Agent skill
implement
Use when the user has a clear, small task ready for direct implementation from conversation context without needing a plan or Arc pipeline. Arc's Simple tier executor.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/implement-cmtkdot-arc
SKILL.md
Implement
Execute implementation directly from conversation context and task description. This is Arc's true Simple tier executor — no plan, spec, or /arc-start state required.
Key difference from /arc:core:execute: This skill is standalone. It does not require .arc/ state, plans, or beads. It works from conversation context alone.
Source: Conversation context + input + mentioned files.
Instructions
Step 1: Create Task Graph Immediately
ONLY use what's already available:
- The user's input
- Conversation history (already in context)
DO NOT:
- Read files unless the user explicitly asks you to
- Grep or explore the codebase
- Spawn sub-agents or delegate work — do ALL implementation directly yourself
Create tasks immediately from context. Include file paths in task descriptions so they can be read during execution.
For each work item, create a task:
TaskCreate({
"subject": "Fix auth token validation",
"description": "Full implementation details from context",
"activeForm": "Fixing auth token validation"
})
Set dependencies with addBlockedBy to identify which tasks depend on others.
Step 2: Execute Tasks Sequentially
For each task (in dependency order):
- Claim:
TaskUpdate({ taskId: "N", status: "in_progress" }) - Read files as needed: Use Read tool on file paths from task description
- Implement: Make changes based on context
- Verify: Run any task-specific verification
- Complete:
TaskUpdate({ taskId: "N", status: "completed" }) - Next: Find next unblocked task via TaskList
Step 3: Run Exit Criteria
Before declaring completion:
- Run the verification (tests, commands, etc.)
- If pass → "Exit criteria passed"
- If fail → fix issues and retry
Step 4: Loop Until Done
Continue until:
- All tasks completed AND
- Exit criteria pass
Say "Exit criteria passed" when complete.
Error Handling
| Scenario | Action |
|---|---|
| Context unclear | Ask for clarification |
| Exit criteria fail | Fix issues and retry |
| Context compacted | TaskList → continue |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?