Dailybot Agent Skill
FeaturedTurn any AI coding agent into a real teammate.
The Dailybot Agent Skill is a single cross-agent skill pack that installs into every major AI coding CLI with one command. Once installed, your agent has the same verbs a human teammate has — report progress, complete check-ins, send an email, kudos a colleague, post on Slack or Teams, submit a form, or announce its own health. All of it lands in the same standup feed your team already reads. No context switch, no side channel, no black-box moves.
8
coherent sub-skills, one per API verb
5+
AI coding agents supported
1:1
mapped to public API endpoints
MIT
licensed, end to end
Sub-skills
One skill pack. Every verb your agent needs.
Each sub-skill maps 1:1 to a public Dailybot API endpoint. Composable, coherent, and documented — the way your agent expects.
report
Send a 1–3 sentence progress report to your team. English only, WHAT + WHY. Written the way a real person would say it in a standup.
checkin
List and complete the developer's pending check-ins. The agent fills them the same way a human would — from inside the coding session it's already running in.
chat
Send and edit bot messages on Slack, Teams, Discord, or Google Chat. Support for report-style threads (one headline + replies, in one call).
kudos
Recognize a teammate — or an entire team — for a good review, a merged PR, a saved bug. Kudos land in the same feed as reports.
forms
Full form lifecycle — list, submit, update, and transition responses through workflow states. Perfect for release notes, access requests, or standing forms.
teams
Resolve a human-readable team name into a UUID other sub-skills can consume. The agent never has to guess which Slack channel to post to.
health
Announce the agent online / offline / working / degraded to the team. Health checks also deliver pending team messages back to the agent inbox.
Send an email to a confirmed recipient. Useful for notifications, summaries, follow-ups, or weekly reports. Replies come back as agent messages.
Why it works
The bits that make it feel like a teammate.
1:1 API mapping
Every sub-skill maps to a single public Dailybot endpoint. No new surfaces to learn. If it works via the REST API, it works via the skill — and if a skill call fails, you can debug it against a documented endpoint.
Dual-auth parity
The skill reads either `dailybot login` (personal OTP) or `$DAILYBOT_API_KEY` (long-lived key for CI). Same access on both paths. Parity is a written guarantee — no scoped-down surprises in CI.
Per-repo profile
A `.dailybot/profile.json` per repo standardizes author name, default metadata, and reporting cadence. Every contributor's reports sign and tag consistently, so a manager reading the standup knows who directed what work.
Cross-agent by design
One skill pack, every major AI CLI. Claude Code, Cursor, OpenAI Codex, Gemini, Copilot, Cline, Windsurf. Same install command, same behavior, same reports. Switch agents and nothing about the workflow changes.
Standup-wired
Every action lands in the same daily feed your team already reads. Kudos, reports, form submissions, health status — all in one place, written in the same voice, with the same level of detail. No parallel agent channel to check.
MIT + fully forkable
The whole pack is MIT-licensed. Fork it, strip our branding, run it in your own harness — nothing about your team's workflow is locked to Dailybot. That's the promise, written in a licence and printed on every README.
How Dailybot connects
Every action the skill takes lands in the same standup feed your team already reads. Your agent stops being a black box and starts being a teammate the humans can see.
Built for
Compatible agents
Install
Two commands and your agent is a teammate.
Install the Dailybot CLI once — it authenticates your session and every skill calls the same binary underneath. Then add the skill to whichever AI CLI you use.
Step 1
Install the CLI (recommended baseline)
One command. Sets up the `dailybot` binary and prepares your local auth.
$ curl -sSL https://cli.dailybot.com/install.sh | bashStep 2
Install in your AI CLI of choice
Every major AI CLI reads skills from your project's `.agents/skills/` folder. Pick your CLI, run the command, and the skill is available in every future session.
curl -sSL https://cli.dailybot.com/install.sh | bash
npx skills add DailybotHQ/agent-skillnpx skills add DailybotHQ/agent-skillgit clone https://github.com/DailybotHQ/agent-skill \
.agents/skills/dailybot-agentgit clone https://github.com/DailybotHQ/agent-skill
cd agent-skill && ./setup.shIn practice
What teams actually do with it.
01
Auto-standup from every agent session
Claude finishes a bug fix at 11pm. A one-sentence progress report lands in tomorrow's standup with the human developer credited as co-author. The manager reads the same feed they always read — no separate agent channel.
02
Kudos from inside the code review
Cursor finishes a hard review. The agent kudos the reviewer for good feedback — from the same session, in one command. Recognition happens where the work happens.
03
Async form submissions
Your release form asks for changelog, risk, rollback plan. The agent has all three at hand from the diff. It submits the form and transitions it through workflow states — the humans just approve.
04
Health-checked agents in production
A long-running agent announces itself online at session start and offline at shutdown. If it degrades, the health check surfaces that to the team before a stakeholder does.
Our nightly agents used to run silently. Now every bug fix, every reviewer kudos, every release form lands in the same standup our humans read. The manager doesn't even need to know which teammate is running Claude vs Cursor — the reports read the same.
Engineering leadon team using the Agent Skill across Cursor + Claude Code
FAQ
The questions we hear the most.
Do I need to install the skill once per agent?
No. `npx skills add DailybotHQ/agent-skill` writes the skill into your project's `.agents/skills/` folder once — every major AI CLI reads from that folder, so a single install serves Claude Code, Cursor, Codex, Gemini, and Copilot in the same repo.
Does the skill talk to Slack / Teams / Discord directly?
No. The skill talks to Dailybot's API, and Dailybot handles delivery to whichever chat platform your team is connected to. That's how the same `chat` verb works identically for Slack, Microsoft Teams, Discord, and Google Chat.
What if a repo has more than one agent?
Set an explicit `agent_name` per agent in `.dailybot/profile.json` (for example `claude-code` vs `cursor-review-bot`). Each agent's reports carry that identity so the standup feed shows who did what.
Is agent work visible to the whole team, or just to me?
Everything lands in the same standup feed the humans already read. If you're logged into the CLI, Dailybot also credits you as co-author on every report — so the agent's work shows up in your daily standup, because you directed it.
Can I run the skill without an AI agent?
Yes. The skill is a thin wrapper over the `dailybot` CLI, which you can invoke from any shell, script, or CI job. Install the CLI once and every sub-skill is available even without an agent in the loop.
Is my API traffic authenticated the same way in CI?
Yes. Set `DAILYBOT_API_KEY` in CI and the skill uses it automatically. Personal OTP (`dailybot login`) and API key have identical scopes — parity is a written guarantee.
What it is
The Dailybot Agent Skill is the official adapter between your AI coding agent — Cursor, Claude Code, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Windsurf — and Dailybot’s full public API surface. It exposes eight coherent sub-skills, each mapped 1:1 to a documented Dailybot verb, so your agent can act like a real teammate from inside the same session it’s already running in.
Why teams use it
Your agent is doing real work — writing PRs, fixing bugs, running plans. But that work stays invisible unless it lands where the team already looks. The Agent Skill closes the loop: agent finishes a task, agent files a progress report, humans see it in the standup the next morning. No new tab, no new tool, no new habit.
How it works with Dailybot
Every sub-skill is a thin wrapper over a public Dailybot endpoint documented at dailybot.com/developers. Auth is either a personal CLI token (dailybot login) or an API key (DAILYBOT_API_KEY) — the skill picks whichever is available and falls back gracefully. A per-repo .dailybot/profile.json standardizes author name, default metadata, and reporting cadence, so every contributor’s reports sign and tag consistently.
Ship agent work your team can actually see.
Install the skill in your favorite AI CLI and every action your agent takes lands in the same standup your humans already read.