メニュー
Decision guide for choosing the right specialized agent for each task type
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
| name | Selecting Agents |
| description | Decision guide for choosing the right specialized agent for each task type |
| when_to_use | before dispatching work to specialized agents, when multiple agents could apply |
| version | 1.0.0 |
Use the right agent for the job. Each agent is optimized for specific scenarios and follows a focused workflow.
This skill helps you choose which specialized agent to use based on the task at hand.
For automatic agent selection: When executing implementation plans, use the /cipherpowers:execute command which applies this skill's logic automatically with hybrid keyword/LLM analysis. Manual selection using this skill is for ad-hoc agent dispatch outside of plan execution.
When selecting agents (manually or automatically), you must analyze the task requirements and context, not just match keywords naively.
DO NOT use naive keyword matching:
DO use semantic understanding:
Examples of INCORRECT selection:
Examples of CORRECT selection:
Selection criteria:
Red flags that indicate you're selecting incorrectly:
When to use: After code changes that affect documentation
Scenarios:
Skill used: maintaining-docs-after-changes
Command: /cipherpowers:verify docs
Key characteristic: Reactive to code changes - syncs docs with current code state
When to use: Complex, multi-layered debugging requiring deep investigation
Scenarios:
Skills used: systematic-debugging, root-cause-tracing, defense-in-depth, verification-before-completion
Key characteristic: Opus-level investigation for complex scenarios, not simple bugs
When to use: Rust tasks during plan execution via /cipherpowers:execute
Scenarios:
Key characteristic: Minimal context (147 words), follows plans literally, reports BLOCKED when stuck
When to use: Rust development outside of plan execution
Scenarios:
Skills used: test-driven-development, testing-anti-patterns, code-review-reception
Key characteristic: Full workflow with TDD, code review, extensive guidance (~5000+ words with @ expansion)
When to use: Non-Rust tasks during plan execution via /cipherpowers:execute
Scenarios:
Key characteristic: Minimal context (~150 words), follows plans literally, reports BLOCKED when stuck
When to use: Development outside of plan execution
Scenarios:
Skills used: test-driven-development, testing-anti-patterns, code-review-reception
Key characteristic: Full workflow with TDD, code review, extensive guidance (~5000+ words with @ expansion)
When to use: Reviewing code changes before merging
Scenarios:
Skill used: conducting-code-review
Command: /cipherpowers:code-review
Key characteristic: Structured review process with severity levels (BLOCKING/NON-BLOCKING)
When to use: Evaluating implementation plans before execution
Scenarios:
/cipherpowers:plan/cipherpowers:executeSkill used: verifying-plans
Command: /cipherpowers:verify plan
Key characteristic: Evaluates plan against 35 quality criteria across 6 categories (Security, Testing, Architecture, Error Handling, Code Quality, Process)
| Confusion | Correct Choice | Why |
|---|---|---|
| "Just finished feature, need docs" | technical-writer + /summarise | technical-writer syncs API/feature docs, /summarise captures learning |
| "Quick docs update" | technical-writer | All doc maintenance uses systematic process |
| "Fixed bug, should document" | /summarise command | Capturing what you learned, not updating technical docs |
| "Changed README" | Depends | Updated feature docs = technical-writer. Captured work summary = /summarise |
| "Production debugging done" | /summarise command | Document the investigation insights and lessons learned |
Scenario 1: Added new API endpoint → technical-writer - Code changed, docs need sync
Scenario 2: Spent 3 hours debugging Azure timeout → /summarise command - Capture the investigation, decisions, solution
Scenario 3: Both apply - finished user authentication feature → technical-writer first - Update API docs, configuration guide → /summarise second - Capture why you chose OAuth2, what issues you hit
Scenario 4: Random test failures in CI → ultrathink-debugger - Complex timing/environment issue needs deep investigation
Scenario 5: Simple bug fix in Rust → rust-agent - Standard development workflow with TDD
Scenario 6: Just finished writing implementation plan → plan-review-agent - Validate plan before execution
Scenario 7: About to execute plan, want quality check → plan-review-agent - Ensure plan is comprehensive and executable
/execute (minimal context, literal execution)/execute (minimal context, literal execution)Use boolean decision trees instead of imperatives for 100% compliance under pressure
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches cipherpowers:code-review-agent subagent to review implementation against plan or requirements before proceeding
Establish workflow boundary checklists with clear pass/fail criteria and escalation procedures
Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification