Agent skill
done
Completion marker for the /do workflow. Outputs hierarchical execution summary showing Global Invariants respected and all Deliverables completed. Called by /verify after all criteria pass, not directly.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/done-doodledood-claude-code-plugins-2
SKILL.md
/done - Completion Marker
Goal
Output a completion summary showing what was accomplished, organized by the Manifest hierarchy.
Input
$ARGUMENTS = completion context (optional)
What to Do
Read the execution log and manifest. Output a summary that shows:
- Intent - What was the goal
- Global Invariants - All respected
- Deliverables - Each with its ACs, all passing
- Key changes - Files modified, commits made
- Tradeoffs applied - How preferences were used
Output Format
## Execution Complete
All global invariants pass. All acceptance criteria verified.
### Intent
**Goal:** [from manifest]
### Global Invariants
| ID | Description | Status |
|----|-------------|--------|
| INV-G1 | ... | PASS |
### Deliverables
#### Deliverable 1: [Name]
| ID | Description | Status |
|----|-------------|--------|
| AC-1.1 | ... | PASS |
**Key Changes:**
- [file] - [what changed]
---
### Tradeoffs Applied
| Decision | Preference | Outcome |
|----------|------------|---------|
### Files Modified
| File | Changes |
|------|---------|
---
Manifest execution verified complete.
Principles
- Mirror manifest structure - Hierarchy should match: Intent → Global Invariants → Deliverables
- Show evidence - Link changes to deliverables, describe behavioral changes (not just file lists)
- Adapt detail to complexity - Simple task = condensed output. Complex task = full hierarchy.
- Called by /verify only - /done is the final step after /verify confirms all criteria pass. If the execution log doesn't show verification, something went wrong upstream.
Medium Routing
When medium is non-local, /done output goes through the calling context (/verify → /do). No special routing needed — just produce the summary as normal.
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?