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

80%

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

82%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-structured integration skill with copy-paste code, a clear step sequence, and end-to-end test/troubleshooting coverage. Its main gaps are the absence of mid-flow validation checkpoints before destructive rebuild/restart steps and no progressive disclosure via bundle reference files.

Suggestions

Add an explicit validation checkpoint before the destructive Step 7 rebuild/restart (e.g., typecheck or verify pool-bot tokens via getMe) and gate the restart on its success, raising workflow_clarity toward 5.

Move the long Agent Teams CLAUDE.md template block (Step 5c) into a references/ file and link to it from the body, demonstrating one-level-deep progressive disclosure.

Collapse the "How It Works" ASCII flow and "Architecture Notes" into a single section to trim the minor redundancy and push conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The ~380 lines are proportionate to an 8-step, 6-file integration with concrete code and minimal concept explanation, though the "How It Works" ASCII flow and "Architecture Notes" overlap slightly, keeping it just below the lean anchor 5.	4 / 5
Actionability	Every step ships copy-paste-ready TypeScript with exact file paths (src/telegram.ts, container/agent-runner/src/ipc-mcp-stdio.ts) and executable commands (npm run build, ./container/build.sh, launchctl unload/load), fully matching the executable anchor 5.	5 / 5
Workflow Clarity	A clearly numbered 8-step sequence with a terminal Test step and a Troubleshooting feedback loop, but validation lives only at the end rather than as mid-flow checkpoints before the destructive rebuild/restart, so it falls short of the gated anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is a single well-sectioned file (How It Works, Prerequisites, Steps 1-8, Architecture Notes, Troubleshooting, Removal) with content appropriately placed inline; it is well organized but lacks the one-level-deep external references that would reach anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

78%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, third-person description that answers both what and when with concrete trigger phrases and a useful prerequisite. It is slightly under-specific on the actual mechanics and carries minor overlap risk with the base Telegram skill.

Dimension	Reasoning	Score
Specificity	"Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group" names the domain plus 1-2 concrete actions but omits the richer mechanics (pool bots, renaming, IPC routing), matching anchor 3 rather than the multi-action anchor 4.	3 / 5
Completeness	It clearly states what the skill does and gives an explicit "when" via concrete trigger phrases ("Triggers on ..."), plus a prerequisite, squarely matching the anchor 5 example that answers both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Lists four explicit trigger phrases ("agent swarm", "agent teams telegram", "telegram swarm", "bot pool") with good synonym coverage, but "bot pool" is more technical than user-natural and common phrasings like "multiple bots" are absent, so it sits below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	"Agent Swarm (Teams) support to Telegram" is a clear niche with distinct triggers, but it sits adjacent to the base /add-telegram skill (explicitly a prerequisite), leaving minor overlap risk rather than the minimal risk of anchor 5.	4 / 5
	Total	16 / 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: 1 day 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.