hoavdc/CodexKit / skills/codexkit-execution-planner
codexkit-execution-planner
VerifiedTurn ambiguous requests into an executable implementation plan with assumptions, sequence, acceptance checks, and rollback thinking.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.2 KB |
| agents/openai.yaml | config | 228 B |
| examples/common-mistakes.md | markdown | 791 B |
| examples/good-output.md | markdown | 742 B |
| references/plan-template.md | markdown | 169 B |
| verification/checklist.md | markdown | 1.3 KB |
examples/common-mistakes.md
View on GitHub# Common Mistakes — Execution Planner
> Anti-patterns to watch for when using the Execution Planner skill.
## 1. Phantom milestones
**What goes wrong:** Milestones listed without tasks that lead to them — the plan looks complete but has no execution path
**How to fix it:** Every milestone must have ≥1 task dependency chain leading to it
## 2. Everyone owns everything
**What goes wrong:** Tasks assigned to 'Team' or 'Engineering' — no individual accountability
**How to fix it:** Assign one person as the DRI (Directly Responsible Individual) per task
## 3. Optimistic-only timeline
**What goes wrong:** No buffer, no risk-adjusted dates — plan breaks on first delay
**How to fix it:** Add 20% buffer for unknowns, explicitly mark dates as 'target' vs 'hard deadline'
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: 466k | Updated | Claude CodeCodex | Verified | 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: 466k | 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: 319k | 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: 319k | Updated | Claude CodeCodex | Verified | Install |