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.
74
67%
Does it follow best practices?
Impact
79%
4.93xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/slack/SKILL.mdEvaluation results
96%
96%Morning Slack Catch-Up
Unread message discovery workflow
Connect to existing session
0%
100%
Snapshot before click
0%
100%
Activity tab check
0%
100%
More unreads button
0%
66%
Wait delays present
0%
100%
Activity screenshot
0%
100%
DMs screenshot
0%
100%
Unreads screenshot
0%
100%
Re-snapshot after navigation
0%
100%
DMs tab check
0%
100%
82%
82%Incident Post-Mortem Research
Channel search and structured data extraction
JSON snapshot for channels
0%
100%
Search button then fill
0%
20%
Press Enter after fill
0%
100%
Wait networkidle after search
0%
100%
Sidebar scroll selector
0%
100%
Re-snapshot after navigation
0%
100%
Search filter usage
0%
0%
Connect to existing session
0%
100%
Snapshot before first click
0%
100%
Screenshots as evidence
0%
100%
61%
12%Quarterly Slack Usage Audit
Structured Slack analysis report generation
Report summary section
60%
20%
Unread channels section
100%
25%
Channel snapshot section
87%
25%
Search results section
100%
25%
Screenshots table in report
100%
75%
Annotated screenshot
0%
100%
Get URL or title
0%
100%
Connect to existing session
0%
100%
Wait delays
0%
100%
Search with filter
0%
30%
Key conversations section
100%
33%
Report metadata
100%
100%
- Repository
- vercel-labs/agent-browser
- Commit
fa043a4
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.