benny-reproduce-poll
Direct polling instructions for dormant Benny repro and bounded-fix automation. Not a registered plugin skill.
- License 许可
- MIT
- 最近更新
- 2026-09-28
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- benny-reproduce-poll
- description
- Direct polling instructions for dormant Benny repro and bounded-fix automation. Not a registered plugin skill.
02 资源文件 3
- 参考文档references/control-adapter.md611 B
- 参考文档references/feature-map.example.md509 B
- 参考文档references/verify-existing-fix.md406 B
03 SKILL.md 正文
Reproduce and optionally fix accepted reports
Use the same fixed-cutoff, pagination, tuple ordering, overlap, canonical lease, report_id, retry, dead-letter, and operation-key rules as triage. If no marker exists, keep the report pending for a later poll. Accept exactly one schema-v1 marker at the exact root coordinates, with a recomputed matching report_id, an approved current or explicitly migrated identity, and verdict bug or performance. Quarantine wrong identities, conflicts, and unapproved rotations.
Before repository execution, revalidate the approved operational/config hash and adapter credentials/scopes. Run all repository commands, untrusted code, builds, and tests in an isolated worktree without connector credentials and with network denied by default. If enforcement is not observable, stop. Every exceptional host must be allowlisted in the setup receipt. Children receive no credentials or write tools and return typed proposals only.
Read the approved feature map and references/control-adapter.md. Reproduce the discriminating symptom twice through the real UI, capture bounded evidence, and verify an existing source branch or pull request before proposing a competing fix. A bounded fix may create a source-linked branch and draft pull request only; never merge or deploy.
Reconcile tracker, verdict, evidence, branch, and draft-PR operation keys before each action. After ambiguous timeouts, perform authoritative destination lookup; never replay while the result is unknown. The coordinator validates exact source/operations thread, repository, operation key, effect budget, and outbound minimization. Scan Slack, tracker, branch, commit, and draft-PR payloads for credentials and personal contact details; dead-letter instead of republishing a hit.
Write concise evidence inside the original source thread or configured operations thread. Never post at the source root. Persist only IDs, hashes, bounded status, and redacted failure reasons.
04 同仓库更多 Skills
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
unslop
Cut AI tells from any writing. Must always apply.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for $technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.