菜单
Given a feature description, function signature, or existing test suite, surfaces edge cases worth testing across six categories. Explanation depth scales to user skill level. Optionally focuses on critical areas when critical-areas.json is present.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Instrument a Playwright run with OpenTelemetry and emit a run.json artifact correlating every test to the outbound HTTP requests it made — "which test made which request?" — with zero manual bookkeeping in test code. Trace-only v1 contract, additive-safe for future pytest/k6/node producers. Self-contained (bundles its own dataclasses and span reader).
Playwright JSON results → Markdown + JSON test report. Summarises passed, failed, flaky, and skipped counts with a per-failure error block and a summary table. Exits non-zero when any test failed so the CI step fails on real failures. Complements canary-fail-fast (which aborts early); this skill summarises the full run at the end.
Surface test failures fast and loud — audit a Playwright config for fail-fast knobs (maxFailures/forbidOnly/retries) and print a loud, categorized failure digest to the CI log + ::error annotations at run end, failing the step so the signal can't be missed. Self-contained (bundles its own Playwright JSON parser and failure categorizer).
Analyses a test suite for CI readiness: coverage depth, flakiness, assertion quality, critical path coverage, and suite runtime. Accepts documented failures (quarantined tests with linked open issues count as verified). Investigates config/auth failures using the consuming repo's declared user_catalog_skill.
Risk-based test prioritisation. Given a codebase or diff, identifies which areas carry the most risk using git churn, downstream dependents, business-critical signals, and existing coverage depth. Produces a ranked list with recommended test types per area.
For a given test, function, or code path, traces downstream effects and produces a severity label. Investigates config/auth failures using the consuming repo's declared user_catalog_skill. Optionally focuses on critical paths when critical-areas.json is present.
| name | canary-edge-case-discovery |
| description | Given a feature description, function signature, or existing test suite, surfaces edge cases worth testing across six categories. Explanation depth scales to user skill level. Optionally focuses on critical areas when critical-areas.json is present. |
Surfaces the edge cases that tests typically miss: the inputs and conditions that work in demos but break in production.
After writing happy-path tests: "what else should I test?"
When reviewing a feature for robustness
As Phase 2 of /canary-test-pipeline
When asked "what edge cases should I cover?"
Provide one of:
A feature description: "points accrual on tier upgrade"
A function signature: accruePoints(memberId: string, amount: number): Promise<Result>
A test file path: tests/loyalty/points.spec.ts
Or nothing — Canary will infer from open files and recent context
If .canary/critical-areas.json is present, focus edge case discovery on the
highest-risk areas first (rank_score ≥ 0.6).
For each category, generate specific, actionable cases — not generic advice.
Zero, negative, max integer, empty string, null, undefined, one-off-by-one. For amounts: 0, 1, MAX_SAFE_INTEGER, -1, 0.001 (floating point). For strings: empty string, whitespace-only, max-length + 1 character.
Concurrent writes to the same resource. Double-submit (user clicks twice). Stale reads after an update. Lock contention. Out-of-order async responses.
DST transition times. Dates at midnight UTC vs local time. Non-ASCII characters in names and addresses. RTL text in string fields. Locale-specific number formats (1.000,00 vs 1,000.00). Emoji in text fields.
Request timeout mid-flight. Dropped connection after partial response. Retry storms (client retries while server is still processing). Response truncation.
Extra fields the schema doesn't expect. Missing required fields. Wrong types (string where number expected). SQL or script injection strings. Deeply nested objects. Arrays where scalars expected.
Keyboard-only navigation paths. Missing ARIA labels. Focus trap conditions. Screen reader text for dynamic content. Colour contrast for status indicators. (Only include if the input is a UI feature or test.)
Governed by --level flag. Infer from context when not specified:
User is asking from a test file or uses technical language → sdet
User describes themselves as new or asks "why" questions → junior
User mentions manual testing or is non-technical → manual
| Level | Audience | Output style |
|---|---|---|
sdet | Senior SDETs | Bullet list of cases only |
junior | Junior SDETs | Cases + one-line why this matters |
manual | Manual testers | Cases + numbered reproduction steps |
sdet example)Edge cases — points accrual on tier upgrade
Boundary values
· amount = 0
· amount = MAX_SAFE_INTEGER
· memberId empty string
· memberId with special characters
Race conditions
· concurrent accrual calls for the same memberId
· double-submit within 100ms
...
Suggested next: /canary-write-test "add edge case tests for accruePoints boundary values"
```text
## Flags
- `--level sdet|junior|manual` — output depth (default: inferred)
## Related skills
- `/canary-critical-areas` — produces `critical-areas.json` used for focus
- `/canary-write-test` — generates tests for the surfaced cases
- `/canary-test-pipeline` — Phase 2