CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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:<botId>, hop-limited via SLACK_A2A_MAX_HOPS), plus scripts/open-a2a-room.ts to open a room and register it.

Quality

80%

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

Fix and improve this skill with Tessl

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

Quality

Content

77%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.

This is a strong, unusually rigorous skill body: every apply step is executable with real commands, validation is built in before any file is touched, and the Notes section documents genuine edge cases rather than padding. The two real weaknesses are the missing bundle files referenced by the copy step and a couple of trimmable sections that dilute token efficiency.

Suggestions

Ship `src/channels/slack-a2a.ts` and `src/channels/slack-a2a.test.ts` in the skill bundle (or fix the `nc:copy` block and file descriptions to match what is actually shipped) — as bundled, step 2 of Apply cannot succeed.

Trim or relocate low-action content: the "Canonical home" branch-mirroring paragraph and the deferred-nicety Notes entries ("Attribution name", "MPIM id prefix") could move to a reference file or be cut.

Consider moving the Engagement and Notes sections' rationale detail into a single `references/` file with one-line pointers, keeping SKILL.md as an overview plus the Apply/Configuration/Remove steps.

DimensionReasoningScore

Conciseness

The body is dense with non-derivable, project-specific knowledge (the guard seam, MPIM event semantics, hop-counter scope, cross-host caveats) and does not explain concepts Claude already knows. Minor trimmable sections — "Canonical home" branching policy and some deferred-nicety Notes entries ("Attribution name", "MPIM id prefix") — keep it below the lean 5 anchor.

4 / 5

Actionability

Commands are concrete and copy-paste ready throughout: the `grep -sq 'export function setBotInboundPolicy'` precheck, `nc:copy`/`nc:append` blocks, `pnpm run build`, `pnpm exec vitest run src/channels/slack-a2a.test.ts`, and the `tsx scripts/open-a2a-room.ts --instances dana,eli --user U0AAAAAAA` example with the SQL update. Not 5 because step 2's `nc:copy` ships "three files" but the bundle contains only `scripts/open-a2a-room.ts` — `src/channels/slack-a2a.ts` and `slack-a2a.test.ts` are absent, so that step is not executable as bundled.

4 / 5

Workflow Clarity

The Apply section is a clearly numbered 4-step sequence with an explicit verify-first checkpoint (step 1), a stop-on-fail instruction with recovery guidance ("If the check fails, **stop**: re-run /add-slack... then re-apply this skill"), and build-plus-test validation that pins the policy's behavior end-to-end; Remove is likewise numbered and complete. This matches the 5 anchor's explicit validation steps and error-recovery feedback loop.

5 / 5

Progressive Disclosure

Section organization is good and references are one level deep (the `slack-multi-instance` skill, the guard module, the opener script — which does exist and matches its documented flags), but the actual bundle structure contradicts the body: `nc:copy` and the file descriptions reference `src/channels/slack-a2a.ts` and `src/channels/slack-a2a.test.ts`, neither of which is present in the bundle. Scoring against the real file listing per the rubric guideline, dangling referenced paths are more than the 4 anchor's "minor organization gaps".

3 / 5

Total

16

/

20

Passed

Description

75%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 exceptionally specific and distinctive, naming exact mechanisms, env vars, and file paths with no fluff. Its single material weakness is the missing "Use when..." trigger clause, which caps completeness and leaves natural trigger phrasings underrepresented.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up bot-to-bot Slack conversations, opening multi-bot group DMs, or letting sibling bots chat in allowlisted rooms."

Include a few natural user phrasings ("make bots talk to each other", "bot-to-bot chat", "multi-party DM") alongside the technical terms to improve trigger_term_quality.

Keep the env-var and re-attribution detail, but consider moving deep implementation specifics (e.g. hop-limit internals) after the trigger clause so the opening sentence leads with what the user would say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with exact identifiers: "Registers the admission policy on the Slack channel's bot-inbound guard", "admitted only for rooms allowlisted in SLACK_A2A_ROOMS", "re-attributed as slack:bot:<botId>, hop-limited via SLACK_A2A_MAX_HOPS", plus "scripts/open-a2a-room.ts to open a room and register it". No vague language; coverage of the skill's actions is comprehensive, matching the 5 anchor rather than 4's 'minor gaps'.

5 / 5

Completeness

The "what" is clear and detailed (admission policy registration, re-attribution, hop limiting, room opener), but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline. Not 4 because the "when" is entirely absent rather than merely implicit-but-present.

3 / 5

Trigger Term Quality

Includes natural terms a user would say — "Slack rooms", "group DM (MPIM)", "agent-to-agent", "bots" — but misses common phrasings like "make bots talk to each other" or "bot conversation/chat". Good keyword coverage with a few natural synonyms missing, so 4 rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Highly niche: "NanoClaw sibling bots", "SLACK_A2A_ROOMS", the Slack bot-inbound guard seam, and hop-limiting via SLACK_A2A_MAX_HOPS create a clear trigger footprint with minimal overlap risk against generic Slack or messaging skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

nanocoai/nanoclaw

Path

.claude/skills/slack-a2a-rooms/SKILL.md

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.