agentleFS
navoditknavoditk/pm-ai-skills-framework/skills/skillevaluator-mastery/SKILL.md

skillevaluator-mastery

Skill0 starsChanged 46 days agoMITView on GitHub

Interactive training for NVIDIA SkillEvaluator. Guided lessons, quizzes, scenario challenges, and a full reference covering all four evaluation tiers, install/CLI usage, skill package layout, report formats, and CI/CD integration. Say "skillevalexpert" to start.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    USE FOR: "skillevalexpert", "teach me SkillEvaluator", "quiz me on Tier 3", "SkillEvaluator cheat sheet", "SkillEvaluator final exam" DO …

    line 25
  2. Very specific:

    DO NOT USE FOR: PM/finance domain questions answered by this catalog's other skills (see docs/03_SKILL_STANDARD.md).

    line 26
  3. Distinctive:

    When module counter exceeds 8 and user says "skillevalexpert", offer: scenarios, final exam, or review any module.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

SkillEvaluator Mastery

How this skill is loaded: this file is the canonical copy (also the one this repository's own NVIDIA SkillEvaluator Tier 1 checks validate). In this repository, Claude Code discovers it through the thin loader in .claude/skills/skillevaluator-mastery/, Codex through the one in .agents/skills/skillevaluator-mastery/, and GitHub Copilot through either. To use it in another repo or globally, copy (not symlink, for cross-platform reliability) this whole skills/skillevaluator-mastery/ folder to that repo's .github/skills/, .claude/skills/, or .agents/skills/ (project-level), or to ~/.copilot/skills/ (personal, works across all your repos). See About agent skills. Once loaded, say "skillevalexpert" to start.

UTILITY SKILL — interactive NVIDIA SkillEvaluator trainer. INVOKES: ask_user, sql, view USE FOR: "skillevalexpert", "teach me SkillEvaluator", "quiz me on Tier 3", "SkillEvaluator cheat sheet", "SkillEvaluator final exam" DO NOT USE FOR: PM/finance domain questions answered by this catalog's other skills (see docs/03_SKILL_STANDARD.md); do not fabricate CLI flags, schema fields, or report shapes not present in references/ or docs/15_SKILLS_AND_SKILLEVALUATOR_REFERENCE.md

Routing and Content

TriggerAction
"skillevalexpert", "teach me"Read next references/module-N-*.md, teach
"quiz me", "test me"Read current module, 5+ questions via ask_user
"scenario", "challenge"Read references/scenarios.md
"reference"Read relevant module, summarize
"final exam"Read references/final-exam.md

Specific SkillEvaluator questions get direct answers without loading references — cite docs/15_SKILLS_AND_SKILLEVALUATOR_REFERENCE.md and this skill's references/ modules rather than answering from unverified memory. Reference files live in references/. Read on demand with view.

Behavior

On first interaction, initialize progress tracking:

CREATE TABLE IF NOT EXISTS mastery_progress (key TEXT PRIMARY KEY, value TEXT);
CREATE TABLE IF NOT EXISTS mastery_completed (module TEXT PRIMARY KEY, completed_at TEXT DEFAULT (datetime('now')));
INSERT OR IGNORE INTO mastery_progress (key,value) VALUES ('xp','0'),('level','Newcomer'),('module','0');

XP: lesson +20, correct +15, perfect quiz +50, scenario +30. Levels: 0=Newcomer 100=Apprentice 250=Navigator 400=Practitioner 550=Specialist 700=Expert 850=Certifier 1000=Evaluator 1150=Grandmaster 1500=Architect. Max XP from all content: 1600 (8 modules × 145 + 8 scenarios × 30 + final exam 200).

When module counter exceeds 8 and user says "skillevalexpert", offer: scenarios, final exam, or review any module.

Rules: ask_user with choices for ALL quizzes/scenarios. Show XP after correct answers. One concept at a time; offer quiz or review after each lesson. Every factual claim about SkillEvaluator's actual behavior, costs, or bugs must trace to a references/module-*.md file, docs/15_... or docs/13_NVIDIA_EVALUATOR_UPGRADE_POLICY.md — never invent a flag, metric name, or report field.

For traceability, end each teaching/quiz turn with Workflow: skillevaluator-mastery.

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.