slack-construct-agents

Standing context for Slack sibling agents — one room per team, creator-posted introductions, bot-to-bot hop discipline. Ships as instructions.md composed into the group's CLAUDE.md at spawn; there is no workflow to invoke.

Quality

55%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/slack-agent-flow/container/skills/slack-construct-agents/SKILL.md

Quality

Content

60%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 a concise, well-intentioned overview for a standing-context carrier, but its sole referenced payload (instructions.md) is absent from the bundle, which hollows out both actionability and progressive disclosure. Shipping the missing instructions.md (or inlining its rules) is the single highest-leverage fix.

Suggestions

Add the missing instructions.md to the bundle (references/ or the skill directory) so the one signaled reference resolves; this most directly lifts progressive_disclosure and actionability.

Trim the provenance/meta sentences ("ships separately...", "arrives with the slack-agent-flow skill") to move conciseness toward 5.

If instructions.md is intentionally absent in this distribution, inline the core sibling-agent rules (room shape, who posts introductions, the hop self-limit) so the skill is self-contained and actionable.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining concepts Claude already knows, but it spends some tokens on provenance/meta ("ships separately with the Slack channel payload", "arrives with the slack-agent-flow skill") that could be trimmed, fitting score-4 rather than the fully-lean score-5.	4 / 5
Actionability	As an instruction-only carrier it gives some concrete guidance ("payload is instructions.md", "there is nothing further to load or run here"), but the actual rules it points to are not present in the bundle, leaving the concrete executable substance incomplete and matching the score-3 anchor.	3 / 5
Workflow Clarity	By design there is no multi-step workflow, and the single non-action (rules already composed into standing instructions; nothing to run) is stated unambiguously, so the simple-skill exception applies; it is score-4 rather than 5 because effort goes to clarifying provenance instead of crisply stating the one governing rule.	4 / 5
Progressive Disclosure	The body points to a one-level-deep payload ("instructions.md in this directory") but that file does not exist in the references/scripts/assets bundle, so the single signaled reference is a broken pointer; scoring against the actual bundle structure fits score-2 (minimal structure, reference effectively missing) rather than score-3 where at least a real reference exists.	2 / 5
	Total	13 / 20 Passed

Description

51%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 concretely identifies a narrow niche and several specific behaviors, but it is written in construct-internal jargon with no "Use when..." trigger guidance, so a user is unlikely to naturally invoke it. Adding a natural-language trigger clause would raise both completeness and trigger-term quality.

Suggestions

Add an explicit "Use when..." trigger clause (e.g., "Use when a Slack group shares space with sibling agents and needs room/introduction/hop discipline") to lift completeness above 3.

Replace or supplement jargon ("bot-to-bot hop discipline") with natural user-facing terms and synonyms so trigger_term_quality improves.

Include the concrete file extension or payload name as a keyword (e.g., "instructions.md", "CLAUDE.md compose") to broaden discoverable trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete behaviors — "one room per team", "creator-posted introductions", "bot-to-bot hop discipline", "composed into the group's CLAUDE.md at spawn" — giving multiple specific actions with only minor coverage gaps, fitting the score-4 anchor rather than the comprehensive score-5.	4 / 5
Completeness	It clearly states the "what" (standing context carrier for sibling-agent rules) but provides no "when"/trigger guidance at all, which per the guidelines caps completeness at 3; it is not the score-4 level because there is no explicit (even weak) "when" clause.	3 / 5
Trigger Term Quality	The terms present ("sibling agents", "bot-to-bot hop discipline", "instructions.md") are construct-internal jargon rather than the natural phrases a user would say; no "Use when..." trigger or synonyms/extensions appear, matching the score-2 anchor of one or two generic keywords missing natural phrases.	2 / 5
Distinctiveness Conflict Risk	It occupies a clear, narrow niche (Slack sibling-agent standing context) with little overlap risk against unrelated skills, fitting the score-4 anchor; it is not score-5 because the absence of concrete trigger phrases leaves some ambiguity about exactly when it applies.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nanocoai/nanoclaw
Path: .claude/skills/slack-agent-flow/container/skills/slack-construct-agents/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.