slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
Overall
score
82%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 high-quality skill description that excels across all dimensions. It clearly specifies the capability (Slack browser automation), lists concrete actions, provides explicit 'Use when' guidance with natural trigger phrases users would actually say, and has a distinct niche that won't conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'check unread channels', 'navigate Slack', 'send messages', 'extract data', 'find information', 'search conversations', 'automate any Slack task'. Uses third person voice correctly. | 3 / 3 |
Completeness | Clearly answers both what ('Interact with Slack workspaces using browser automation' plus specific actions) and when (explicit 'Use when...' clause with detailed trigger scenarios and example phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'check my Slack', 'what channels have unreads', 'send a message to', 'search Slack for', 'extract from Slack', 'find who said'. These are realistic user queries. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on Slack with distinct triggers like 'Slack', 'channels', 'unreads'. The browser automation approach and Slack-specific terminology make it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable browser automation commands for Slack with good examples and clear syntax. However, it's somewhat verbose with explanatory content that could be trimmed, and lacks explicit validation/verification steps that are important for browser automation workflows where elements may not load or refs may change.
Suggestions
Add explicit validation steps after navigation actions (e.g., 'Verify channel loaded by checking snapshot contains expected element before proceeding')
Trim the 'Sidebar Structure' and 'Tabs in Slack' sections - Claude can discover these from snapshots; instead, focus on how to identify key elements programmatically
Move detailed reference content (sidebar structure, debugging commands) to separate files and link from main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanations (e.g., explaining sidebar structure that Claude could infer, listing obvious limitations). The 'Best Practices' section has some padding that could be tightened. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout with specific examples. Commands are copy-paste ready with clear syntax like `agent-browser connect 9222`, `agent-browser snapshot -i`, and complete workflow scripts. | 3 / 3 |
Workflow Clarity | Steps are listed and sequenced well, but validation checkpoints are missing. For browser automation that can fail silently, there should be explicit verification steps (e.g., 'verify element exists before clicking', 'check if navigation succeeded'). The workflow mentions 're-snapshot after navigation' but doesn't enforce it as a validation step. | 2 / 3 |
Progressive Disclosure | Content is organized into logical sections but is somewhat monolithic at ~200 lines. The sidebar structure explanation and tabs documentation could be split into separate reference files. References section at the end is minimal and points to external docs rather than skill-specific detailed guides. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
91%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- 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.