- Home
- Skills
- Code Quality & Review
- IntentWeft
IntentWeft
Trace project requirements to evidence, uncover contradictions, and turn material risks into practical verification steps.
Free
Works with the AI Agents you already use
About this skill
IntentWeft helps AI coding agents keep project intent connected to the work they perform. It connects requirements to actual evidence, highlights contradictions, and recommends practical corrections and checks.
What it does
- Preflight a plan against the relevant requirements and constraints.
- Review a change for realistic failure scenarios and trace each material finding to supporting evidence.
- Verify a correction using observed results rather than assumed success.
- Prepare a handoff with scope, evidence, decisions, and unresolved questions.
How to use
Provide the task, relevant requirements, and available project evidence. Ask for a preflight, review, verification, or handoff. A finding can include its trigger, impact, correction, and verification step.
Limits
It cannot guarantee detection of every problem or certify security, legal outcomes, or correctness. It only uses evidence and tools available to the host. File access and persistence depend on host permissions. The optional Python helper checks selected file fingerprints and report structure; it does not prove semantic correctness.
Source and documentation: https://github.com/ufodia/intentweft
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 1 day ago
- Free with an Agensi account
Nothing to install. It runs in your AI agent.
- Optional
Python 3.10+
Permissions
Project file access depends on the host and your approval. The optional helper reads explicitly selected files and does not make network requests.