agentleFS
Sign inStart free
LedgerHQLedgerHQ/ledger-live/.agents/skills/batch-feature-dev/SKILL.md

batch-feature-dev

Skill627 starsChanged 6 days agoMITView on GitHub

Handle batches of Jira tickets through shared analysis, per-ticket feature-dev, Lumen UI guardrails, changesets, and draft PRs. Use when the user provides multiple Jira tickets or asks to deliver tickets one by one with PRs.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read relevant skills before entering their phase:

    line 12
  2. Distinctive:

    Before coding, produce a compact matrix: id/link, area, owning packages, UI impact, tests/screenshots, dependencies, shared work, blockers.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Batch Feature Dev

Deliver ticket batches as coordinated PRs while keeping each ticket scoped and reviewable.

Load First

Read relevant skills before entering their phase:

  • feature-dev per ticket or coupled group.
  • git-conventions before branch, commit, rebase, or push work.
  • create-changeset before changesets; create-pr for draft PRs.
  • ldls-native or ldls-web before Lumen UI work.
  • structure-flow before placing any code; mvvm-architecture for the app side in apps/*/src/mvvm/.
  • validate-changes for validation.

Workflow

  1. Place the code. Intake every Jira ticket link, description, attachment, mockup, and constraint (fetch details with available Jira/Atlassian tools; ask if anything is inaccessible), then decide with structure-flow which layer and package own each concern of each ticket. Only screens composing @features/* and app-only code go to apps/*/src/mvvm/. Work several tickets need gets one owning package.
  2. Before coding, produce a compact matrix: id/link, area, owning packages, UI impact, tests/screenshots, dependencies, shared work, blockers. Ask consolidated questions for missing mockups, conflicts, unclear copy, APIs, analytics, navigation, flags, and edge cases.
  3. Branch via git-conventions. Start unrelated tickets from updated develop; chain only for real dependencies, target the previous branch, and state it in the PR. For shared groundwork, prefer one small foundation PR plus dependent PRs.
  4. For each ticket/group, run full feature-dev, starting from the agreed placement. Treat tickets and mockups as source of truth; ask on conflicts; use Lumen components; add only English source translations; keep shared utilities owned and justified.
  5. Validate affected scope with validate-changes, plus screenshots or manual visual checks for UI. Add a changeset with exact package names; use create-pr for draft PR and Slack message.
  6. Handoff each PR with ticket, branch, target, URL, changeset, validation results, screenshots/status, risks, and follow-ups. After the batch, summarize dependency graph and review order.

Stop When

Pause for missing ticket/mockup details, incompatible tickets, product/design decisions, meaningless validation, or changed chaining strategy.

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