agentleFS
Sign inStart free
stardustaistardustai/stardust-skills/skills/task-management/SKILL.md

task-management

Skill0 starsChanged 2 months agoMITView on GitHub

Use when an agent needs current internal task, project, TODO, owner, deadline, follow-up, or progress context from the CEO agent service. It provides read-only local HTTP API lookup instructions for task context.

14 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when a conversation asks about internal projects, tasks, TODOs, owners, deadlines, status, blockers, follow-ups, task detail …

    line 13
  2. Distinctive:

    Treat API results as read-only evidence from the service database.

    line 37
  3. Very specific:

    Prefer matches supported by match.reasons, the conversation title, sender, message text, and owner fields.

    line 38
  4. Very specific:

    Use project.detail_url, todo.detail_url, and follow-up detail_url when a reply should point a user to the UI.

    line 40
  5. Distinctive:

    If multiple returned projects are plausible and the exact task still cannot be identified, ask a clarifying question instead of guessing.

    line 42
  6. Distinctive:

    Do not mutate tasks through this API.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Task Management

Use this skill when a conversation asks about internal projects, tasks, TODOs, owners, deadlines, status, blockers, follow-ups, task detail links, or progress and the visible chat context is not enough.

Read-only API

The local CEO agent service exposes task context as JSON:

curl -sS --get 'http://127.0.0.1:8765/api/task-management/search' \
  --data-urlencode 'q=<message text or project/task keywords>' \
  --data-urlencode 'conversation_id=<open conversation id if known>' \
  --data-urlencode 'owner_user_id=<sender or owner user id if known>' \
  --data-urlencode 'limit=3'

To fetch one project exactly:

curl -sS 'http://127.0.0.1:8765/api/task-management/projects/<project_id>'

Result Use

  • Treat API results as read-only evidence from the service database.
  • Prefer matches supported by match.reasons, the conversation title, sender, message text, and owner fields.
  • Use project.detail_url, todo.detail_url, and follow-up detail_url when a reply should point a user to the UI.
  • If multiple returned projects are plausible and the exact task still cannot be identified, ask a clarifying question instead of guessing.
  • Do not mutate tasks through this API. Task creation or updates still belong to the task agent or service workflow.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free