From axis-core
Author behavior evals for a change in five categories — Functional, Security, Performance, Accessibility, Drift — pinned to threshold floors per risk level (AXIS-26 §8.2, §8.3).
How this skill is triggered — by the user, by Claude, or both
Slash command
/axis-core:eval-authorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Every requirement in `delta.md` MUST trace to at least one eval. Eval depth scales with risk (§6.3, §8.2).
Every requirement in delta.md MUST trace to at least one eval. Eval depth scales with risk (§6.3, §8.2).
| Category | Asks | Typical form |
|---|---|---|
| Functional | Does the system do what the spec says? | YAML cases, BDD .feature, pytest, jest |
| Security | Does the system avoid CWE-mapped weaknesses? | Targeted exploit attempts, fuzz inputs |
| Performance | p95 latency, throughput, resource budgets | Load script + assertion |
| Accessibility | WCAG 2.2 AA criteria for user-facing surfaces | axe-core, manual checklist |
| Drift | Does runtime still match spec? | Schema diffs, telemetry fingerprints |
| Risk | Behavior pass rate | Latency p95 | Constitutional |
|---|---|---|---|
| low | ≥95% | — | 0 MUST violations |
| moderate | ≥98% | within 10% of baseline | 0 MUST; SHOULD requires ADR |
| high | ≥99.5% | within 5% of baseline | 0 violations; full CWE Top 25 clear; threat model signed; canary stable |
delta.md, propose at least one eval. For high-risk security or PII requirements, propose Functional + Security..axis/changes/<id>/evals/<category>/<slug>.<ext>..axis/evals/config.yaml).Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub thaithienvanid/axis-method --plugin axis