hoavdc/CodexKit / skills/codexkit-execution-planner
codexkit-execution-planner
UnverifiedTurn ambiguous requests into an executable implementation plan with assumptions, sequence, acceptance checks, and rollback thinking.
Execution Planner
Use this skill when the request is larger than a quick patch and needs a plan that can survive real implementation.
Principles
- keep the plan close to the code that will change
- make assumptions explicit
- sequence work to reduce rework
- define how success will be checked
Workflow
- Restate the user goal in operational language.
- List constraints, dependencies, and assumptions.
- Break the work into thin, testable slices.
- Define acceptance checks for each slice.
- Note rollback or containment options for risky steps.
Output structure
Use the template in references/plan-template.md.
Avoid
- task lists with no verification strategy
- plans that front-load polish before foundations
- broad estimates with no dependency reasoning
Quality Criteria
- All placeholder sections are filled with domain-specific content
- Structure follows the relevant industry standard or framework
- Language matches target audience (technical / executive / legal)
- Output is ready for review — not a rough draft requiring major rework
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Does the draft structure follow the stated framework or industry standard? |
| Completeness | Are all required sections present with substantive (not placeholder) content? |
| Context-fit | Does tone, detail level, and terminology match the intended audience? |
| Consequence | If sent to the intended recipient without further editing, what would fail? |
Edge Cases
- No existing template for this type — Use the closest available template and document all customizations made.
- Stakeholder requirements conflict — Flag conflicts explicitly in the draft. Do not silently choose one requirement over another.
- Output required in multiple formats — Produce the canonical format first, then derive others. Note any formatting limitations.
Changelog
- v1.0.0 — Initial release
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: 464k | 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: 464k | 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: 318k | Updated | Claude CodeCodex | Unverified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |