agentleFS
xsovad06xsovad06/sova/.agents/skills/sova-new-feature/SKILL.md

sova-new-feature

Skill3 starsChanged 6 days agoApache-2.0View on GitHub

Set up a new feature branch and prepare for development.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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:

    Ensure the current working tree is clean: git status

    line 17
  2. Distinctive:

    Read CLAUDE.md and AGENTS.md for project conventions

    line 32
  3. Very specific:

    Read agent memory files if they exist (.claude/agent-memory/.

    line 33
  4. Distinctive:

    Create a task checklist with the tasks

    line 38
  5. Very specific:

    Ready to implement?: Run the sova-develop skill <description> or the sova-develop-full skill <description>

    line 51
  6. Very specific:

    Need to understand approaches first?: Run the sova-develop-explain skill <description>

    line 52
  7. Distinctive:

    NEVER use emojis in any output

    line 56

≈ “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

Start New Feature

Set up a new feature branch and prepare for development.

Feature name/description: the arguments provided when this skill is invoked

Workflow

1. Ensure Clean Starting Point

  • Resolve the default branch: BASE=$(gh repo view --json defaultBranchRef --jq .defaultBranchRef.name)
  • Fetch it: git fetch origin "$BASE"
  • Ensure the current working tree is clean: git status

2. Create Feature Branch

  • Derive a branch name from the description (lowercase, hyphenated)
    • Features: feat/<name> (e.g., feat/income-crud)
    • Fixes: fix/<name> (e.g., fix/currency-conversion)
    • Refactors: refactor/<name> (e.g., refactor/auth-flow)
  • If the project keeps active branches in worktrees (.claude/worktrees/ exists, or its rules say so), create the branch in a new worktree so the primary checkout stays on the base branch, then do all further work from that directory:
    BASE=$(gh repo view --json defaultBranchRef --jq .defaultBranchRef.name)
    git worktree add ".claude/worktrees/<issue-or-topic>" -b "<branch-name>" "origin/$BASE"
  • Otherwise, from a checkout on the base branch: git pull origin "$BASE", then git checkout -b <branch-name>

3. Review Context

  • Read CLAUDE.md and AGENTS.md for project conventions
  • Read agent memory files if they exist (.claude/agent-memory/; for a split cookbook in .claude/agent-memory/cookbook/, read its README.md index and only the relevant domain files)
  • Identify which existing modules/files will be affected

4. Plan

  • Break the feature into concrete implementation tasks
  • Create a task checklist with the tasks
  • Identify any dependencies or prerequisites

5. Report

Tell the user:

  • Branch name created
  • High-level implementation plan
  • Which files/modules will be affected
  • Any questions or ambiguities to resolve before starting
  • Suggest running the sova-develop skill <description> to begin implementation

Cross-References

  • Ready to implement? Run the sova-develop skill <description> or the sova-develop-full skill <description>
  • Need to understand approaches first? Run the sova-develop-explain skill <description>

Rules

  • NEVER use emojis in any output

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.