add-telegram-swarm

Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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-sequenced implementation skill with copy-paste code, explicit validation, and rollback instructions. Its main weakness is structure: everything lives inline in one long file with no progressive disclosure, and the formatting rules are duplicated.

Suggestions

Move the large Agent Teams CLAUDE.md template (Step 5c) and possibly the full pool-implementation code into reference files (e.g. references/agent-teams-claude.md), keeping SKILL.md an overview with clearly signaled one-level-deep links.

Deduplicate the WhatsApp/Telegram formatting rules: state them once (Step 5a) and reference that block from the Agent Teams instructions instead of repeating them verbatim.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable code, exact file paths, and commands with almost no explanation of concepts Claude already knows; however the WhatsApp/Telegram formatting rules are duplicated verbatim (Step 5a and Step 5c item 5) and a few prose spots could be trimmed.	4 / 5
Actionability	Fully executable throughout: copy-paste TypeScript for the pool functions, exact zod schema diffs, exact env/build/restart commands, verbatim user-facing scripts, and concrete log-grep verification commands.	5 / 5
Workflow Clarity	Eight clearly sequenced steps with an explicit wait-for-user checkpoint for tokens, an end-to-end test step with expected outcomes, a troubleshooting section providing diagnostic feedback loops, and a removal rollback section.	5 / 5
Progressive Disclosure	No bundle files exist and the entire skill is one ~380-line SKILL.md. Section headers are clear, but large blocks that could live in reference files (the ~60-line Agent Teams CLAUDE.md template, full implementation code) are fully inlined with no overview-to-detail split.	3 / 5
	Total	17 / 20 Passed

Description

82%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: it states what the skill does concretely, explicitly declares trigger phrases, and cleanly separates itself from the base Telegram setup skill. The only weakness is modest specificity — it describes the outcome but not the several concrete actions involved (bot pool, renaming, IPC routing).

Dimension	Reasoning	Score
Specificity	Names the domain ('Add Agent Swarm (Teams) support to Telegram') and one concrete capability ('Each subagent gets its own bot identity in the group'), but lists only 1-2 actions rather than several specific ones, matching the 'not comprehensive' anchor.	3 / 5
Completeness	Explicitly answers both 'what' (add swarm support, per-subagent bot identities) and 'when' via an explicit 'Triggers on ...' clause with four concrete trigger phrases plus a stated prerequisite (/add-telegram), fully matching the top anchor.	5 / 5
Trigger Term Quality	'agent swarm', 'agent teams telegram', 'telegram swarm', and 'bot pool' give good synonym coverage of the core concept, but natural phrasings users might say (e.g. 'separate bot per agent', 'multiple telegram bots') are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Telegram agent swarm) with distinct trigger terms; the prerequisite note explicitly distinguishes it from the base /add-telegram skill, so conflict risk is minimal.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: jbaruch/nanoclaw-telegram
Path: .claude/skills/add-telegram-swarm/SKILL.md
Commit: 7454673

Reviewed: 17 hours ago

Table of Contents

Discovery Implementation Validation

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.