slack-a2a-rooms

Agent-to-agent Slack rooms — a group DM (MPIM) holding a human plus two or more NanoClaw sibling bots, where each bot hears the room over its own Socket Mode connection. Registers the admission policy on the Slack channel's bot-inbound guard so bot-authored inbound is admitted only for rooms allowlisted in SLACK_A2A_ROOMS (re-attributed as slack:bot:<bot_id>, hop-limited via SLACK_A2A_MAX_HOPS), plus scripts/open-a2a-room.ts to open a room and register it.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/slack-a2a-rooms/SKILL.md

Quality

Content

81%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 is highly actionable with a clear, validated multi-step workflow and good structural organization; the main weakness is a verbose Notes section that mixes deferred design ideas with operational guidance.

Suggestions

Move the 'deferred' design discussions from Notes into a separate DESIGN.md (or mark them clearly as non-actionable) so operational notes stay lean.

Confirm the two missing bundle files (src/channels/slack-a2a.ts, src/channels/slack-a2a.test.ts) are actually shipped alongside SKILL.md, or note explicitly that they are generated by the apply step.

Tighten the Notes bullets that restate body content (e.g., the MPIM id prefix and bot-sender drop behavior already covered above) to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is dense and project-specific (earned, not padding about concepts Claude already knows), but the Notes section carries several 'deferred' design discussions and asides that could be trimmed to tighten the whole.	3 / 5
Actionability	Provides copy-paste-ready, executable guidance throughout — the guard grep check, nc:copy/nc:append directives, build and vitest commands, the opener script invocation, and a concrete SQL update.	5 / 5
Workflow Clarity	The Apply steps are clearly numbered with explicit validation checkpoints (verify-seam grep that stops on failure, build guarding against guard drift, end-to-end test) and a feedback loop ('re-run /add-slack … then re-apply'), and the destructive barrel edit is guarded.	5 / 5
Progressive Disclosure	Well-sectioned (Apply, Configuration, Engagement, Remove, Notes) with clear one-level-deep references to the shipped opener script (verified present in scripts/); docked one point because two referenced files (slack-a2a.ts, slack-a2a.test.ts) are not present in the bundle directories and the Notes section inlines design discussion that could live separately.	4 / 5
	Total	17 / 20 Passed

Description

67%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 is highly specific and clearly distinct, but it omits any explicit 'Use when…' trigger guidance and leans on internal jargon over natural user phrasings, which caps completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when setting up two or more NanoClaw Slack bots to converse with a human in a shared group DM (MPIM).'

Soften the jargon with at least one plain-language phrase a user would naturally say, such as 'let Slack bots talk to each other in a shared room'.

Move the deeper mechanics (Socket Mode, hop-limit env var names) after the trigger clause so the opening sentence stays scannable.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Registers the admission policy on the Slack channel's bot-inbound guard', admits only rooms 'allowlisted in SLACK_A2A_ROOMS', 're-attributed as slack:bot:<bot_id>', 'hop-limited via SLACK_A2A_MAX_HOPS', plus the opener script — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when…' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Has some natural terms ('Slack', 'group DM (MPIM)', 'sibling bots', 'agent-to-agent') but leans heavily on project jargon (Socket Mode, bot-inbound guard, env-var names) and omits common user phrasings like 'make Slack bots talk to each other'.	3 / 5
Distinctiveness Conflict Risk	Targets a very specific niche (NanoClaw agent-to-agent Slack rooms via MPIM with sibling bots) with distinct triggers, making conflict with other skills minimal.	5 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/slack-a2a-rooms/SKILL.md
Commit: 7902716

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.