agentleFS
Sign inStart free
qivora-labsqivora-labs/agentinit/.claude/skills/new-feature/SKILL.md

new-feature

Skill1 starsChanged 12 days agoMITView on GitHub

Plan a feature, wait for confirmation, then implement it and run the project checks.

42 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use evidence-driven-testing, greploop-apps and 10 more.

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.
  • jaydubya818Skill

    evidence-driven-testing

    Capture observable runtime proof with video, screenshots, or measured output. Use when a change needs evidence beyond test reports.

    Also in 6 projects that use this

  • jaydubya818Skill

    greploop-apps

    Run greploop through @greptile-apps when the normal trigger rejects a large PR. Use only with the companion greploop skill.

    Also in 4 projects that use this

  • VercelSkill

    before-and-after

    Add existing screenshots or screen recordings to a GitHub pull request as a before/after or preview block. Use when a PR needs visual media attached to its description. Browser navigation and capture belong to agent-browser.

    Also in 6 projects that use this

  • BboyfaroukSkill

    greploop

    Iteratively improves a PR until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes, re-triggers review, and repeats. Use when the user wants to fully optimize a PR against Greptile's code review standards.

    Also in 6 projects that use this

  • u9401066Skill

    bug-fix

    Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.

    Also in 3 projects that use this

  • SvampenSkill

    init-project

    Generates a tailored .claude/project-config.md for the current project. Asks about project type, quality check commands, documentation paths, insight tags, and review strictness.

    Also in 4 projects that use this

  • +1 more from jaydubya818

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add one feature. Plan the files, wait for confirmation, then implement that plan.

    line 9
  2. Very specific:

    Read AGENTS.md and ARCHITECTURE.md.

    line 15
  3. Distinctive:

    After the user confirms, implement only the confirmed plan.

    line 17
  4. Distinctive:

    If a test-library rule is active, add tests for the feature's observable behavior and follow that rule.

    line 18
  5. Distinctive:

    NEVER: write files before the user confirms the file plan.

    line 27
  6. Distinctive:

    NEVER: create or edit a path that is not in the confirmed plan.

    line 28
  7. Distinctive:

    NEVER: run network commands, install packages, or read secrets.

    line 29
  8. Distinctive:

    If a check fails, fix the feature and run that check again.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 40 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

Purpose

Add one feature. Plan the files, wait for confirmation, then implement that plan.

Input

The user's input: a feature name and a short description. If either part is missing, ask for it and stop.

Steps

  1. Read AGENTS.md and ARCHITECTURE.md. For each file you will edit, read the closest AGENTS.md in that file's directory tree. The closest file wins where they disagree.
  2. Propose a file plan: each path to create or edit, its responsibility, and the active rules that apply. Then stop and wait for the user to confirm. Do not create or edit files before that confirmation.
  3. After the user confirms, implement only the confirmed plan. Follow the active rules.
  4. If a test-library rule is active, add tests for the feature's observable behavior and follow that rule.
  5. Run pnpm typecheck.
  6. Run pnpm lint.
  7. Run pnpm test.

Output

List the files created or edited, the decisions you made, and the result of each check that ran.

Guardrails

  • NEVER write files before the user confirms the file plan. Silence is not confirmation.
  • NEVER create or edit a path that is not in the confirmed plan.
  • NEVER run network commands, install packages, or read secrets.
  • If a check fails, fix the feature and run that check again. NEVER weaken a test to make it pass.

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