agentleFS
jhonatan-oliveiradevjhonatan-oliveiradev/agent-skills/skills/building-developer-career-roadmaps/SKILL.md

building-developer-career-roadmaps

Skill1 starsChanged 3 months agoMITView on GitHub

Use when a developer has a capability baseline and career target and needs an adaptive sequence of milestones, dependencies, current focus, and evidence gates.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not treat missing diagnostic evidence as demonstrated weakness.

    line 19
  2. Distinctive:

    Create milestones around observable capability outcomes.

    line 22
  3. Distinctive:

    When assessment, practice, portfolio, or market evidence changes the picture:

    line 37
  4. Distinctive:

    update only affected dependencies and priorities.

    line 40
  5. Distinctive:

    avoid resetting valid progress.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Building Developer Career Roadmaps

Turn a known baseline, target role, constraints, and relevant market signals into the smallest useful sequence of capability milestones. A roadmap is a decision system, not a course list.

Establish the planning inputs

Use explicit inputs:

  • current capability levels and confidence;
  • target-role requirements;
  • blocking prerequisites;
  • weekly learning capacity and practical constraints;
  • existing portfolio evidence;
  • market signals when available, including their freshness and provenance.

Do not treat missing diagnostic evidence as demonstrated weakness. Flag uncertainty that must be resolved first.

Choose milestones by capability dependency

Create milestones around observable capability outcomes. Order them so that:

  1. hard prerequisites come before dependent capabilities;
  2. blocking gaps beat optional polish;
  3. weak evidence can trigger reassessment before unnecessary study;
  4. authentic practice follows the knowledge needed to attempt it;
  5. each milestone ends at a capability or evidence gate.

Content consumption never completes a milestone by itself.

Select one current focus

Choose the smallest high-leverage next focus that is available now. Explain why it comes next using capability dependencies, target-role relevance, evidence confidence, and current constraints.

Give effort as a range when useful, not a promise. Avoid detailed calendar plans that pretend uncertainty has disappeared.

Recalibrate from evidence

When assessment, practice, portfolio, or market evidence changes the picture:

  • preserve completed facts;
  • record the decision that changed;
  • update only affected dependencies and priorities;
  • avoid resetting valid progress;
  • surface why the current focus changed.

Output contract

A useful roadmap names milestones, prerequisites, capability/evidence completion gates, current focus, effort range, and the reasons behind sequencing decisions.

Ownership boundaries

This method owns milestone sequencing, dependencies, current-focus selection, and roadmap recalibration. It does not redefine proficiency criteria, perform formal evaluation, become a long-form curriculum, or turn market frequency into proficiency.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.