agentleFS
apokamoapokamo/kaji/.claude/skills/series-create/SKILL.md

series-create

Skill16 starsChanged 2 days agoApache-2.0View on GitHub

Create a validated sequential Issue series plan from an explicitly ordered GitHub Issue list. Use when a maintainer wants to generate or update an ID-named YAML file under .kaji/series, select standard workflows from Issue type metadata and workflow descriptions, or preview a series without starting it.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Read each Issue without mutation:

    line 25
  2. Very specific:

    Read every .kaji/wf/official//*.yaml and .kaji/wf/custom//*.yaml description and requires_provider value.

    line 31
  3. Very specific:

    If the target exists without --update, stop.

    line 46
  4. Distinctive:

    Run both checks and stop if either fails:

    line 47
  5. Distinctive:

    No Issue, PR, label, sub-issue, state, lock, or member-run mutation.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Series Create

Generate a deterministic series YAML, validate it, show its dry-run plan, and stop before execution.

Input

Accept this manual form:

/series-create <issue>... --id <series-id> [--parent <issue>]
  [--workflow <issue>=<repo-relative-path>]... [--update]

Preserve Issue order exactly. Treat --workflow as a member-specific override. Require --id and at least one positive integer Issue number.

Workflow

  1. Confirm kaji config provider-type returns github; otherwise stop.
  2. Read each Issue without mutation:

    kaji issue view <issue> --json labels,title,state
  3. Read every .kaji/wf/official/**/*.yaml and .kaji/wf/custom/**/*.yaml description and requires_provider value. For each member without an override, select candidates whose description says they are the standard series auto-selection target for the Issue's single type: label and whose provider is github or any.
  4. Auto-select only when exactly one candidate remains. Display the Issue type and matching description sentence as the reason. If the Issue has zero or multiple type: labels, or the candidate count is not one, stop and request --workflow <issue>=<path> for that member.
  5. Invoke the deterministic generator. Do not write YAML manually:

    python -m kaji_harness.scripts.series_generate \
      --id <series-id> [--parent <parent>] \
      --member <issue>=<workflow>... \
      --output .kaji/series/<series-id>.yaml [--update]
  6. If the target exists without --update, stop. Never retry with --update implicitly.
  7. Run both checks and stop if either fails:

    kaji validate-series .kaji/series/<series-id>.yaml
    kaji run-series .kaji/series/<series-id>.yaml --dry-run
  8. Report the generated path, ordered members, workflow selection reasons, validation result, and dry-run plan. Do not start kaji run-series without --dry-run.

Output

  • One .kaji/series/<id>.yaml containing only id, optional parent_issue, strategy, ordered members with resolved workflow paths, and on_failure.
  • A console summary of selection reasons and the validated dry-run plan.
  • No Issue, PR, label, sub-issue, state, lock, or member-run mutation.

Stop Conditions

  • Provider is not GitHub.
  • Input is malformed or Issue type metadata is missing/ambiguous.
  • Workflow selection is not unique and no override was supplied.
  • An override path fails validate-series.
  • The output exists without explicit --update.
  • Generation, validation, or dry-run returns nonzero.

Non-goals

  • Discovering members from an EPIC, parent body, or sub-issue relation.
  • Reordering members or inferring dependencies.
  • Editing Issue metadata or external state.
  • Duplicating schema validation or YAML serialization in the agent.
  • Starting the actual series execution.

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.