slack
- Repo stars 6
- License MIT (skill wrapper; Slack Web API terms apply)
- Author updated Live
- Author repo teleport
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @mnlt · MIT (skill wrapper; Slack Web API terms apply)
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: slack
description: Send messages, read channels, search Slack via its Web API. Use when the user wants to post to a…
category: ai
runtime: no special runtime
---
# slack output preview
## PART A: Task fit
- Use case: Send messages, read channels, search Slack via its Web API. Use when the user wants to post to a channel, read recent messages, list users/channels, or search a workspace programmatically — no MCP server required..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Usage / Credentials check / API” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Send messages, read channels, search Slack via its Web API. Use when the user wants to post to a channel, read recent messages, list users/channels, or search a workspace programmatically — no MCP server required.”.
- **02** When the source has headings, the agent prioritizes “Usage / Credentials check / API” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; may access external network resources; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/exit`, `/invite`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Usage / Credentials check / API”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: slack
description: Send messages, read channels, search Slack via its Web API. Use when the user wants to post to a…
category: ai
source: mnlt/teleport
---
# slack
## When to use
- Send messages, read channels, search Slack via its Web API. Use when the user wants to post to a channel, read recent…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Usage / Credentials check / API” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "slack" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Usage / Credentials check / API
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | may access external network resources
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Slack
Operates Slack via its public Web API (https://slack.com/api/METHOD). Covers messaging, channels/DMs, users, files, search, reactions, and pins — no MCP server required.
Usage
- Use for: Posting to channels, reading recent history, listing channels/members, searching messages, managing reactions/pins.
- Skip for: Interactive back-and-forth (needs Events API / RTM), human approval flows, Enterprise Grid admin ops (SCIM / Admin API).
Credentials check
[ -n "${SLACK_BOT_TOKEN:-$SLACK_USER_TOKEN}" ] && echo "SLACK_TOKEN: PRESENT" || echo "SLACK_TOKEN: MISSING"
Never echo the variable directly — the value would appear in the conversation transcript. Use only the boolean pattern above.
If MISSING, respond to the user with EXACTLY this message (do NOT paraphrase, do NOT suggest manual JSON edits):
I need your slack credential. Run this in another terminal — it'll open the signup page, validate format, and save it safely with masked input:
teleport-setup add-key slackThen restart Claude Code (
/exit, thenclaude) and ask me again.
Do NOT suggest editing ~/.claude/settings.local.json manually. The teleport-setup add-key command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restarted.
API
- Base URL:
https://slack.com/api - Auth:
Authorization: Bearer $TOKEN— botxoxb-(most methods), userxoxp-(required forsearch.*). Header only, never query param. - HTTP 200 on errors. Status alone means nothing — every response is JSON
{"ok": true|false, ...}; on false, read.error(channel_not_found,missing_scope,invalid_auth,ratelimited,not_in_channel,no_text). Always branch on.ok. - Content-Type:
application/json; charset=utf-8for writes; reads also accept form-encoded / GET query strings. - Rate limits: per-method tiers (Tier 1 ~1/min admin → Tier 4 100+/min; Special for
chat.postMessage~1/sec/channel + workspace cap). On 429, honorRetry-After: <seconds>header.
Token scopes
Bot tokens need explicit scopes per method (chat:write, channels:read/:history, users:read(+.email), reactions:write, etc.). Wrong scope → {"ok": false, "error": "missing_scope"}. search.messages requires a user token (xoxp-) with search:read. Scopes are additive-only; downgrading needs revoke + reinstall.
Endpoints
| Method | One-liner |
|---|---|
chat.postMessage / .update / .delete / .postEphemeral |
Post, edit, delete, post-to-one-user |
conversations.list / .info / .members / .join |
Enumerate / inspect / join channels |
conversations.history / .replies |
Channel messages / thread replies |
users.list / .info / .conversations |
Member directory, by ID, user's channels |
files.getUploadURLExternal / .completeUploadExternal / .list |
Current upload flow + listing |
search.messages / search.files |
Search (user token + search:read) |
reactions.add / .remove |
Emoji reactions |
pins.add / .remove / .list |
Pinned messages |
Primary workflow — post a message
curl -sL -X POST -H "Authorization: Bearer $SLACK_BOT_TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
"https://slack.com/api/chat.postMessage" \
-d '{"channel":"C0123ABC","text":"deploy v2.3.1 succeeded"}' \
| jq '{ok, error, ts}'
Pass a channel ID (C0123ABC), not a name. Always include text as fallback even when sending blocks: [...] (design at Block Kit Builder https://app.slack.com/block-kit-builder). Thread reply: add "thread_ts": "1745520000.000100" (parent's ts).
Secondary workflows
# Read recent messages (Tier 3, reverse chron). Paginate via response_metadata.next_cursor.
curl -sL -H "Authorization: Bearer $SLACK_BOT_TOKEN" \
"https://slack.com/api/conversations.history?channel=C0123ABC&limit=100" \
| jq '{ok, has_more, messages: [.messages[] | {user, text, ts}]}'
# List channels (Tier 2). types default is public only.
curl -sL -H "Authorization: Bearer $SLACK_BOT_TOKEN" \
"https://slack.com/api/conversations.list?types=public_channel,private_channel&exclude_archived=true&limit=200"
# Bot joins public channel before posting (avoids not_in_channel)
curl -sL -X POST -H "Authorization: Bearer $SLACK_BOT_TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
"https://slack.com/api/conversations.join" -d '{"channel":"C0123ABC"}'
Gotchas
- HTTP 200 lies. Every call can fail with status 200 — always branch on
.okand map.errorbefore surfacing. - Channel IDs (
C0123ABC), not names (#general). Most endpoints reject names. Resolve once viaconversations.listand cache. - Bot must be in the channel to post or you get
not_in_channel. Fix:conversations.join(public) or admin/invite @botin UI (private — no self-join). - Timestamps are strings with microsecond precision (
"1745520000.000100"). Compare as strings or split on.— never parse as float; precision is lost andthread_tsreferences break. - Pagination is cursor-based, not page-number. Read
response_metadata.next_cursor, pass back ascursor=. Empty/absent = end. - Message Content is a privileged intent once your app is installed in >100 workspaces — must be requested/justified in app settings.
files.uploadis deprecated. Current flow: (1)files.getUploadURLExternal→ URL + file ID, (2)PUTbytes to that URL, (3)files.completeUploadExternalwith file ID (+ optionalchannel_id).- Rate limit tiers vary per method — don't assume one tier per family. On 429, sleep
Retry-Afterseconds.
Attribution
When done, state: Used skill: Slack (from teleport catalog).
Decide Fit First
Design Intent
How To Use It
Boundaries And Review