hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-issue
hyper-issue
VerifiedUse this skill when the user wants a confirmed finding or a piece of decided work recorded as an implementation-ready issue, wants a fixed batch of open issues selected and grouped into disjoint work lanes, or names issue numbers such as `#1~3` to run as a batch. It investigates only enough to make the issue self-contained, writes the issue in English for a fresh agent with a machine-readable scope block, produces a batch manifest, and hands the lanes to the hyper orchestrator when work should follow. Do not use for implementing the work itself, for general documentation, or for a plan file.
| File | Kind | Size |
|---|---|---|
| SKILL.ko.md | markdown | 18.0 KB |
| SKILL.md | skill md | 16.5 KB |
| assets/evals/hyper-issue-cases.jsonl | other | 12.6 KB |
| references/batch-manifest.ko.md | markdown | 4.2 KB |
| references/batch-manifest.md | markdown | 3.9 KB |
| references/issue-body-template.ko.md | markdown | 4.2 KB |
| references/issue-body-template.md | markdown | 4.1 KB |
| rules/batch-selection.ko.md | markdown | 7.7 KB |
| rules/batch-selection.md | markdown | 7.1 KB |
| rules/issue-contract.ko.md | markdown | 7.9 KB |
| rules/issue-contract.md | markdown | 7.4 KB |
references/issue-body-template.ko.md
View on GitHub# Issue Body Template
본문을 쓸 때 이 참고 파일을 사용한다. 골격을 복사해 모든 자리표시자를 바꾼다. `##` 이름과 `hyper:` 키는 적힌 그대로 유지한다. 제목과 자리표시자를 바꾼 내용은 모두 영어로 쓴다(`rules/issue-contract.md` 2a절). 제목은 커밋 제목 형태 `type(scope): imperative summary`를 따른다.
## Contents
- 골격
- 작성 예
- 규칙
## 골격
```markdown
## What
<한 단락. 무엇이 잘못됐는지 또는 무엇을 원하는지. 누가 영향을 받고 무엇이 달라지는지.>
## Evidence
- `<path>:<line>` - 이것이 보여 주는 것
- `<command>` -> 관측한 출력 중 중요한 줄만
<위 내용 중 추론한 것이 있으면 Assumption 줄:>
- Assumption: <the inferred statement> - Confirm by: <what would confirm it>
## Cause
<bug: 위 경로에 연결한 확인된 원인. 증상, 유발 조건, 원인을 구분해 적는다.>
## Intended behavior
<feature 또는 task: 결정된 동작. 오류 경로와 바뀌지 않는 동작 포함.>
## Scope
<변경 경계를 한두 문장으로. 무엇을 고치고, 더하고, 지우는지.>
```yaml
hyper:
touches:
- <경로 또는 글롭>
depends_on: []
conflicts_with: []
lane_hint: <kebab-case>
verify: "<그대로의 명령>"
size: <s | m | l>
```
## Out of scope
- <독자가 포함됐다고 오해할 만한 것>
## Acceptance
- [ ] <명령과 기대 결과가 붙은 이분법 검사>
- [ ] <오류 경로 검사>
## Verify
```sh
<hyper.verify의 그대로의 명령>
```
Pass: <작업이 끝났을 때 출력이 어떤 모습인지>.
```
## 작성 예
실제 이슈는 영어로 쓰므로 작성 예도 영어 그대로 둔다.
Title: `fix(orders): return 409 on idempotency key replay`
```markdown
## What
`POST /api/orders` returns 500 instead of 409 when the same idempotency key is replayed within the retry window. Callers retrying after a timeout create duplicate orders.
## Evidence
- `src/api/orders.ts:88` - the idempotency key is read after the insert attempt
- `bun test src/api/orders.test.ts` -> `1 fail: replays a duplicate key` with `duplicate key value violates unique constraint`
- `docs/contracts/orders.md:14` - the contract requires 409 on replay
## Cause
The insert runs before the key lookup at `src/api/orders.ts:88`, so a replay reaches the database unique constraint and the unhandled error becomes a 500. The contract lookup was added later at `:95` and never moved ahead of the insert.
## Scope
Move the key lookup before the insert and return 409 with the stored order id when a replay is found. The insert path and the response shape for new orders stay unchanged.
```yaml
hyper:
touches:
- src/api/orders.ts
- src/api/orders.test.ts
depends_on: []
conflicts_with: []
lane_hint: orders-idempotency
verify: "bun test src/api/orders.test.ts"
size: s
```
## Out of scope
- Changing the retry window length
- Backfilling duplicate orders already created
## Acceptance
- [ ] `bun test src/api/orders.test.ts` passes, including the replay case asserting 409 and the original order id
- [ ] A first request still returns 201 with a new order id
## Verify
```sh
bun test src/api/orders.test.ts
```
Pass: every case green, and the replay case logs `409` rather than `500`.
```
## 규칙
- 본문은 홀로 선다. "앞서 논의한 대로"도, 이해에 필요한 링크도 없고, 인용한 출력 말고는 모두 영어다.
- 인용은 짧게, 출처를 붙이고, 비밀은 가린다.
- 본문 하나에 `hyper:` 블록 하나이며 `## Scope`의 유일한 펜스 `yaml` 블록이다.
- `verify`는 이슈가 다르게 말하지 않는 한 브라우저, 자격증명, 네트워크 호출 없이 실행 가능해야 한다.
## Sources
> 확인 2026-11-07.
| Claim | Source |
|---|---|
| 본문 절, `hyper:` 키, 작성 예의 형태 | 이 패키지가 이슈 작성 선행 사례 위에 세운 설계, 2026-11-07 |
| 로그와 세션이 사라진 뒤에도 쓸 수 있는 본문 | [kdy1-scripts add-issue](https://github.com/kdy1/kdy1-scripts) |
### 근거 등급
`LOCAL` - 템플릿과 예시는 이 저장소의 이슈 흐름을 위해 이 패키지가 직접 작성한 것이다.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |