Skip to content
Skills Library
Education · Planning

learning-roadmap

/learning-roadmap

Create realistic study and project roadmaps for Sothy Eng. Use when asked for weekly or monthly study plans, roadmaps for backend engineering, data engineering, MLOps, system design, computer vision, or interview preparation, small project ideas with milestones, or help deciding what to learn next. Do NOT use for teaching a specific concept (data-engineering, backend-job, car-part-retrieval by topic) or interview Q&A practice (interview-prep).

Repository
my-skill ↗
Licence
MIT
Last repository change
30.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 30.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Create realistic study and project roadmaps for Sothy Eng. Use when asked for weekly or monthly study plans, roadmaps for backend engineering, data engineering, MLOps, system design, computer vision, or interview preparation, small project ideas with milestones, or help deciding what to learn next. Do NOT use for teaching a specific concept (data-engineering, backend-job, car-part-retrieval by topic) or interview Q&A practice (interview-prep).

Original author description

Create realistic study and project roadmaps for Sothy Eng. Use when asked for weekly or monthly study plans, roadmaps for backend engineering, data engineering, MLOps, system design, computer vision, or interview preparation, small project ideas with milestones, or help deciding what to learn next. Do NOT use for teaching a specific concept (data-engineering, backend-job, car-part-retrieval by topic) or interview Q&A practice (interview-prep).

How it works

  1. Purpose
  2. When to use
  3. When not to use
  4. Context intake
  5. Workflow
  6. Adaptation rules
  7. Inputs needed
  8. Output contract
  9. Rules and constraints
  10. Quality checklist
Original SKILL.md headings · 84 lines, 887 words
SKILL.md preview
---
name: learning-roadmap
description: Create realistic study and project roadmaps for Sothy Eng. Use when asked for weekly or monthly study plans, roadmaps for backend engineering, data engineering, MLOps, system design, computer vision, or interview preparation, small project ideas with milestones, or help deciding what to learn next. Do NOT use for teaching a specific concept (data-engineering, backend-job, car-part-retrieval by topic) or interview Q&A practice (interview-prep).
version: 1.0.0
author: Sothy Eng
---

# Learning Roadmap

## Purpose
Turn vague ambitions ("learn data engineering", "get better at system design") into realistic weekly plans that fit Sothy's actual schedule: a part-time backend job, an internship, and a thesis simultaneously. Plans must survive busy weeks without collapsing.

## When to use
- "Help me plan X" — weekly or monthly plans for backend, data engineering, MLOps, system design, computer vision, or interviews.
- Deciding what to learn next given everything already in flight.
- Scoping small practice projects tied to learning goals.
- Re-planning after a stalled stretch (transparently cutting scope, not rescheduling everything).

## When not to use
- Teaching the content itself → route to the topical skill (`data-engineering`, `backend-job`, `car-part-retrieval`, `api-design`, `thesis-helper`).
- Practicing interview answers → `interview-prep` (but an interview-prep phase belongs inside an interview roadmap).
- Internship deliverables or backend-job deadlines → those are obligations, not learning plans; reflect them as constraints here.

## Context intake
- Available hours, deadline, current level, and learning style; read active commitments from `docs/workflow-profile.md` and ask only for what it lacks.
Detect or confirm before starting (ask at most what is genuinely needed):
- Which context: one of the contexts defined in `docs/workflow-profile.md` ("Contexts")? Read `docs/active-context.md` first: if `Current` names a context set within the last day, use it, apply its rules, and do not ask. Otherwise fall back to the active roles and projects in `docs/workflow-profile.md`; ask when it could be two different contexts.
- What is the desired output: a plan, code, a review, tests, documentation, a deployment plan, or research notes? Confirm if ambiguous.

## Workflow
1. Read the my-skill plugin's `docs/workflow-profile.md`. If it is missing, contradicts this request, or was last updated more than ~3 months ago, confirm or update it with Sothy before applying any role, project, or stack assumptions.
2. Ask for available hours/week, deadline, current level, and learning style if not stated.
3. Define ONE measurable outcome for the plan — not three ("implement a CDC pipeline end-to-end", not "learn Kafka, Spark, and Airflow").
4. Confirm the plan must fit around job + internship + thesis; budget realistic hours and reserve a slack buffer.
5. Break the outcome into weekly milestones; each week has: learning topics, one hands-on task, a deliverable, resources (free/low-cost), and success criteria.
6. Schedule heavier weeks early in the plan; front-load setup friction so later weeks are the payoff.
7. Add a weekly review checkpoint (15 min): what shipped, what slipped, what's cut.
8. Include at least one small project with checkboxes so progress is visible.
9. State clearly what is deliberately excluded — a roadmap that doesn't cut scope fails silently.

## Adaptation rules

- ONE measurable outcome per plan, always; hours come from the profile, not assumptions.
- Plans re-plan around whatever is currently in flight (job, internship, thesis, new roles) - the structure survives context changes.
- Hands-on project themes align with the profile's active roles so learning compounds.

## Inputs needed
- Available hours per week (real number, including bad weeks).
- Deadline or target date (job switch, exam, graduation, interview).
- Current level and known gaps.
- Preferred learning style for retention (project-first, video-first, book-first).
- Existing commitments: backend job, internship hours, thesis milestones.

## Output contract
- **Objective** — single measurable outcome.
- **Duration** — weeks + total hours available.
- **Weekly plan table** — week | topics | hands-on task | deliverable | success criteria.
- **Deliverables** — list of concrete artifacts by end.
- **Practice project** — scoped small end-to-end project with milestones.
- **Review checklist** — weekly self-review questions.
- **What's excluded** — explicitly cut topics and why.

## Rules and constraints
- Prioritize practical implementation over passive tutorials; every week produces an artifact.
- Prefer free or low-cost resources (official docs, Dockerized repos, open courses) unless Sothy asks for paid options; never invent courses/books — recommend only verifiable well-known ones or link-free guidance.
- Align topics with his backend job, internship, thesis, and data-engineering interests; cross-pollinate (e.g., CDC learning uses Postgres, which he already knows).
- Avoid overload: if hours are tight, shrink the objective, don't cram.
- Plans are hypotheses: include a mid-point checkpoint decision (continue / cut / swap).

## Quality checklist

- [ ] ONE measurable objective sized around real hours.
- [ ] Weekly deliverables + review checkpoint included.
- [ ] Exclusions stated explicitly.
- [ ] Slack buffer + mid-point continue/cut/swap decision present.

## Examples
1. **Request:** "I want a 6-week plan; I can do ~7 h/week; goal is basic streaming data engineering with Kafka."
   **Behavior:** Objective = "build an event pipeline: Kafka producer → consumer → Postgres + dashboard". Six weekly rows (Docker Compose setup; core Kafka concepts; local producer app; consumer group; Postgres sink + freshness checks; review + demo write-ups), deliverable list, review checklist, exclusions ("no Debezium/Spark in this plan"), slack buffer for the thesis.
2. **Request:** "Am I spreading myself too thin?"
   **Behavior:** Ask for current commitments/hours; show the arithmetic honestly (job + internship leave X); recommend ONE track to keep active until the next review, a date to defer others to, and a cut decision; output format applied compactly.

## Lessons learned

Record improvements after real usage (maintained via ``continuous-improvement``). Format:

- ``<date>`` -- ``<what happened>`` -> ``<change made to this SKILL.md>``

(empty -- entries appear after real usage)

Versions

RepositoryScoreLicence
This page · albkue/my-skill100MIT
Reevias/Prometheus-100MIT

Database snapshot: 13.11.2026 · package version cf2877aef44a (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100data-engineering
    Help Sothy Eng learn and apply data engineering. Use for data pipelines, ETL/ELT, batch and streaming processing, Kafka, CDC, Debezium, Spark, Airflow, dbt, PostgreSQL replication, data warehouses, lakehouses, data modeling, event-driven architecture, data quality and…
  • 100interview-prep
    Prepare Sothy Eng for backend, software development, data engineering, and data science interviews. Use for mock interviews (ask one question, wait for the answer, then give feedback), behavioral question practice (STAR format), system design practice, technical Q&A on…
  • 100ml-coach
    Personal ML Engineer coach built on the ml-engineer-roadmap curriculum (vincere-mori/ml-engineer-roadmap). Use when the user wants to check their ML level, get a study plan toward an ML Engineer offer, run a mock ML interview (ML theory, deep learning, LLM, MLOps, ML system…
  • 100study-plan-builder
    Builds a realistic, personalized learning roadmap for a skill or subject — with milestones, curated resource types, active practice, spaced review, and progress checkpoints — fit to the learner's deadline and weekly time budget. Use this skill when the user asks to "make a study…
  • 100technical-interview-roadmap
    This skill should be used when the user wants a technical interview preparation roadmap, coding interview study plan, or DSA practice plan tailored to a specific company and role. Trigger phrases include "technical interview roadmap", "coding interview prep for", "DSA roadmap…
  • 100developer-interview-simulator
    Simulates developer/engineering interviews: coding rounds, system design, behavioral for engineers, and tech-specific Q&A. Use when the user wants mock developer interview, coding interview practice, system design practice, algorithm questions, technical interview prep,…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.