generic-automation-and-it/smooth-ai-stockanalysis / .agents/skills/agile-github-task-from-diff
agile-github-task-from-diff
VerifiedCreate a GitHub Task (sub-issue) from the current git diff vs main and link it as a sub-issue of a parent Feature in the local GitHub SmoothAiStockAnalysis. Use when Codex needs to summarize branch changes into a horizontally sliced task with acceptance criteria and create it via `gh`.
| File | Kind | Size |
|---|---|---|
| AGENTS.md | markdown | 1.6 KB |
| SKILL.md | skill md | 5.7 KB |
| agents/openai.yaml | config | 436 B |
| scripts/create_github_task_from_diff.pyexecutable | script | 12.9 KB |
AGENTS.md
View on GitHub# agile-github-task-from-diff — AGENTS.md
## TL;DR
Script-driven skill: `create_github_task_from_diff.py` owns diff classification, issue authoring, project add, sub-issue linking, and the branch-rename suggestion; the agent only decides the feature link and executes the suggested rename.
## Non-Negotiables
- **Don't author the issue title/body by hand** — the script is the source of truth for the `[layer]` title format and acceptance-criteria checklist. Hand-authored issues drift from the horizontal-slicing contract.
- **Never guess a branch `<type>` or slug** when the script's suggestion looks wrong — stop and ask, per the format-enforcement rule in `git-policy.instructions.md`.
## Key Behaviors
- `classify_horizontal_slice()` keys the `backend` layer off path prefixes `src/` and `SmoothAiStockAnalysis` so renamed solution changes still classify as backend work.
- The script's `LAYER_TO_TYPE` map drives the suggested branch name printed after creation; `git-commit-push-pr` later parses the issue number back out of that branch name for its `Closes #` link — the two skills are coupled through the `<type>/<issue>-slug` convention, not through any shared code.
- Sub-issue linking uses a REST endpoint (`POST .../sub_issues`) that fails soft: the script prints a manual-link fallback instead of erroring, so a "created but not linked" outcome is normal, not a bug.
## Changelog
| Date | Change | Ref |
|:-----|:-------|:----|
| 2026-06-12 | Initial version. Branch-rename derivation moved from SKILL.md prose into the script (`suggest_branch_name`); stale `ProsmarBunkering` path prefix removed. | |
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 |