generated/copilot/skills/consolidate-task/SKILL.md
Use when you need to summarize a completed task into an architectural decision record, reducing clutter in .tasks/. Triggers on: 'use consolidate-task mode', 'consolidate-task', 'consolidate task', 'summarize task'.
npx skillsauth add mcouthon/agents consolidate-taskInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Read the task file at .tasks/{task-folder}/task.md and create an architecture decision summary.
Not every completed task needs an ADR. ADRs document architectural decisions, not implementation work.
Skip ADR entirely when:
Update existing ADR when:
Create new ADR when:
When updating, add an entry to the "Updates" table and integrate changes into relevant sections.
Required format: ADR-NNN-{decision-name}.md
docs/architecture/ for existing ADR-* filesADR-003-* → next is 004)001 if no ADR files existdocs/architecture/ADR-NNN-{decision-name}.mdExample: ADR-004-unified-query-execution.md
# {Decision Title}
**Source:** Task {NNN} ({Month Year})
## Decision
One sentence describing the high-level architectural choice.
## Why
- Bullet points explaining the motivation
- Focus on problems solved, not implementation details
## Problem Statement (if applicable)
What issue prompted this change? What was broken or suboptimal?
## Solution
Brief description with before/after comparison:
### Before
{Old approach - can include diagrams or code}
### After
{New approach - can include diagrams or code}
## Implementation Phases
| Phase | What Changed |
| --------- | ------------------ |
| 1. {Name} | {One-line summary} |
| ... | ... |
## Key Architectural Patterns
Include 2-3 code snippets showing the most important patterns established.
Only patterns that future developers need to understand and follow.
## Current Structure
```
relevant/directory/
├── file1.py # Brief purpose
├── file2.py # Brief purpose
```
## Deleted
- List of deleted files/code (shows what was replaced)
## Updates (for existing ADRs only)
| Date | Task | Summary |
| ------------ | ----- | ------------------------------------ |
| {Month Year} | {NNN} | One-line description of what changed |
docs/architecture/README.md (create if missing with a decisions table)development
Systematic debugging with hypothesis-driven investigation. Use when something is broken, tests are failing, unexpected behavior occurs, or errors need investigation. Triggers on: 'this is broken', 'debug', 'why is this failing', 'unexpected error', 'not working', 'bug', 'fix this issue', 'investigate', 'tests failing', 'trace the error', 'use debug mode'. Full access mode - can run commands, add logging, and fix issues.
development
Systematic debugging with hypothesis-driven investigation. Use when something is broken, tests are failing, unexpected behavior occurs, or errors need investigation. Triggers on: 'this is broken', 'debug', 'why is this failing', 'unexpected error', 'not working', 'bug', 'fix this issue', 'investigate', 'tests failing', 'trace the error', 'use debug mode'. Full access mode - can run commands, add logging, and fix issues.
testing
Behavioral testing strategy — deciding what to test and how. Use when writing tests, reviewing test quality, or fixing tests that test mocks instead of behavior. Triggers on: 'use testing mode', 'write tests', 'test strategy', 'tests are brittle', 'tests test mocks', 'improve test quality', 'what should I test'. Full access mode - can write and run tests.
development
Use when finding code smells, auditing TODOs, removing dead code, cleaning up unused imports, or assessing code quality. Triggers on: 'use tech-debt mode', 'tech debt', 'code smells', 'clean up', 'remove dead code', 'delete unused', 'simplify'. Full access mode - can modify files and run tests.