Skip to main content

yezhwi/superpowers-engineering-harness

SkillsMP 已收集 yezhwi/superpowers-engineering-harness 中的 10 个 Skill。打开任一 Skill 可查看来源和详情。

最近记录的来源活动
SkillsMP 收录数据更新
已收集 skills
10
GitHub 星标
2
GitHub Forks
0

这个仓库中的 skills

职业分类待补全

已展示 10 / 10 个已收集 Skill。

职业分类
未分类
描述

Use when starting or resuming a task in a repo with .harness/ state, when unsure which harness phase comes next, or when asked to run the Engineering Harness loop end-to-end. Orchestrates the fixed state machine; MUST NOT implement business code itself.

原文语言:英语

更新
职业分类
未分类
描述

Review Q2/Q3 changed business paths for production diagnosability and persist structured review input.

原文语言:英语

更新
职业分类
未分类
描述

Turn a User Requirement into a Task Contract: Acceptance Criteria, Requirements, Invariants, Risks, Verification Plan. Produces .harness/requirements.yaml and .harness/invariants.yaml and advances task state CREATED -> SPECIFYING -> PLANNED. This skill MUST…

原文语言:英语

更新
职业分类
未分类
描述

Adversarial review of a Task Contract: construct failure scenarios, attempt to violate Requirements and Invariants. Produces .harness/findings/FND-nnn.yaml files with status=PROPOSED only. This skill MUST NOT confirm bugs, review code style, or suggest…

原文语言:英语

更新
职业分类
未分类
描述

Reproduce an adversarial finding through the mandatory lifecycle PROPOSED -> REPRODUCING -> CONFIRMED (bug reproduced, test RED) -> FIXING -> FIXED (test GREEN) -> VERIFIED (full regression) -> CLOSED, or REJECTED. Each status has one meaning and its own…

原文语言:英语

更新
职业分类
未分类
描述

Review verified diff for unnecessary implementation complexity before adversarial review.

原文语言:英语

更新
职业分类
未分类
描述

Run before implementation to record minimal necessary approach using Harness Decision Ladder.

原文语言:英语

更新
职业分类
未分类
描述

Use when quality_gate.py has returned PASS or BLOCKED and the loop must decide to finish (CONVERGED/DONE), continue iterating, or escalate. Applies v0.1 escalation rules with no scoring.

原文语言:英语

更新
职业分类
未分类
描述

Use when entering VERIFYING or before GATING and fresh evidence is required. Decides which evidence types the task needs, then runs collect_evidence.py; MUST NOT judge pass/fail itself.

原文语言:英语

更新
职业分类
未分类
描述

Use when task state is GATING and a go/no-go decision is needed before CONVERGED. Runs quality_gate.py and maps its exit code to state transitions; MUST NOT assess quality by judgement.

原文语言:英语

更新
已展示 10 / 10 个已收集 Skill。