agentleFS
WeaverseWeaverse/.agents/skills/create-task/SKILL.md

create-task

Skill0 starsChanged 6 days agoMITView on GitHub

Create a Weaverse GitHub issue with duplicate detection and complete metadata. Use when explicitly asked to create a task or issue, not for implementation or review support on an existing issue.

14 other projects use a version of this, 1 of them edited.

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

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search related issues in all states, across the organization as well as the target repository: gh search issues '<topic>' --owner Weaverse …

    line 12
  2. Very specific:

    Read the issue template, labels, assignees, milestones, organization issue types and project fields.

    line 16
  3. Very specific:

    Use GET orgs/Weaverse/issue-types for types and gh project field-list for board field/option IDs.

    line 17
  4. Distinctive:

    Use available assignee, labels, milestone, type, project, status and priority.

    line 18
  5. Distinctive:

    Do not invent fields or silently rewrite an approved body.

    line 21
  6. Very specific:

    Create noninteractively using the supported --type flag, not an issue-type GraphQL mutation:

    line 22
  7. Very specific:

    If the installed CLI lacks --type, report the version gap rather than starting an upgrade or workaround.

    line 30
  8. Distinctive:

    Read the issue and project item back.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 11 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

  1. Resolve the repository from the request and gh repo view --json nameWithOwner; do not assume the default checkout is the destination. If authentication or destination is missing, return the blocker, not a login wizard.
  2. Search related issues in all states, across the organization as well as the target repository: gh search issues '<topic>' --owner Weaverse --limit 100 --json number,title,state,url,repository. Refine the search or paginate if results are truncated, and read likely matches with gh issue view. Reuse a genuine match even if closed. Reopening or editing it needs authority; a loosely related epic is not a match.
  3. Read the issue template, labels, assignees, milestones, organization issue types and project fields. Use GET orgs/Weaverse/issue-types for types and gh project field-list for board field/option IDs. Use available assignee, labels, milestone, type, project, status and priority; distinguish absent from inaccessible.
  4. Prepare the title, body and metadata together. Include outcome, scope/non-goals, acceptance and context. Show the final payload and destination for approval unless that exact scope is already approved. Do not invent fields or silently rewrite an approved body. In unattended work, return a specific blocker.
  5. Create noninteractively using the supported --type flag, not an issue-type GraphQL mutation:

    gh issue create --repo "$REPO" --title "$TITLE" --body-file "$BODY_FILE" \
      --type "$TYPE" --assignee "$ASSIGNEES" --label "$LABELS" --milestone "$MILESTONE"

    Omit only metadata that is unavailable or intentionally unset in the approved payload. If the installed CLI lacks --type, report the version gap rather than starting an upgrade or workaround.

  6. For an approved project, use gh project item-add --url "$ISSUE_URL" --format json, retain the item ID, then set single-select fields with gh project item-edit --id ... --project-id ... --field-id ... --single-select-option-id .... Adding a project does not set its status or priority. Names are not field IDs.
  7. Read the issue and project item back. If a board update fails after creation, report the existing issue URL and the incomplete field; do not create a duplicate on retry.

Report the issue URL, verified metadata, reused match (if any), and anything left unset with its reason.

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.