ワンクリックで
radisha-create-skill
Use when creating a new skill for radisha - validates content, checks for conflicts, and integrates with existing skills
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Use when creating a new skill for radisha - validates content, checks for conflicts, and integrates with existing skills
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Given a TheRock nightly build (URL or run-id), return the rocm-systems pin_sha used in that build
Check whether a given rocm-systems commit is included in a specific TheRock nightly build
Find the first TheRock nightly build that includes a given rocm-systems commit
Reviews Pull Requests or local diffs with an 8-agent fan-out covering static analysis, dead code, code smells + quality (naming, complexity, single-responsibility, magic numbers), language rules (C++/Python/CMake), architecture, simplification, performance (hot-path classification, allocations, locks, I/O), and undefined behaviour (signed overflow, lifetime, strict aliasing, data races, sanitizer coverage; C/C++/unsafe-Rust only). Use when the user asks to "review this PR", "review the diff", "audit this branch", "/pr-review", or when staging changes before push.
Walk through a PR review interactively, one finding at a time. Generate review via pr-review, then for each issue present analysis + proposed inline comment, let user accept/edit/skip, accumulate into a PENDING GitHub review, submit at end.
Use when user wants to list, analyze, review, or summarize GitHub PR comments on a pull request number or URL
| name | radisha-create-skill |
| description | Use when creating a new skill for radisha - validates content, checks for conflicts, and integrates with existing skills |
Meta-skill for creating new radisha skills. Validates proposed skill content, checks for conflicts with existing skills, and handles integration.
Use this skill when:
┌─────────────────────────────────────────────────────────────────┐
│ User provides skill content │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌───────────────────────┐
│ Phase 1: Analyze │
│ - Usefulness │
│ - Alignment │
│ - Conflicts │
└───────────────────────┘
│
▼
┌───────────────────────┐
│ Phase 2: Report │
│ Present findings to │
│ user, suggest fixes │
└───────────────────────┘
│
▼
┌───────────────────────┐
│ User approves? │
└───────────────────────┘
│ │
no yes
│ │
▼ ▼
┌─────────┐ ┌───────────────────────┐
│ Stop │ │ Phase 3: Create skill │
└─────────┘ └───────────────────────┘
│
▼
┌───────────────────────┐
│ Phase 4: Integrate │
│ - Update radisha-help │
│ - Update README │
│ - Update related skills│
└───────────────────────┘
│
▼
┌───────────────────────┐
│ Report completion │
└───────────────────────┘
When user provides skill content, analyze these aspects:
Answer: Will this skill help the AI perform better?
| Question | Good Sign | Bad Sign |
|---|---|---|
| Does it provide structure? | Clear phases, checkpoints | Vague guidelines |
| Does it reduce ambiguity? | Explicit triggers, outputs | "Use when appropriate" |
| Does it prevent mistakes? | Common mistakes section | No anti-patterns |
| Is it actionable? | Specific steps to follow | Abstract principles only |
Check how the skill fits with existing radisha skills:
| Relationship | Check |
|---|---|
| Precursor | Does it come before other skills? (e.g., exploration → planning) |
| Successor | Does it come after other skills? (e.g., planning → programming) |
| Parallel | Does it work alongside other skills? |
| Independent | Is it standalone? |
Check for conflicts with existing skills:
For each existing skill:
- Does the new skill overlap in purpose?
- Are there contradictory instructions?
- Is there ambiguity about when to use which?
Common conflicts to check:
| Existing Skill | Potential Conflict |
|---|---|
ask | Quick explanations vs. structured analysis |
planning-* | Which planning type applies? |
programming-* | Language-specific overlap? |
testing-* | Testing approach conflicts? |
Verify the skill follows radisha patterns:
| Pattern | Check |
|---|---|
| Tool names | Uses AskUserQuestion not AskQuestion |
| Task tracking | References platform's task tools |
| Plan mode | Platform-agnostic language |
| Output location | Follows planning/ convention if applicable |
| Formatting | Tables, ASCII diagrams, not prose-heavy |
| Checkpoints | User validation at key points |
Present analysis to user in this format:
## Skill Analysis: [Skill Name]
### Usefulness
| Aspect | Assessment |
|--------|------------|
| Structure | [Clear/Vague] |
| Triggers | [Explicit/Ambiguous] |
| Anti-patterns | [Present/Missing] |
| Actionability | [High/Medium/Low] |
**Verdict:** [Useful / Needs work / Not recommended]
### Alignment
- **Relationship:** [Precursor to X / Successor to Y / Independent]
- **Workflow position:** [Where it fits in the skill chain]
### Conflicts
| Existing Skill | Conflict | Resolution |
|----------------|----------|------------|
| [skill] | [overlap description] | [how to fix] |
### Issues to Fix
1. [Issue 1 with suggested fix]
2. [Issue 2 with suggested fix]
### Recommended Category
`skills/[category]/[skill-name]/SKILL.md`
---
**Proceed with creation?** (with fixes applied)
Wait for user approval before proceeding.
Choose category based on skill purpose:
| Purpose | Category prefix | Path |
|---|---|---|
| Planning workflows | planning- | skills/planning-[name]/ |
| Language-specific coding | programming- | skills/programming-[lang]/ |
| Testing approaches | testing- | skills/testing-[name]/ |
| Code exploration | exploration- | skills/exploration-[name]/ |
| Library-specific | libraries- | skills/libraries-[name]/ |
| Git workflows | git- | skills/git-[name]/ |
| Radisha management | radisha- | skills/radisha-[name]/ |
| Standalone utility | Top-level | skills/[name]/ |
Ensure skill follows this structure:
---
name: category/skill-name
description: One-line description - when to use this skill
---
# Skill Title
Brief overview (1-2 sentences).
<IMPORTANT>
Critical rules that must always be followed.
</IMPORTANT>
## When to Use
Clear triggers for invoking this skill:
- Trigger 1
- Trigger 2
## Process / Phases
Step-by-step workflow with:
- Numbered phases
- Checkpoints for user validation
- Clear deliverables
## Output
What gets produced:
- File location (if applicable)
- Format/structure
## Common Mistakes
| Mistake | Fix |
|---------|-----|
| [anti-pattern] | [correct approach] |
## Integration with Other Skills
| After This Skill | Use |
|------------------|-----|
| [scenario] | [next skill] |
Before creating, apply all fixes identified in Phase 2:
mkdir -p skills/[category]/[skill-name]
Write SKILL.md to the directory.
After creating the skill, update these files:
radisha-help/SKILL.mdAdd to appropriate section:
**[Category] skills:**
- `category/skill-name` - Brief description
README.mdThree updates required:
A. Skill Categories table:
### [Category] Skills
| Skill | Description |
|-------|-------------|
| `category/skill-name` | Description |
B. Detailed section:
#### `category/skill-name`
[Detailed description with key features]
C. Directory structure:
├── [category]/
│ └── [skill-name]/
│ └── SKILL.md
If conflicts were found, update related skills to disambiguate:
Example: When creating exploration-explore-code, we updated ask skill:
## When NOT to Use
- **Systematic code exploration** → use `exploration-explore-code`
After all integration:
## Skill Created: [category/skill-name]
**Files created:**
- `skills/[category]/[skill-name]/SKILL.md`
**Files updated:**
- `skills/radisha-help/SKILL.md` - Added to skill list
- `README.md` - Added to tables and directory structure
- [Other updated files if any]
**Integration:**
- Workflow position: [where it fits]
- Related skills: [how it connects]
The skill is now ready to use.
Before completing, verify:
name and descriptionAskUserQuestion, etc.)radisha-help updated with skill referenceREADME.md tables updatedREADME.md detailed section addedREADME.md directory structure updated| Mistake | Fix |
|---|---|
| Creating without analysis | Always do Phase 1-2 first |
| Skipping conflict check | Read existing skills before creating |
| Wrong tool names | Use AskUserQuestion, TaskCreate, etc. |
| Forgetting README updates | Update all three sections |
| Forgetting radisha-help update | Add skill reference to radisha-help/SKILL.md |
| No user approval | Always present analysis, wait for approval |
| Wrong category | Match purpose to existing categories |
| Category prefix | Purpose | Examples |
|---|---|---|
planning- | Task planning workflows | planning-feature, planning-bugfix, planning-refactor |
programming- | Language-specific coding | programming-cpp, programming-python, programming-cmake-best-practices |
testing- | Testing approaches | testing-testplan, testing-gtest-gmock, testing-pytest |
exploration- | Code understanding | exploration-explore-code |
libraries- | Library-specific knowledge | libraries-amd-smi |
git- | Git workflows | git-prepare-pull-request, pr-review |
radisha- | Radisha management | radisha-update, radisha-create-skill |
ask | Quick explanations | (standalone) |