orch-add-feature
Helps your agent build brand-new software features from start to finish. It coordinates research, planning, implementation, and testing.
What it does
This tool helps build a brand-new feature for a computer program from start to finish. It researches, plans, writes tests, implements the code, and reviews everything before completion.
When to use it
- ✓When you want to add a capability that doesn't exist yet.
- ✓When building something entirely new for a program.
- ✓If the goal is to implement a new feature from scratch.
Example of what to ask your AI
“Add OAuth2 login functionality to the notification system.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The tool follows a step-by-step process. It starts by researching, then plans the tasks, writes tests to ensure everything works, implements the necessary code, and finally reviews everything before approval.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add affaan-m/ECC --skill orch-add-featureOr download just the file:
curl -L https://raw.githubusercontent.com/affaan-m/ECC/main/skills/orch-add-feature/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
orch-add-feature
Actor · action · target: orch · add · feature. Thin wrapper over the shared
engine in orch-pipeline.
When to Use
- The user wants a capability that does not exist yet ("add", "build", "implement", "support …").
- It is net-new behavior — not a correction (
orch-fix-defect) and not an alteration of existing behavior (orch-change-feature).
Operation settings
- Default size floor: standard — run Research + Plan unless clearly small.
- Phase mask: 0 → 1 → 2 → 4 → 5 → 6 (skip 3 Scaffold; that is MVP-only).
- First move (phase 4): write new failing tests for the new behavior, then implement to green.
How It Works
- Run the
orch-pipelineengine with the settings above. - Classify size first; small / trivial features collapse toward 4 → 5 → 6.
- Stop at Gate 1 (plan approval) and Gate 2 (pre-commit).
- Add
security-reviewerif the feature touches a security trigger.
Related:
/feature-devis a standalone version of this flow.orch-add-featurediffers by sharing theorch-pipelineengine — the size classifier and the two gates — with the rest of the family, so it right-sizes trivial features to 4 → 5 → 6.
Example
orch-add-feature: add OAuth2 login to nws-poller
→ research existing auth libs → plan task_list [GATE 1: approve]
→ TDD each task → code-review (+ security-reviewer: auth path)
→ commit [GATE 2: confirm]
FAQ
What's the difference between adding a feature and fixing a bug?
Adding a feature creates something new that didn't exist. Fixing a bug corrects something that isn't working as intended.
What are 'tests' in this context?
These are automatic checks that ensure the new code works correctly and doesn't break other parts of the program.
What are 'gates'?
These are checkpoints where you or someone else needs to approve the work before proceeding to the next stage.
Details
Original description by the author
Orchestrate building a brand-new feature end to end — research, plan, TDD implementation, review, and gated commit — by delegating each phase to the matching ECC agent. Use when adding a capability that does not exist yet.
repo: affaan-m/ECC
Popularity
- GitHub stars
- 280k
- Ranking position
- #247
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
accessibility
Helps your agent create interfaces that everyone can use. Ensures websites and apps work well for people with disabilities, like those who are blind or have reduced mobility.
affaan-m/ECC
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC
Similar skills
git-workflow-and-versioning
Organizes code work using Git. Helps save progress, manage different versions, and avoid conflicts when working in a team.
addyosmani/agent-skills
observability-and-instrumentation
Adds tools to monitor what the code does in production. Helps understand if something went wrong and why, making fixes easier.
addyosmani/agent-skills
github-pr-workflow
Prepares GitHub pull requests, ensuring code quality and documentation.
paperclipai/paperclip