xiduzo/wtf / skills/wtf.implement-trace
wtf.implement-trace
VerifiedThis skill should be used when a developer is ready to implement, resume, or continue a GitHub Trace issue — for example "implement trace
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.6 KB |
| references/issue-body-update-pattern.md | markdown | 1.7 KB |
references/issue-body-update-pattern.md
View on GitHub# Issue Body Update Pattern
Use this pattern whenever you need to update a section of a GitHub issue body without overwriting the rest. All body reads and writes go through the **gh body helper** so multi-line UTF-8 content survives on every platform — see `../../references/gh-body-helper.md`.
## Steps
1. Fetch the current body to a UTF-8 temp file. The helper prints the temp file's path on stdout:
```bash
python3 .wtf/gh-body.py read <issue_number>
```
2. Read that path with the Read tool, then replace only the target section with the Write or Edit tool — do not manually construct the full body from scratch, as other sections may have changed since the issue was created.
3. Push the updated body back:
```bash
python3 .wtf/gh-body.py edit <issue_number> --body-file "<path-from-step-1>"
```
## Notes
- Always read before writing — never assume the current body matches the original draft.
- **Never capture a body into a shell variable** (`BODY=$(gh issue view …)`) — PowerShell joins multi-line output with spaces and destroys the body. Always go through `read` → temp file → Read tool.
- The second write in a run (e.g. updating the Test Mapping table after an earlier step updated the Technical Approach section of the Trace body) must re-`read` the body rather than reusing the temp file from the earlier step, since other sections may have been updated in between.
- `read` uses `mkstemp`, so every call yields a unique path — parallel runs never collide; no need to hand-roll names with the issue number or `$(date +%s)`.
- If `.wtf/gh-body.py` is absent, use the raw-`gh` fallback in `../../references/gh-body-helper.md` (unguarded on Windows).
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: 471k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |