clickup-api
ClickUp v3 API conventions, channel/DM creation rules, thread reply endpoints, and the company-wide 🧞 emoji prefix requirement for any Claude-authored…
Skill by search-atlas-group
Chalk Labs
Need help deploying clickup-api?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/search-atlas-group-clickup-api
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/clickup-api
What's inside
- Skill name
clickup-api- Description
- ClickUp v3 API conventions, channel/DM creation rules, thread reply endpoints, and the company-wide 🧞 emoji prefix requirement for any Claude-authored ClickUp message. Use when sending ClickUp messages, creating channels, replying to threads, or scripting against the ClickUp API.
- License
- MIT
- Instructions
- 57 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# clickup-api
ClickUp v3 quirks the team has been bitten by. Read before sending any message, creating any channel, or calling any ClickUp endpoint.
## Hard rules (NEVER violate)
### Never create public channels
**Forbidden:** `POST /chat/channels` — creates a public channel visible to the entire 50+ person workspace. This has caused real noise/cleanup incidents.
**Required pattern:** `POST /chat/channels/direct_message` with `user_ids` — creates a private DM (1 user) or group DM (2+ users). All messaging to teammates routes through DMs, never new public channels.
### Always prefix team-facing messages with 🧞
Any ClickUp message sent to teammates via Claude — DM, group DM, thread reply, or channel post — MUST start with the 🧞 emoji. Lets recipients identify Claude-authored messages at a glance. Applies to all scripts, MCP tools, and direct API calls. No exceptions.
## Endpoint reference
### DM creation
- `POST /chat/channels/direct_message` body: `{"user_ids": [<numeric>, ...]}`
- 1 user_id → private 1:1 DM
- 2+ user_ids → group DM
- Returns channel ID — then `POST /chat/channels/{id}/messages` to send.
### Thread replies
- Reply to a message: `POST /messages/{message_id}/replies`
- **NOT** the channel endpoint. A common mistake is posting back to the channel as a new top-level message instead of as a reply on the thread.
### Channel listing
- `GET /chat/channels` — paginated. Use the `cursor` from `next_cursor` field for the next page. `total_count` field returns the page size, not the full count — pages have `has_more`.
### DM creation fallback (auth-scoped failure recovery)
If `POST /chat/channels/direct_message` returns 401/403 (the configured token may lack v3 chat-write scope), DO NOT block. Instead:
1. List channels via `clickup_get_chat_channels`.
2. Filter to `type=DM`.
3. Probe each candidate's first few messages via `clickup_get_chat_channel_messages`, looking for the target user_id as sender.
4. Reuse the existing DM channel.
Reference incident: an existing teammate DM was identified this way on 2026-05-21 after v3 token auth failed.
## Roster hygiene
The `team_roster.json` file contains stale entries for people who have left the company. Before tagging, mentioning, or sending outbound messages:
1. Cross-check against current ClickUp workspace members (`clickup_get_workspace_members` or `clickup_resolve_assignees`).
2. Filter out likely-departed members before any outbound action.
3. Departures happen in waves (15+ in one day on recent offboarding) — assume roster is stale unless freshly synced.
## Partner channels — skip the noise
Do NOT assume a channel owner needs to reply to partner-channel messages unless
they are directly tagged. Partner-channel messages should usually be handled by
the CSM/support team. Filter untargeted partner-channel pings out of any triage
workflow.
## Reference
Full endpoint details in `~/.claude/reference/clickup-api.md`.From search-atlas-group/amm-founding-circle, MIT.
More from search-atlas-group/amm-founding-circle
- 0.524score
agency-scorecard
search-atlas-group
Builds and maintains an EOS-style weekly Scorecard — 5 to 15 leading numbers that tell you Monday whether you'll have a problem Friday — pulled automatically…
SkillBFreshness: BClaude Code +9 - 0.524score
client-health-score
search-atlas-group
Rolls engagement, deliverable timeliness, and sentiment signals for each client into one internal early-warning score, so a churn risk gets caught months…
SkillBFreshness: BClaude Code +9 - 0.479score
brand-kit-from-url
search-atlas-group
This skill orchestrates autonomous discovery of brand materials across enterprise platforms (Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong…
SkillCFreshness: CClaude Code +9 - 0.474score
building-autonomous-agents
search-atlas-group
The mental model behind an always-on system — a tool is something you invoke, an agent is something that runs, and the gap between them is a trigger.
SkillCFreshness: CClaude Code +9 - 0.474score
autonomy-budget
search-atlas-group
Hand a multi-day job to your agent and walk away — for real.
SkillCFreshness: CClaude Code +9 - 0.474score
capability-map
search-atlas-group
Map what your agent can actually DO across your stack today versus what's gapped, and learn the two workarounds that bridge a missing action.
SkillCFreshness: CClaude Code +9 - 0.474score
client-dashboard
search-atlas-group
Give your client a live, branded view of the work your agents are doing — without giving them your tools, your logins, or a plugin bolted into their site.
SkillCFreshness: CClaude Code +9 - 0.474score
agency-morning-brief
search-atlas-group
Your autonomous morning chief-of-staff for the agency.
SkillCFreshness: CClaude Code +9 - 0.474score
connection-monitor
search-atlas-group
Put a watch on your always-on agent so silence can never masquerade as success.
SkillCFreshness: CClaude Code +9 - 0.474score
agent-runbook
search-atlas-group
Routing runbook for engineering tasks across the agent stack (ao spawn, GSD, OMC, /goal, /loop, /schedule, inline, codex, gemini, Claude Flow swarm).
SkillCFreshness: CClaude Code +9 - 0.474score
codebase-map
search-atlas-group
Generate or refresh a codebase structural map for the current repo.
SkillCFreshness: CClaude Code +9 - 0.471score
cli-llm-routing
search-atlas-group
Use installed AI CLIs for second opinions, latest-docs checks, and long-context review.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jun 22, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from search-atlas-group
- 0.524score
agency-scorecard
search-atlas-group
Builds and maintains an EOS-style weekly Scorecard — 5 to 15 leading numbers that tell you Monday whether you'll have a problem Friday — pulled automatically…
SkillBFreshness: BClaude Code +9 - 0.524score
client-health-score
search-atlas-group
Rolls engagement, deliverable timeliness, and sentiment signals for each client into one internal early-warning score, so a churn risk gets caught months…
SkillBFreshness: BClaude Code +9 - 0.479score
brand-kit-from-url
search-atlas-group
This skill orchestrates autonomous discovery of brand materials across enterprise platforms (Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong…
SkillCFreshness: CClaude Code +9 - 0.474score
autonomy-budget
search-atlas-group
Hand a multi-day job to your agent and walk away — for real.
SkillCFreshness: CClaude Code +9 - 0.474score
agency-morning-brief
search-atlas-group
Your autonomous morning chief-of-staff for the agency.
SkillCFreshness: CClaude Code +9 - 0.474score
agent-runbook
search-atlas-group
Routing runbook for engineering tasks across the agent stack (ao spawn, GSD, OMC, /goal, /loop, /schedule, inline, codex, gemini, Claude Flow swarm).
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get clickup-api running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
clickup-api skill. Agent Mart. https://agentmart.dev/skills/search-atlas-group-clickup-api (last updated 2026-10-24)