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
- NemesLaszlo/claude-code-harnesstheir own version, first seen Nov 8, 2026
- ice-lfernandes/claude-spring-architecttheir own version, first seen Nov 7, 2026
- nerviz-ai/nerviztheir own version, first seen Nov 7, 2026
- michaelshimeles/rstacktheir own version, first seen Nov 1, 2026
- qbicus/skillstheir own version, first seen Oct 25, 2026
- ricci-labs/twisetheir own version, first seen Oct 20, 2026
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.
jaydubya818Skillevidence-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
jaydubya818Skillgreploop-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
VercelSkillbefore-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
BboyfaroukSkillgreploop
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
u9401066Skillbug-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
SvampenSkillinit-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
Other versions41 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 41
- jhd3197/ServerKit★ 1.8ksame name
- michaelshimeles/rstack★ 1.4ksame name
- michaelshimeles/skills★ 1.4ksame name
- fpindej/netrock★ 234same name
- X-isdoingreat/canvas-pilot★ 123same name
- AnjanJ/rails_error_dashboard★ 93same name
- dan-the-dev/xp-developer-skills★ 31same name
- Fadi88/one-man-startup★ 16same name
- ice-lfernandes/claude-spring-architect★ 11same name
- nerviz-ai/nerviz★ 11same name
31 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- create-issueSkill
- dumb-it-downSkill
- falsify-projectSkill
- from-issueSkill
- github-repo-hygieneSkill
- overengineering-reviewSkill
- project-doc-scaffolderSkill
- system-diagrammerSkill
- test-writerSkill
- to-adrSkill
- verify-projectSkill
- zero-techdebtSkill
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
- Distinctive: line 10
Use this skill when the user wants recommended new or next features for the current project.
- Very specific: line 17
Read README, AGENTS.md, CONTRIBUTING, DESIGN, roadmap docs, ADRs, and package manifests if present.
- Distinctive: line 26
Prefer features that are small enough to start soon and meaningful enough to demo.
- Distinctive: line 27
Avoid speculative features that are not supported by project evidence.
- Distinctive: line 28
Do not recommend dependency churn as a feature unless it unlocks user-visible value.
- Distinctive: line 30
Default ranking factors: user value, evidence strength, effort, risk, and fit with the project direction.
- Distinctive: line 69
If using external research, say what was checked and link sources.
- Distinctive: line 70
Do not invent users, roadmap commitments, metrics, or business priorities.
- Distinctive: line 71
Ask one targeted question only if the project has too little context to rank recommendations responsibly.
- Distinctive: line 72
Do not create issues or PRs unless the user explicitly asks.
“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.
Files
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
- 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.
- Read
- 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.
- 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.
- 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.
- 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.
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
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.

