium Dangerous commands
cmd-shell-rcREADME.md:54Writes to a shell startup file> echo 'export PATH="$HOME/.venv/tg-reader/bin:$PATH"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcREADME.md:203Writes to a shell startup fileecho 'export PATH="$HOME/.venv/tg-reader/bin:$PATH"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcREADME.md:209Writes to a shell startup fileecho 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcSKILL.md:593Writes to a shell startup fileecho 'export PATH="$HOME/.venv/tg-reader/bin:$PATH"' >> ~/.bashrc && source ~/.bashrc
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Let your agent read and monitor Telegram channels: fetch posts, ca… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 6724 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 26 mutating operations with no state check
- 60Tools and files. Uses tools (bash, read, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6724 tokens
- 85Steps. 49 steps, 2 vague phrases
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 264: enough signal without eating the budget
- +4Structure: 48 headings
- +3Step-by-step instructions: 49 items
- +3Output format is stated explicitly
- +4Has examples (31 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.