jabrena/plinth / skills/004-commands-installation
004-commands-installation
VerifiedUse when you need to install the embedded project commands into command directories (.github/commands, .claude/commands, .cursor/command, .codex/commands), selecting the destination interactively and copying the embedded command definitions from project assets. This should trigger for requests such as Install embedded commands; Bootstrap .cursor/command; Bootstrap .claude/commands; Copy project commands; Install project command suite. Part of Plinth Toolkit
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.9 KB |
| assets/commands/benchmark.md | markdown | 2.0 KB |
| assets/commands/close-spec.md | markdown | 1.7 KB |
| assets/commands/create-acceptance-criteria.md | markdown | 6.2 KB |
| assets/commands/create-adr.md | markdown | 1.3 KB |
| assets/commands/create-diagram.md | markdown | 1.4 KB |
| assets/commands/create-feature-branch.md | markdown | 3.0 KB |
| assets/commands/create-spec.md | markdown | 3.5 KB |
| assets/commands/create-worktree.md | markdown | 3.1 KB |
| assets/commands/explore-design.md | markdown | 4.6 KB |
| assets/commands/explore-problem.md | markdown | 6.7 KB |
| assets/commands/implement-spec.md | markdown | 11.6 KB |
| assets/commands/onboarding.md | markdown | 5.9 KB |
| assets/commands/profile.md | markdown | 1.9 KB |
| assets/commands/update-issue.md | markdown | 1.8 KB |
| references/004-commands-installation.md | markdown | 3.5 KB |
assets/commands/profile.md
View on GitHub---
description: 'Coordinate a reproducible Java profiling and optimization lifecycle.'
argument-hint: '[target]'
model: 'inherit'
agent: 'plinth-java-performance'
tools:
- 'Read'
- 'Write'
- 'Edit'
- 'Bash'
metadata:
author: 'Juan Antonio Breña Moral'
version: '0.19.0'
---
# profile
Coordinate a Java profiling lifecycle from reproducible baseline through evidence-backed optimization verification.
## Usage
```text
/profile <application-or-module> [issue|plan|openspec-change|suspected-problem] [runtime-command] [workload]
```
## Accepted inputs
- Application, module, or repository path
- Optional issue, implementation plan, OpenSpec change, or suspected performance problem
- Runtime command and representative workload
- Optional existing baseline or profiling artifacts
## Owner and skills
- Owner: `@plinth-java-performance`
- Associated skills: `@161-java-profiling-detect`, `@162-java-profiling-analyze`, `@163-java-profiling-refactor`, and `@164-java-profiling-verify`
## Workflow
1. Record runtime, environment, workload, and baseline metadata.
2. Use profiling detection to collect reproducible evidence.
3. Analyze hotspots and rank findings by impact, confidence, and risk.
4. Ask for user approval before selecting an optimization target.
5. Delegate application-code changes to the appropriate Java/framework coder agent.
6. Repeat an equivalent measurement and compare against the baseline.
7. Report the outcome as verified, inconclusive, or regressed with evidence.
## Output
- Baseline metadata
- Profiling artifacts and findings
- Prioritized optimization recommendation
- Delegation record
- Before/after comparison
- Verified, inconclusive, or regressed outcome
## Safeguards
- Do not optimize without user approval.
- Do not claim improvement from non-equivalent measurements.
- Do not let `@plinth-java-performance` implement application-code changes directly.
- Keep baseline, evidence, delegation, and verification artifacts traceable.
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 |