aaroncharrier
- 12 skills
- 0 followers
- 17 hours ago last updated
- ▌ Quest Giver · aaroncharrier bundleMentor-first quest design for data engineering and Codex or ChatGPT practice inside a real project. Use when Codex needs to create a new project quest, continuation quest, lightweight drill, debugging challenge, workflow practice quest, or prompt-engineering or context-engineering exercise with checkpoints, acceptance criteria, quest-wiki tracking, and a clear next step.
- ▌ Jira Updater · aaroncharrier bundleRun jira_loader.py validate, preview, or apply against one Jira markdown artifact and return the loader output in a fixed human-readable format.
- ▌ Scratch Notes · aaroncharrier bundleCapture short scratch notes, reminders, work observations, decisions, and task follow-ups into an append-only Markdown file at the current project root. Use when the user wants a fast, low-friction place in Codex UI to record operational context or career-relevant work evidence without starting a broader task-management workflow.
- ▌ Interview Engine · aaroncharrier bundleResolve ambiguity in prompt-generation and other requests through a JSON-backed requirements interview stored in `.interview-engine/session-<yyyy-MM-dd_HH-mm-ss>/interview_questions.JSON`.
- ▌ Python Explainer · aaroncharrier bundleExplain Python snippets, files, classes, modules, and small multi-file examples, and review them for modern Python 3.11+ best practices or targeted improvement guidance. Use when requests ask what Python code does, whether Python code follows best practices, or how to improve a Python module without defaulting to a full rewrite.
- ▌ End Of Day Review · aaroncharrier bundleGather approved end-of-day evidence, verify gaps through $interview-engine, and merge a factual daily entry into a project-scoped weekly Markdown work log. Use when Codex needs to document a user's work day from Teams chats, Teams meeting chats, Outlook calendar events, sent emails, Codex session logs, and user input without inventing missing facts or creating extra trackers.
- ▌ Execution Planner · aaroncharrier bundleTransform a refined specification into a clear, structured, and traceable execution plan. Use when Codex has a validated specification from `$specification-builder` and must define ordered actionable steps without generating deliverables or introducing new decisions.
- ▌ Project Bootstrap · aaroncharrier bundleDeterministically create a new analytics or data-engineering project scaffold by creating the target folder and copying the bundled template pack into its existing layout. Use when Codex needs to initialize a new Codex project from the packaged root docs, role files, BRD/PRD/SRD templates, data-document templates, questionnaires, and an empty `repo/` with Windows-only behavior, minimal LLM involvement, overwrite protection via `--force`, and no runtime document editing or questionnaire processing.
- ▌ Measurable Task Plan · aaroncharrier bundleCreate exactly one MEASURABLE_TASK_PLAN.md from a generic task, project, bug, improvement, data engineering effort, or technical objective. Use when the user explicitly invokes $measurable-task-plan or asks Codex to convert an objective into an executable task plan with measurable outcomes, three-question clarification batches, discovery tasks for unknowns, task-level acceptance criteria, validation actions, and tangible evidence requirements. Do not use for PROJECT_PLAN.md, WORK_LOG.md, Jira issues, implementation, roadmap creation, business cases, progress tracking, or status updates.
- ▌ Interview Prompt Flow · aaroncharrier bundleGenerate Codex prompt artifacts only, including prompt files, templates, and reusable instruction sets, using an interview-first workflow. Use only when the user explicitly wants a prompt to be written, not when they want a direct answer, tutorial, guide, or general explanation.
- ▌ Project Initiation Pm · aaroncharrier bundleRun conversation-first project initiation after project-bootstrap creates the scaffold. Use when Codex should read referenced project docs first, classify the work, interview the user 3 questions at a time, directly populate PROJECT_PLAN/WORK_LOG docs, create only justified supporting data docs, escalate to BRD/PRD/SRD only when the project is expected to exceed 6 weeks, and deterministically delete the six unused BRD/PRD/SRD template/questionnaire files for shorter projects.
- ▌ Interview Prompt Builder · aaroncharrier bundleBuild downstream prompt file from interview output at `.interview-engine/session-<yyyy-MM-dd_HH-mm-ss>/interview_output.json`. Use when turning interview results into prompts. Never build a prompt from an unresolved interview or the raw user request alone.