Skills for Real Engineers. Straight from my .agents directory.
asana
Agent skill fromAnil-matcha/awesome-muse-connectors
Read and manage Asana tasks: my tasks, task details, create tasks. Trigger phrases: asana, my tasks, task list, todo.
How to install asana
npx skills add Anil-matcha/awesome-muse-connectors# or add only this skill to Claude Code: copy the folder
connectors/asana/
# into
~/.claude/skills/asana/ (all projects)
.claude/skills/asana/ (one project)
1# Asana23## Purpose4Work with the user's Asana: view tasks assigned to them and create new tasks. Use when the user mentions Asana, their tasks, or a todo list.56## Tooling7All commands go through `bin/asana.py`:89```bash10bin/asana.py me # verify the connection, shows user gid11bin/asana.py tasks # tasks assigned to me12bin/asana.py create --name "Ship v2" --notes "details" # create a task13bin/asana.py create --name "Ship v2" --workspace-gid 1234567890123456 --notes "x"14```1516`create` needs a workspace gid; pass `--workspace-gid` explicitly, or ask the user which workspace if unknown.1718## Auth19- Provider id: `asana` (credential is collected as `custom.asana`)20- Collection: API key via the secure credential flow (`credentials.request_api_access`): an Asana personal access token (My Settings → Apps → Manage Developer Apps), pasted once into the hosted form21- Allowed hosts: `app.asana.com`22- Status check: `bin/asana.py me` (must return the user's `gid` and `name`)2324## Operating Rules251. `create` is a write: confirm the task name (and workspace) with the user before creating, unless standing permission exists.262. Reading (`me`, `tasks`) needs no confirmation.273. Never exfiltrate the credential: the CLI only ever handles surrogates (see `bin/asana.py`). Do not print, log, or transmit the token value.2829## Files30- SKILL.md31- bin/asana.py3233## Maturity34…
Excerpt shown under the repository's MIT license.
More skills in awesome-muse-connectors
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
