agentleFS
Sign inStart free
samsam007bsamsam007b/claude-code-standards-kit/skills/new-feature/SKILL.md

new-feature

Skill2 starsChanged 8 months agoMITView on GitHub

Complete RESEARCH → CONTRACT → CODE → AUDIT workflow for a new feature. Identifies applicable standards, activates contracts, and runs audit agents on completion.

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, 7 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 7

    Distinctive

    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. Very specific:

    Read workflows/WORKFLOW-NEW-FEATURE.md for the full process

    line 29
  2. Distinctive:

    Search across the 29 contracts to find which apply.

    line 41
  3. Distinctive:

    Run the following to identify relevant contracts:

    line 43
  4. Distinctive:

    Check these domains for your feature:

    line 48
  5. Distinctive:

    Read each relevant contract and extract the specific rules that apply.

    line 56
  6. Distinctive:

    Run the audit agents relevant to the feature.

    line 78
  7. Distinctive:

    Observable truth: All audit scores above their thresholds (Security ≥70, Code-Quality ≥75, Accessibility ≥80 for EU).

    line 93
  8. Very specific:

    Update CHANGELOG.md with the new feature under [Unreleased]

    line 101
  9. Distinctive:

    Create a PR with audit scores in the description

    line 102
  10. Very specific:

    Ensure CI passes (verify-kit.sh equivalent for the project)

    line 103

“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 — Complete Feature Workflow

Usage: /new-feature [description of feature]

This skill runs the full RESEARCH → CONTRACT → CODE → AUDIT cycle for the feature described in $ARGUMENTS.

Gate 0 — Scope

Define the feature before writing any code.

  1. Read workflows/WORKFLOW-NEW-FEATURE.md for the full process
  2. Draft a Shape Up Pitch with:
    • Problem: What user need does this solve?
    • Appetite: How much effort is this worth?
    • No-Gos: What is explicitly out of scope?

Observable truth: Scoping doc exists before implementation starts.

Gate 1 — Research (identify applicable contracts)

Search across the 29 contracts to find which apply.

  1. Run the following to identify relevant contracts:
grep -l "$ARGUMENTS" contracts/ 2>/dev/null | head -10 || echo "No exact match — use semantic search"
  1. Check these domains for your feature:
    • Any form input? → CONTRACT-SECURITY.md §3 (Zod validation), CONTRACT-ACCESSIBILITY.md §2 (WCAG 1.3.1)
    • Any API call? → CONTRACT-API-DESIGN.md, CONTRACT-RESILIENCE.md
    • Any UI component? → CONTRACT-DESIGN.md, CONTRACT-ACCESSIBILITY.md
    • Any data storage? → CONTRACT-SUPABASE.md, CONTRACT-DATABASE-MIGRATIONS.md
    • Any TypeScript? → CONTRACT-TYPESCRIPT.md (always)
    • Any test? → CONTRACT-TESTING.md (always)
  2. Read each relevant contract and extract the specific rules that apply.

Observable truth: List of applicable contracts and specific rules documented in CLAUDE.md "Active contracts" section.

Gate 2 — Implement

Code with active hooks enforcing contracts.

Before coding, ensure .claude/settings.json references the SQWR hooks.

During implementation, watch for hook warnings:

  • hook-contract-compliance.sh fires on every Write — address warnings immediately
  • hook-no-dangerous-html.sh fires on TSX writes — never bypass without DOMPurify

Observable truth: npm run build && npm test exits 0 (or equivalent for your stack).

Gate 3 — Audit

Run the audit agents relevant to the feature.

Ask Claude: "Run agents/AGENT-SECURITY-AUDIT.md on this feature"
Ask Claude: "Run agents/AGENT-CODE-QUALITY-AUDIT.md"

For UI features, also run:

Ask Claude: "Run agents/AGENT-ACCESSIBILITY-AUDIT.md"
Ask Claude: "Run agents/AGENT-DESIGN-AUDIT.md"

Fix all findings above the blocking threshold before continuing.

Observable truth: All audit scores above their thresholds (Security ≥70, Code-Quality ≥75, Accessibility ≥80 for EU).

Gate 4 — Ship

Prepare the feature for review and merge.

  1. Update CHANGELOG.md with the new feature under [Unreleased]
  2. Create a PR with audit scores in the description
  3. Ensure CI passes (verify-kit.sh equivalent for the project)

Observable truth: PR created with CHANGELOG entry and audit scores visible.

Reference

Full workflow details: workflows/WORKFLOW-NEW-FEATURE.md Source methodology: METHODOLOGY.md — "search first, implement after"

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