一键在 Manus 中运行任何 Skill

speckit-superb-implementation-gate

星标2

分支0

更新时间2026年7月3日 16:16

Mandatory read-only pre-implementation gate. Reports test-first readiness while leaving task execution decisions with Spec Kit.

安装

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。

在 Manus 中运行

来源

RbBtSn0w

RbBtSn0w/gh-address-cr

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Implementation Gate

User Context

$ARGUMENTS

This command is read-only. It never changes spec.md, plan.md, tasks.md, task checkboxes, git state, or lifecycle state.

Step 1 - Resolve Required Artifacts

Resolve the active feature through the Spec Kit prerequisite helper. Require readable spec.md, plan.md, and tasks.md. If one is missing, report the missing artifact and return control to its owning Spec Kit command.

Step 2 - Load Test-First Guidance

Run:

bash .specify/extensions/superb/scripts/bash/resolve-skill.sh --skill test-driven-development

When the skill is available, apply its durable discipline: write a focused failing test, observe the expected failure, make the minimum production change, then observe the focused and regression checks pass.

When it is unavailable, apply this bridge-native minimum instead:

Every behavior-changing task identifies a focused test command.
The test must fail for the intended missing behavior before production work.
The smallest implementation makes that test pass.
Relevant regression checks pass before the task is marked complete.

The missing skill reduces guidance depth but does not block the standard Spec Kit implementation path.

Step 3 - Report Readiness

Inspect incomplete tasks and report:

missing artifacts or unresolved prerequisites;
whether upstream or native minimum TDD guidance applies;
behavior-changing tasks without a focused test command or explicit test-first expectation.

Do not interpret task scheduling metadata. The owning Spec Kit implementation flow and active agent runtime decide how tasks execute.

Return only a readiness result:

## Implementation Readiness

**Artifacts:** READY | BLOCKED
**TDD guidance:** UPSTREAM | NATIVE MINIMUM
**Incomplete tasks:** [task ids]
**Missing test-first readiness:** [task ids or none]
**Blocking findings:** [findings or none]

Readiness checked; return control to `/speckit.implement`.

同仓库更多 Skills

同仓库

gh-address-cr

RbBtSn0w/gh-address-cr

Use when a GitHub Pull Request has unresolved review threads, pending reviews, stale/outdated threads, local findings ingestion, or needs mandatory final-gate proof in one PR-scoped session.

2026-07-092

speckit-superb-brainstorm

RbBtSn0w/gh-address-cr

Optional after-specify refinement gate. Bridges an installed obra/superpowers brainstorming skill into the active Spec Kit spec.md without creating a second design document or replacing speckit.specify.

2026-07-032

speckit-superb-check

RbBtSn0w/gh-address-cr

Diagnose the five Superpowers disciplines used by Superb and report the focused hook and standalone-command contract.

2026-07-032

speckit-superb-critique

RbBtSn0w/gh-address-cr

Read-only implementation critique against active Spec Kit artifacts.

2026-07-032

speckit-superb-debug

RbBtSn0w/gh-address-cr

Apply systematic root-cause investigation to the current failing task.

2026-07-032

speckit-superb-finish

RbBtSn0w/gh-address-cr

Complete branch handoff after Spec Kit convergence and fresh checks.

2026-07-032

Implementation Gate

User Context

$ARGUMENTS

This command is read-only. It never changes spec.md, plan.md, tasks.md, task checkboxes, git state, or lifecycle state.

Step 1 - Resolve Required Artifacts

Step 2 - Load Test-First Guidance

Run:

bash .specify/extensions/superb/scripts/bash/resolve-skill.sh --skill test-driven-development

When it is unavailable, apply this bridge-native minimum instead:

Every behavior-changing task identifies a focused test command.

The test must fail for the intended missing behavior before production work.

The smallest implementation makes that test pass.

Relevant regression checks pass before the task is marked complete.

The missing skill reduces guidance depth but does not block the standard Spec Kit implementation path.

Step 3 - Report Readiness

Inspect incomplete tasks and report:

missing artifacts or unresolved prerequisites;

whether upstream or native minimum TDD guidance applies;

behavior-changing tasks without a focused test command or explicit test-first expectation.

Do not interpret task scheduling metadata. The owning Spec Kit implementation flow and active agent runtime decide how tasks execute.

Return only a readiness result:

## Implementation Readiness **Artifacts:** READY | BLOCKED **TDD guidance:** UPSTREAM | NATIVE MINIMUM **Incomplete tasks:** [task ids] **Missing test-first readiness:** [task ids or none] **Blocking findings:** [findings or none] Readiness checked; return control to `/speckit.implement`.

name	speckit-superb-implementation-gate
description	Mandatory read-only pre-implementation gate. Reports test-first readiness while leaving task execution decisions with Spec Kit.
compatibility	Requires spec-kit project structure with .specify/ directory
metadata	{"author":"github-spec-kit","source":"superb:commands/implementation-gate.md"}

name	speckit-superb-implementation-gate
description	Mandatory read-only pre-implementation gate. Reports test-first readiness while leaving task execution decisions with Spec Kit.
compatibility	Requires spec-kit project structure with .specify/ directory
metadata	{"author":"github-spec-kit","source":"superb:commands/implementation-gate.md"}