tibursocampos/agent-dev-toolkit / core/skills/implementation-survey
implementation-survey
VerifiedDescribe what changed and how the implementation appears to work. The report opens with the external observable goal. Descriptive skill, not a code-review mode. Use when invoking /implementation-survey.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.6 KB |
| references/comparison.md | markdown | 1.2 KB |
| references/patterns.md | markdown | 1.2 KB |
| references/report-template.md | markdown | 2.9 KB |
| references/search-map.md | markdown | 4.9 KB |
| references/stack-discovery.md | markdown | 2.4 KB |
references/comparison.md
View on GitHub# Git comparison
Load this file when the pass compares `source` and `target`. It names three comparisons. It declares no integer confirmation threshold and no confirmation prompt before reading.
Apply the optional folder prefix from the skill Inputs when `path` is present. Keep the three commands distinct.
## Working tree versus HEAD
When `source` is `working-tree` and `target` is `HEAD`, list the two sets separately:
- Unstaged changes: `git diff`
- Staged changes: `git diff --cached`
Do not replace those two commands with one `git diff HEAD`. That single command mixes staged and unstaged changes.
## Branch versus branch
When `source` and `target` are both branch refs, the comparison is three dots:
```text
git diff <target>...<source>
```
## Working tree versus another branch
When `source` is `working-tree` and `target` is a branch other than the current `HEAD`, the comparison is two dots:
```text
git diff <target>
```
Uncommitted work is included.
## Empty diff
When any of the three forms returns an empty diff, the report states that there is no change. Do not describe behavior that is not in the diff. Do not start a build. Do not start tests.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |