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.
91
91%
Does it follow best practices?
Impact
—
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 an excellent skill description that covers all key dimensions thoroughly. It provides specific concrete actions, clearly explains two operational modes, and includes an explicit and comprehensive list of trigger terms. The description is well-structured, uses third person voice correctly, and would allow Claude to confidently select this skill when Slack-related tasks arise.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: navigate channels, read/send messages, search conversations, check unreads, manage status. Also describes two distinct operational modes (CDP and headless) with clear details about each. | 3 / 3 |
Completeness | Clearly answers both 'what' (control Slack via CDP or headless API tokens with specific actions listed) and 'when' (explicit 'Triggers on:' clause with comprehensive trigger terms). Both dimensions are thoroughly covered. | 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 are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Slack specifically. The two-mode architecture (CDP vs headless) and Slack-specific trigger terms make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, highly actionable skill with excellent workflow clarity including verification steps, decision trees, and error recovery. Its main weakness is length — the token-obtaining OAuth flow, headless API curl examples, and script-finding boilerplate could be moved to referenced files to improve conciseness and progressive disclosure.
Suggestions
Move the 'Obtaining tokens' OAuth flow instructions and headless API curl examples to a separate HEADLESS.md reference file, keeping only a brief summary and link in the main skill.
Consider simplifying the script-finding bash blocks — the multi-fallback path resolution is verbose and could be extracted to a helper or referenced file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but it's quite long. The token-obtaining section (OAuth flow steps) and some of the headless API curl examples add bulk that could be referenced externally. The script-finding bash blocks are verbose boilerplate. | 2 / 3 |
Actionability | Highly actionable with fully executable bash commands, concrete curl examples, specific data-qa selectors for clicking, and clear command syntax with flags. Every operation has copy-paste ready code. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit verification steps (navigate then verify with 'where'). The decision tree provides clear routing logic, chaining patterns show common multi-step operations, and the error recovery table provides feedback loops for common failures. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's monolithic — the headless mode details, token obtaining instructions, and API curl examples could be split into separate reference files. For a skill this long (~180 lines), more content should be externalized. | 2 / 3 |
Total | 10 / 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