slack-notifications
Slack MCP integration for agent-to-human notifications and bi-directional communication. Use when agents need to post progress updates, request approvals, or read user responses via Slack channels and threads.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies its domain (Slack MCP integration), lists specific concrete actions (post updates, request approvals, read responses), and includes an explicit 'Use when' clause with natural trigger terms. It is concise, uses third-person voice, and is highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'post progress updates', 'request approvals', 'read user responses', and specifies the communication medium (Slack channels and threads). | 3 / 3 |
Completeness | Clearly answers both what ('Slack MCP integration for agent-to-human notifications and bi-directional communication') and when ('Use when agents need to post progress updates, request approvals, or read user responses via Slack channels and threads'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Slack', 'notifications', 'approvals', 'progress updates', 'channels', 'threads'. These cover the main use cases well and are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: Slack-specific MCP integration for agent-to-human communication. The combination of 'Slack', 'MCP', 'agent-to-human', and specific actions like 'approvals' makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently covers Slack MCP integration for agent notifications. It provides executable code examples, clear workflow sequencing for the dual-channel approval pattern, and appropriate progressive disclosure to reference files. The content is concise while being comprehensive enough to handle the main use cases including error handling and session recovery.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows what Slack, MCP, and polling are. Every section delivers actionable information without explaining basic concepts. The message format examples are compact yet clear. | 3 / 3 |
Actionability | Provides executable JS code for posting messages and polling for replies, concrete message format templates with emoji conventions, specific regex patterns for parsing responses, and exact rate limit numbers. Copy-paste ready. | 3 / 3 |
Workflow Clarity | The bi-directional communication workflow is clearly sequenced (steps 1-5) with explicit handling for different outcomes (chat wins, Slack wins, session ends). The dual-channel pattern includes a feedback loop (poll → retry → timeout) and checkpoint recovery for session boundaries. | 3 / 3 |
Progressive Disclosure | Clean overview with well-signaled one-level-deep references to REFERENCE.md for OAuth scopes/token setup and security guidelines, and to .opencastle/stack/notifications-config.md for project-specific config. Content is appropriately split between the skill overview and reference material. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- monkilabs/opencastle
- Commit
18c6f2c
- 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.