agentleFS
jeremymcsjeremymcs/skills/new-feature/SKILL.md

new-feature

Skill8 starsChanged 6 months agoMITView on GitHub

Research the current project and recommend new or next features based on repository context, product surface, docs, issues, tests, TODOs, recent work, and user goals. Use when the user asks what to build next, wants feature recommendations, or needs a prioritized roadmap from the current codebase.

41 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

10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 9

    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:

    Use this skill when the user wants recommended new or next features for the current project.

    line 10
  2. Very specific:

    Read README, AGENTS.md, CONTRIBUTING, DESIGN, roadmap docs, ADRs, and package manifests if present.

    line 17
  3. Distinctive:

    Prefer features that are small enough to start soon and meaningful enough to demo.

    line 26
  4. Distinctive:

    Avoid speculative features that are not supported by project evidence.

    line 27
  5. Distinctive:

    Do not recommend dependency churn as a feature unless it unlocks user-visible value.

    line 28
  6. Distinctive:

    Default ranking factors: user value, evidence strength, effort, risk, and fit with the project direction.

    line 30
  7. Distinctive:

    If using external research, say what was checked and link sources.

    line 69
  8. Distinctive:

    Do not invent users, roadmap commitments, metrics, or business priorities.

    line 70
  9. Distinctive:

    Ask one targeted question only if the project has too little context to rank recommendations responsibly.

    line 71
  10. Distinctive:

    Do not create issues or PRs unless the user explicitly asks.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 39 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

New Feature

Use this skill when the user wants recommended new or next features for the current project.

The output should be actionable recommendations, not a broad product essay.

Workflow

  1. Establish the project shape.
    • Read README, AGENTS.md, CONTRIBUTING, DESIGN, roadmap docs, ADRs, and package manifests if present.
    • Inspect source layout, app routes, tests, examples, scripts, and recent commits.
    • Review open issues or PRs when the project issue tracker is available.
  2. Identify signals.
    • Existing product capabilities and obvious gaps.
    • Repeated TODOs, FIXME comments, failing/skipped tests, missing docs, missing workflows, or incomplete UX paths.
    • Recent work that suggests a natural next step.
    • Operational needs such as setup, observability, testing, security, accessibility, or release automation.
  3. Generate candidate features.
    • Prefer features that are small enough to start soon and meaningful enough to demo.
    • Avoid speculative features that are not supported by project evidence.
    • Do not recommend dependency churn as a feature unless it unlocks user-visible value.
  4. Rank recommendations.
    • Default ranking factors: user value, evidence strength, effort, risk, and fit with the project direction.
    • Mark uncertainty explicitly when the repo lacks product context.
  5. Present the result.
    • Lead with the top 3-5 recommendations.
    • For each recommendation include:
      • Feature name
      • Why now
      • Evidence from the project
      • Suggested first slice
      • Effort and risk
    • End with a short "Not recommended yet" section when there are tempting but premature ideas.

Output Format

## Recommended Next Features

### 1. Feature name

Why now:

Evidence:

Suggested first slice:

Effort/risk:

### 2. Feature name

...

## Not Recommended Yet

- Idea: reason to defer.

Guardrails

  • Cite concrete repo signals, file paths, issue references, or observed behavior.
  • If using external research, say what was checked and link sources.
  • Do not invent users, roadmap commitments, metrics, or business priorities.
  • Ask one targeted question only if the project has too little context to rank recommendations responsibly.
  • Do not create issues or PRs unless the user explicitly asks.

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.