affaan-m avatar

Intent Driven Development

Turns vague feature requests into testable acceptance criteria before you write code. It inspects your repo first, asks minimal questions about things it can't infer, then produces observable criteria with verification methods. Choose Quick Capture for straightforward changes or Full Brief for anything touching auth, data migrations, or external APIs. It won't block you on trivial stuff, but it will flag when you're about to do something destructive without thinking it through. The real value is in how it separates technical facts it can discover from business constraints it can't, so you're not guessing what "done" means halfway through implementation.

skills.sh installs
4.8K
GitHub stars
300.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add affaan-m/ecc --skill intent-driven-development --agent claude-code

Installs into .claude/skills of the current project.

Files

Intent-Driven Development

Produce useful acceptance criteria without turning specification into ceremony. Inspect available context first, expose genuine ambiguity, and choose verification methods that fit the work and its risk.

When to Activate

  • User asks to clarify a feature, define acceptance criteria, or de-risk a change before implementation
  • Request touches security, authentication, persistent data, migrations, external APIs, or compliance
  • User wants to prepare a handoff artifact for another agent or team
  • Request is ambiguous enough that the expected outcome is not yet observable or testable
  • User explicitly invokes this skill with /intent-driven-development

Do not activate for trivial edits, straightforward one-line fixes, active debugging sessions, code review requests, or implementation requests whose acceptance conditions are already clear.

How It Works

Sponsors

Details

Repository
github.com/affaan-m/ecc
Categories
Security, Git & Pull Requests, Code Review & Quality, AI & Agent Building, Debugging
First seen
Jul 14, 2026

More from affaan-m/ecc

All 263

Recommended

More Security
1iii-hq avatariii-error-handlingiii-hq/iiiHandle iii engine and SDK errors across Node, Python, Rust, and browser workers. Use when interpreting error codes, retryability, RBAC denial, timeouts, handler4.7Kskills.sh installs
2ghostsecurity avatarghost-scan-secretsghostsecurity/skillsGhost Security - Secrets and credentials scanner. Scans codebase for leaked API keys, tokens, passwords, and sensitive data. Detects hardcoded secrets and gener4.7Kskills.sh installs
3github avatarsecret-scanninggithub/awesome-copilotGuide for configuring and managing GitHub secret scanning, push protection, custom patterns, and secret alert remediation. For pre-commit secret scanning in AI 4.6Kskills.sh installs
4ghostsecurity avatarghost-scan-depsghostsecurity/skillsGhost Security - Software Composition Analysis (SCA) scanner. Scans dependency lockfiles for known vulnerabilities, identifies CVEs, and generates findings with4.6Kskills.sh installs
5napoleond avatarclawdirect-devnapoleond/clawdirectBuild agent-facing web experiences with ATXP-based authentication, following the ClawDirect pattern. Use this skill when building websites that AI agents intera4.6Kskills.sh installs
6napoleond avatarinstaclawnapoleond/instaclawPhoto sharing platform for AI agents. Use this skill to share images, browse feeds, like posts, comment, and follow other agents. Requires ATXP authentication.4.6Kskills.sh installs