Full Stack Feature
ReviewAudited by ClawScan on May 1, 2026.
Overview
This is a coherent instruction-only workflow skill for full-stack feature development, but it can guide broad code and migration changes and delegates to other skills or agents that users should review.
This skill appears safe to install as an instruction-only project workflow aid. Before using it on an important codebase, review the referenced skills, commands, and agents, keep changes in version control, and manually approve database migrations or production-impacting changes.
Findings (3)
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.
The agent could make broad changes to the codebase or database schema as part of implementing a feature.
The skill may guide creation or modification of application code and database migration artifacts. This is expected for full-stack feature work, but it is high-impact enough to require normal user review.
Command: `/new-feature` ... Output: Implemented API routes, data models, migrations, and business logic passing unit tests.
Use version control, inspect diffs, and require explicit approval before applying migrations, modifying production-impacting code, or deploying changes.
Installing from a mutable remote source could fetch content that differs from the reviewed registry artifact.
The README documents a user-run install command from a mutable GitHub branch path. This is not hidden or automatic, but users should verify the source before running it.
npx add https://github.com/wpank/ai/tree/main/skills/meta/full-stack-feature
Prefer the registry install path when possible, or pin and review the remote source before installing from GitHub.
Work may be handed to other local agents whose instructions and permissions affect the resulting code changes.
The skill explicitly routes work to other agents. That delegation is central to the skill's purpose, but the artifacts do not define trust, permission, or data-boundary rules for those agents.
| 4. API Design | `api-design-principles` | `/create-api-route` | `ai/agents/api/` | ... | 6. Backend | `api-development`, `database-migration-patterns` | `/new-feature` | `ai/agents/migration/` |
Review any referenced agents or commands before use, and avoid delegating sensitive project work to untrusted or unreviewed agents.