03-assert — Claude Code skill: what it does, how to install
03-assert runs a project's assertions and fixes code until they pass, with optional checks on architecture and a running UI. Useful as the last gate before you push.
MIT ★ 571 updated 2026-10-29
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-dev@aidd-frameworkWhat 03-assert does
The skill runs a project's own assertions and edits code until they pass. You get a pass or fail verdict on the work. Every applicable facet runs by default: assert (coding) always, assert-frontend when the work has a UI and a frontend is up (it resolves the URL itself), assert-architecture only when conformance is requested.
What each facet does with a failure differs. Coding and frontend fix and re-run until green. Architecture only names the places where code drifts from the documented architecture; it never patches anything, so don't wait for a fix from it. A facet whose precondition is missing gets skipped with a reason recorded. Before an action runs, the skill reads that action's file under actions/, not just the table.
The frontend facet keeps assets/task-template.md updated through its fix loop. Hand it failing CI checks and the fixing facets gather every failed check, repair each reproducible one locally, then repeat all applicable commands in the final sweep. Pushing stays with the caller, and only after green. Checks that live only in CI stay unverified.
What it helps with
- drive failing project assertions back to green
- find where code drifted from the documented architecture
- check a running UI and fix the behaviour that is off
- work through a batch of failed CI checks locally
- get a clear pass or fail verdict on the work
Example prompts for the agent
- Run
03-asserton the changes insrc/apiand keep going until the assertions pass. - Validate the work in
src/componentswith the frontend facet; the UI is already running. - Run
03-assertwithassert-architectureand tell me where the code breaks the documented design.
How to install 03-assert
1Plugin marketplace
/plugin marketplace add ai-driven-dev/framework/plugin install aidd-dev@aidd-frameworkThis installs the whole aidd-dev plugin with all its skills
2Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 03-assert -a claude-code3Manually: put the files in place
~/.claude/skills/03-assert/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/03-assert/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 03-assert -a codex2Manually: put the files in place
.agents/skills/03-assert/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 03-assert -a cursor2Manually: put the files in place
.cursor/skills/03-assert/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ai-driven-dev/framework plugins/aidd-dev/skills/03-assert2Manually: put the files in place
.github/skills/03-assert/SKILL.md1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 03-assert -a gemini-cli2Platform CLI
gemini skills install https://github.com/ai-driven-dev/framework --path plugins/aidd-dev/skills/03-assertManually: put the files in place
.devin/skills/03-assert/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 03-assert -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about 03-assert
How do I install 03-assert in Claude Code?
Use the marketplace: run /plugin marketplace add ai-driven-dev/framework, then /plugin install aidd-dev@aidd-framework.
What does 03-assert do?
It runs the project's assertions and fixes code until they pass, and on request checks architecture conformance or a running UI. The result is a pass or fail verdict.
Does 03-assert write tests?
No. It works with the assertions the project already has and repairs code against them. Writing or reviewing tests is out of scope.
Source text
SKILL.md · MIT
--- name: 03-assert description: Assert the work behaves by iterating the project's coding assertions until they pass, plus optional architecture and frontend facets. Use to validate an implementation. Not for reviewing or writing tests. argument-hint: work | scope --- # Skill: assert Validate that the work behaves as intended: run the project's assertions, iterating and fixing until they pass. ## Actions | # | Action | Facet | | --- | --------------------- | ----------------------------------------------------------- | | 01 | `assert` | Run the project's coding assertions, fixing until they pass | | 02 | `assert-architecture` | Report where the code breaks the documented architecture | | 03 | `assert-frontend` | Inspect the running UI, fixing until the behavior is right | Run every applicable facet by default, or one when named. Coding (`01`) always applies; add `03` when the work has a UI and a frontend is running, the facet resolving the URL itself; run `02` only when architecture conformance is asked for. Skip a facet whose precondition is absent, with a noted reason. Ask only when the intent is genuinely ambiguous. Before running an action, read its file in `actions/`, not only the table or assets. ## Transversal rules - Gate: it returns a pass or fail verdict on the work. - Fix loop: the coding and frontend facets fix and re-run until they pass. The architecture facet only reports, never fixes. - Stop only when every selected assertion passes a final clean sweep. - On supplied CI failures, fixing facets collect all failed checks, repair each reproducible failure locally, and rerun every applicable command in the final sweep; the caller pushes once after green if authorized, with CI-only checks unverified. ## Assets - `assets/task-template.md`: the tracking file the frontend facet fills across its fix loop.
© AI-Driven Dev · MIT · ai-driven-dev/framework