Agent skill
slack
Manage unread Slack messages across the workspace: list, open, and reply with confirmation. Stores metadata for later actions.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/slack-antoniolg-agent-kit
SKILL.md
Slack (inbox + reply)
Requirements
- Environment variable:
SLACK_USER_TOKEN(user token). - Recommended scopes:
channels:read,groups:read,im:read,mpim:read,channels:history,groups:history,im:history,mpim:history,users:read,chat:write. - To mark as read (granular scopes):
channels:write,groups:write,im:write,mpim:write(depends on conversation type).
Commands (from the skill folder)
1) Inbox (unread)
scripts/slack-inbox --json-out /tmp/slack-inbox.json
- Shows a clean numbered list.
- Saves metadata for later actions.
2) Open a message
scripts/slack-open --index <n>
- Uses
/tmp/slack-inbox.jsonto resolve IDs. - Writes
/tmp/slack-open.json.
3) Reply (with user confirmation)
scripts/slack-reply --index <n> --text "reply"
- In channels: replies in thread if it exists (default).
- In DMs: use
--no-threadto reply as a new message. - After replying, mark as read with
scripts/slack-mark-read --index <n>.
4) Mark as read
scripts/slack-mark-read --index <n>
Metadata format
/tmp/slack-inbox.json contains:
indexid(channel id)nametypelast_readlatest_tslatest_textlatest_user_idlatest_user_nameunread_countunread_has_more
Rules
- Show the user only the clean list; do not show IDs.
- Before replying, ask for confirmation.
- If the JSON is stale or missing, re-run inbox.
- In DMs, always reply with
--no-threadand then mark as read. - After replying (channels or DMs), mark as read to clear pending items.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?