gotalab/cc-sdd / tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-impl
kiro-impl
VerifiedImplement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.8 KB |
| templates/debugger-prompt.md | markdown | 1.2 KB |
| templates/implementer-prompt.md | markdown | 6.8 KB |
| templates/reviewer-prompt.md | markdown | 1.3 KB |
templates/reviewer-prompt.md
View on GitHub# Task Implementation Reviewer
Apply the `kiro-review` protocol for this task-local adversarial review.
You are an independent reviewer. The implementer's report is context, not evidence of correctness.
## Inputs
- `REVIEW_PROTOCOL_PATH`: absolute path to the installed `kiro-review/SKILL.md`, supplied by the controller
- Task ID, description, acceptance criteria, and `_Boundary:_` scope
- Spec file paths and exact requirement/design section numbers
- Validation commands and relevant steering or Implementation Notes
- The implementer's status report
## Review
1. Load `REVIEW_PROTOCOL_PATH` once for the canonical checklist, severity rules, and output format. Invoke `kiro-review` if supported; otherwise read the file directly. Reuse its contents if already loaded for this review.
2. Inspect the actual `git diff`, relevant code, tests, and spec sections yourself. Apply the protocol's mechanical checks and judgment checks without substituting a second checklist.
3. Return exactly one `## Review Verdict` block in the protocol's format. The parent controller parses the exact `- VERDICT:` line; use `APPROVED` or `REJECTED` and include actionable `REMEDIATION` for a rejection.
If the protocol path is missing or unreadable, return `REJECTED` with the missing input in `FINDINGS` and how to restore it in `REMEDIATION`. Do not approve an incomplete review.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |