Context Driven Development
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If these files become inaccurate, stale, or intentionally misleading, future AI-assisted development could follow the wrong product, technical, or workflow assumptions.
The skill's core behavior is to create persistent context documents that future AI interactions may treat as authoritative.
establish a persistent, structured foundation that informs all AI interactions
Review and version-control the context files, and do not let untrusted contributors change them without normal code-review scrutiny.
The agent may summarize project structure, dependencies, and workflow patterns into new documentation files. This is expected for the skill, but the output should be checked for accuracy before use.
For existing projects, the skill directs the agent to inspect local repository files and history to generate context documents.
Analyze the codebase: - Read package.json, requirements.txt, go.mod, etc. - Look at existing README and docs - Check git history for patterns
Use it on repositories where you are comfortable with the agent reading project files and commit history, and review generated documents before relying on them.
Installing from a moving branch can fetch different content over time, even though the reviewed registry artifact itself is instruction-only.
The README documents an alternate user-run install path from a GitHub branch rather than a pinned commit or packaged release.
npx add https://github.com/wpank/ai/tree/main/skills/meta/context-driven-development
Prefer the reviewed registry install when possible, or pin and review the exact source revision before installing from GitHub.