regression-test-gen
Suggests regression coverage scoped to changed stack behavior, grouped by test layer. Use when a bug fix, refactor or migration is understood and you need to decide which tests prove it stays fixed.
- License 许可
- MIT
- 所属仓库
- Eliyce/paqad-ai
- 最近更新
- 2026-11-13
- Stars
- ★ 8
- Forks
- 0
01 前言 Front Matter
- name
- regression-test-gen
- metadata
- { "cacheable": "true", "model_tier": "medium", "paqad-meta": "skill.meta.yaml", "output_format": "markdown" }
- description
- Suggests regression coverage scoped to changed stack behavior, grouped by test layer. Use when a bug fix, refactor or migration is understood and you need to decide which tests prove it stays fixed.
02 资源文件 3
- 参考文档agents/openai.yaml124 B
- 参考文档references/regression-layer-map.md296 B
- 参考文档skill.meta.yaml371 B
03 SKILL.md 正文
What It Does
Generates regression recommendations that stay tightly scoped to changed behavior and are grouped by test layer so follow-up verification work is deliberate and efficient.
Use This When
Use this after a bug fix, refactor, or migration once the changed behavior is understood and you need to decide what regression coverage should prove it stays fixed.
Inputs
- Read the changed behavior, existing tests, and claimed verification scope first.
- Read the stack-specific testing guide that matches the project.
- Read
references/regression-layer-map.mdbefore proposing new coverage.
Procedure
- List the concrete behaviors changed by the request and ignore unrelated nearby surfaces.
- Map each changed behavior to the narrowest meaningful test layer that can catch regression.
- Reuse existing suites, fixtures, and patterns before suggesting new harnesses.
- Group recommendations by unit, integration, end-to-end, or manual verification layer.
- Call out any changed behavior that should remain manual only and explain why.
Output Contract
- Return sections named
Unit,Integration,End-to-End, andManual Verificationin that order. - Under each section, list only the changed behaviors that belong to that layer.
- If a layer has nothing to add, write
<Layer>: none.
Escalate / Stop Conditions
- Ask when the available test harness is unknown and would materially change the layer recommendation.
- Warn when a requested regression check is broader than the changed behavior and likely to create noise.
- Do not recommend generic full-suite reruns as a substitute for behavior-focused regression coverage.
Resources
references/regression-layer-map.mdruntime/capabilities/coding/stacks/laravel/references/tools/testing.mdagents/openai.yaml
04 同仓库更多 Skills
sample-skill
Sample bundled skill fixture
processing-invoices
Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.
processing-invoices
Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.
understand-idea
Chat and Claude Code: Step 1 of the discover journey: clarifies the goal, who benefits, success and constraints into the idea block. Use when the journey directs it to step 1, not directly.
size-work
Chat and Claude Code: Suggest a size for a ticket from comparable finished work, as a labelled suggestion the team still owns. Use it when someone asks "how big is this?", "roughly how much work is ABC-12?", or wants a backlog item sized. It finds the team's sizing scale at first use, picks two to five of the closest finished tickets with links, and gives a size or range with the drivers behind it and a confidence of low, medium or high, lowered and explained when the area's documents are template text. Every result is labelled a suggested size, never a date or a commitment. It writes nothing into the size field unless the user says "set it", and it refuses to overwrite an existing size unless the user asks to replace it. Produces the sizing block of the record.
refine-ticket
Chat and Claude Code: Improve one or more existing tracker tickets without losing the author's intent. Use it when someone wants a ticket read, diagnosed and tidied up ("this ticket is vague", "fix up ABC-12", "split this, it's too big"). It reads each ticket in full and snapshots it with its last-updated time, says what is wrong with evidence, and proposes a field-by-field before and after change set limited to summary, description, labels, parent, links and new child tickets on a split. It writes nothing until an explicit "apply it" bound to that exact change set, re-checks the ticket for conflicting edits just before writing, never replaces rich descriptions with plain text, never deletes or closes a ticket, and reads each ticket back after applying. Produces the existing and changes blocks of the record.