Best use case
add-new-feature is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Teams using add-new-feature should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/add-new-feature/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How add-new-feature Compares
| Feature / Agent | add-new-feature | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
This skill provides specific capabilities for your AI agent. See the About section for full details.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Add New Feature (SAM Workflow)
You MUST convert the user's request into **durable SAM artifacts** under the repo:
- `plan/feature-context-{slug}.md` (discovery)
- `plan/codebase/{FOCUS}.md` (optional, analysis)
- `plan/architect-{slug}.md` (architecture/design spec)
- `plan/tasks-{N}-{slug}.md` (executable task plan with Agents, deps, and verification)
<feature_request>
$ARGUMENTS
</feature_request>
---
## Orchestrator Discipline
You are an orchestrator. You coordinate work across specialized agents. Prefer delegating discovery and analysis.
---
## Phase 1: Discovery (feature-researcher)
Delegate to `feature-researcher` to produce `plan/feature-context-{slug}.md` and questions for resolution.
---
## Phase 2: Codebase Analysis (codebase-analyzer)
If helpful, delegate to `codebase-analyzer` for one or more focus areas:
- patterns
- architecture
- testing
- conventions
Outputs go to `plan/codebase/`.
---
## Phase 3: Architecture Spec (python-cli-design-spec)
Delegate to `python-cli-design-spec` to write `plan/architect-{slug}.md` based on:
- the feature context doc
- codebase analysis docs (if created)
- existing repo constraints (`CLAUDE.md`, `pyproject.toml`, etc.)
---
## Phase 4: Task Decomposition (swarm-task-planner)
Delegate to `swarm-task-planner` to:
- create `plan/tasks-{N}-{slug}.md`
- ensure every task has:
- **Status**, **Dependencies**, **Priority**, **Complexity**, **Agent**
- Acceptance Criteria (3+)
- Verification Steps (3+)
---
## Phase 5: Plan Validation Gate (plan-validator)
Delegate to `plan-validator`. If it returns `BLOCKED`, do not proceed.
---
## Phase 6: Context Manifest (context-gathering)
Delegate to `context-gathering` with the task file path. It must insert a `## Context Manifest` into the task file.
---
## Success Outcome
When all phases complete, provide the user:
- the feature slug
- the task file path
- next step: run the `implement-feature` skill with the slug or task file pathRelated Skills
advanced-features
Implement advanced task features - Priorities, Tags, Due Dates, Reminders, Recurring Tasks, Search, Filter, and Sort. Use when adding Phase 5 advanced functionality. (project)
advanced-features-2025
Advanced 2025 Claude Code plugin features. PROACTIVELY activate for: (1) Agent Skills with progressive disclosure (2) Hook automation (PreToolUse, PostToolUse, etc.) (3) MCP server integration (4) Repository-level configuration (5) Team plugin distribution (6) Context efficiency optimization Provides cutting-edge plugin capabilities and patterns.
Addon/Feature System Development Guide
**Version:** 1.0
add-feature
Scaffold complete feature with types, repository, API routes, components, store actions, and tests. Use when adding major new functionality like water tracking, sleep tracking, etc.
add-feature-hook
Creates TanStack Query hooks for API features with authentication. Use when connecting frontend to backend endpoints, creating data fetching hooks.
meta:cli-feature-creator
CLI Feature Creator wizard for adding new aaa CLI commands. Use when user asks to "add aaa command", "create CLI feature", "add CLI command", or needs to extend the aaa CLI with new functionality.
correlation-methylation-epiFeatures
This skill provides a complete pipeline for integrating CpG methylation data with chromatin features such as ATAC-seq signal, H3K27ac, H3K4me3, or other histone marks/TF signals.
1k-feature-guides
Feature development guides for OneKey. Use when adding new chains, socket events, notifications, pages, or routes. Covers blockchain integration, WebSocket subscriptions, push notifications, and navigation patterns.
genomic-feature-annotation
This skill is used to perform genomic feature annotation and visualization for any file containing genomic region information using Homer (Hypergeometric Optimization of Motif EnRichment). It annotates regions such as promoters, exons, introns, intergenic regions, and TSS proximity, and generates visual summaries of feature distributions. ChIPseeker mode is also supported according to requirements.
Clarify Epic/Feature/UserStory/Task ticketing guidance in SKILL
No description provided.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.