agentleFS
Sign inStart free
luckyfoxdesignluckyfoxdesign/llm-settings-template/.agents/skills/create-task/SKILL.md

create-task

Skill0 starsChanged 39 days agoMITView on GitHub

Create an implementation-ready backlog task in this workspace from a request, idea, or issue. Use for task drafting and backlog additions; do not start implementation or close a task.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use harbor-exec and rewardkit.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Arize-aiSkill

    harbor-exec

    Use when working with Harbor's `harbor exec` CLI workflow: compiling files, directories, or globs into Harbor tasks; running map jobs; configuring artifacts and existence-only verification; using map-reduce; writing or reviewing ExecConfig YAML/JSON/TOML; or debugging command behavior, config validation, and job outputs.

    Also in 4 projects that use this

  • Arize-aiSkill

    rewardkit

    Write Harbor task verifiers using Reward Kit. Use when creating or editing a

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create one implementation-ready task without starting it.

    line 8
  2. Very specific:

    Read and follow the complete algorithm in docs/workflows/task-lifecycle.md, section /create-task Equivalent …

    line 11
  3. Distinctive:

    Use the user's request and any supplied issue, idea, observation, paths, or acceptance criteria as inputs.

    line 12
  4. Very specific:

    Ask only for information whose absence would materially change the task contract.

    line 13
  5. Very specific:

    Stop after creating and validating the backlog file.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 10 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

Create Task

Create one implementation-ready task without starting it.

  1. Resolve this SKILL.md path, including symlinks, to locate its owning workspace with AGENTS.md and docs/workflows/task-lifecycle.md. If these are absent, report missing workspace setup.
  2. Read and follow the complete algorithm in docs/workflows/task-lifecycle.md, section /create-task Equivalent (docs/workflows/task-lifecycle.md#create-task-equivalent). Resolve these paths from the workspace root, not from the skill folder. The linked procedure owns lifecycle details.
  3. Use the user's request and any supplied issue, idea, observation, paths, or acceptance criteria as inputs. Inspect only the project context required by the algorithm.
  4. Ask only for information whose absence would materially change the task contract. Record safe assumptions in Context when they do not require a user decision.
  5. Stop after creating and validating the backlog file. Do not move it to docs/wip/, implement it, or commit it.

Finish with the exact result line required by the workspace algorithm.

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