catalan-adobe/slack-cdp
Control Slack via CDP or headless API tokens. Navigate channels, read/send messages, search conversations, check unreads, and manage status. Two modes: CDP (Slack desktop with --remote-debugging-port) for full UI control, or headless (xoxp/xoxb token) for data operations without Slack running. Triggers on: slack, read slack, search slack, slack unreads, send slack message, slack status, navigate slack, check slack, slack messages, go to channel, slack DM.
97
97%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
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 excels across all dimensions. It provides specific capabilities, comprehensive trigger terms, clear when/what guidance, and is distinctively focused on Slack operations. The technical detail about CDP vs headless modes adds useful context without being overly verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Navigate channels, read/send messages, search conversations, check unreads, and manage status.' Also describes two distinct operational modes with technical details. | 3 / 3 |
Completeness | Clearly answers both what (control Slack, navigate channels, read/send messages, etc.) and when (explicit 'Triggers on:' clause with comprehensive list of trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'slack, read slack, search slack, slack unreads, send slack message, slack status, navigate slack, check slack, slack messages, go to channel, slack DM' - these match how users would naturally phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around Slack specifically. The explicit mention of CDP vs headless modes and Slack-specific triggers make it unlikely to conflict with other communication or messaging skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%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 with excellent actionability and workflow clarity. It provides concrete, executable commands for both CDP and headless modes, includes verification patterns, and has a useful decision tree for choosing the right approach. The only weakness is that the content is fairly long and could benefit from splitting detailed sections (like token setup) into separate files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with Node.js, bash, and API concepts. No unnecessary explanations of what Slack is or how OAuth works conceptually—just the specific details needed. | 3 / 3 |
Actionability | Provides fully executable bash commands, curl examples, and complete code snippets. The script location logic, all subcommands, and API calls are copy-paste ready with concrete examples. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit verification steps (e.g., 'After navigate, always verify with where'). Chaining patterns show complete workflows, and the error recovery table provides clear feedback loops. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the skill is somewhat monolithic. The headless vs CDP modes, token obtaining instructions, and error recovery could potentially be split into separate reference files for better navigation. | 2 / 3 |
Total | 11 / 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.
Reviewed
Table of Contents