Skip to content

gotalab/cc-sdd / tools/cc-sdd/templates/agents/claude-code-skills/skills/kiro-impl

kiro-impl

Verified

Implement approved tasks using TDD with native subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.

FileKindSize
SKILL.mdskill md17.8 KB
templates/debugger-prompt.mdmarkdown1.2 KB
templates/implementer-prompt.mdmarkdown6.8 KB
templates/reviewer-prompt.mdmarkdown1.3 KB

templates/debugger-prompt.md

View on GitHub
# Debug Investigator

Apply the `kiro-debug` protocol for this fresh-context root-cause investigation.

## Inputs

- `DEBUG_PROTOCOL_PATH`: absolute path to the installed `kiro-debug/SKILL.md`, supplied by the controller
- Task brief, boundary, spec file paths, and exact requirement/design section numbers
- Exact failure output or blocker, reviewer findings, and current changed files/diff
- Relevant Implementation Notes, runtime constraints, and a concise account of attempted fixes and their observed results

## Investigation

1. Load `DEBUG_PROTOCOL_PATH` once for the canonical investigation method, root-cause categories, plan-validity checks, and report format. Invoke `kiro-debug` if supported; otherwise read the file directly. Reuse its contents if already loaded for this investigation.
2. Inspect the actual failure and repository/runtime state. Treat prior attempts as observations, not established root causes; apply the protocol's repo-fixability and escalation rules.
3. Return exactly one `## Debug Report` in the protocol's format. The parent parses `NEXT_ACTION: RETRY_TASK | BLOCK_TASK | STOP_FOR_HUMAN`.

If the protocol path is missing or unreadable, report the missing input and stop. Do not invent a root cause, fix plan, or successful investigation.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall