Quality Root Skill
SkillDev toolsRun make code-quality from the monorepo root, covering all modules. Never run it per-module.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Quality Root Skill skill
What this skill tells your AI
The instructions your AI receives, as published by thalesgroup/fred in .claude/skills/quality-root/SKILL.md and read by ahel’s review.
Run make code-quality from the monorepo root (/home/dimi/Work/swift), which covers all
modules in dependency order: libs/fred-core, libs/fred-sdk, libs/fred-runtime,
libs/fred-agents, apps/control-plane-backend, apps/knowledge-flow-backend, apps/frontend.
Running it per-module is a known failure mode — cross-module issues only appear from the root.
Steps
cdto the monorepo root (find it by walking up from cwd until you find the top-levelMakefilethat orchestrates sub-projects).- Run
make code-qualitywith a generous timeout (allow up to 10 minutes for a cold run). - Parse the output:
- If all modules pass: report success with a one-line summary per module.
- If any module fails: extract the exact error lines with file:line references, group them by module, and present them as a prioritised fix list.
- If
$ARGUMENTSnames a specific module (e.g.knowledge-flow-backend), still run the full root check but highlight that module's results at the top of the report.
What to look for beyond ruff/tsc errors
After the tool run, also scan the raw output for these softer signals that tools don't flag as errors but that indicate real problems:
# type: ignorecomments that suppressreportMissingImports— the module probably doesn't exist yet.- Basedpyright
reportRedeclaration— a duplicate symbol, often from an unreviewed merge. - Prettier
[warn]lines — formatting drift that will cause the next CI run to fail.
Output format
## Quality gate — <date>
| Module | Status | Issues |
|--------|--------|--------|
| libs/fred-core | ✅ pass | — |
| apps/knowledge-flow-backend | ❌ fail | 2 basedpyright errors |
...
### Failures
**apps/knowledge-flow-backend**
- `structures.py:417` — reportRedeclaration: duplicate validator `_normalize_retry_initial_interval`
Open team decision — auto-fix on pass: Should this skill offer to auto-run
ruff format --fixandprettier --writefor formatting-only failures, or always report-only and let the developer run the fix manually? Agree on this before wiring it into CI.
Signals
- GitHub stars
- 61
- Forks
- 32
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
quality-root- Source
- github.com/thalesgroup/fred