CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

learn-agent-skills

Focused interactive tutor for the Agent Skills Engineering path in AI Engineering from Scratch. Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills. Teaches one lesson per invocation and records evidence in AGENT-SKILLS-LEARNING.md.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is learn-agent-skills in rohitg00/ai-engineering-from-scratch

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an excellent instruction-only skill: fully actionable with exact commands, paths, templates, and lesson sequencing, and a clearly gated workflow with validation checkpoints and honest fallback handling. Its only weaknesses are mild redundancy in the pending/fallback rules and a monolithic single-file layout where a reference file could absorb the progress template.

DimensionReasoningScore

Conciseness

The body is dense and operational — manifest paths, lesson order, host invocation table, preflight commands — with no explanation of concepts Claude already knows. Minor trimming is possible: the pending/fallback rule recurs across sections ("record the lab as pending rather than claiming it ran", "Never describe that fallback as a real host pass") and a ~30-line progress-file template is inlined, placing it at anchor 4 rather than 5.

4 / 5

Actionability

Guidance is copy-paste ready throughout: exact commands ("node --version, npx --version, and python3 --version"), exact paths ("learning-paths/agent-skills.json"), a fetch URL template, the exact required order "22, 24, 25, 26, 27", a complete progress-file template, and an exact hint string "Reply with one letter: <A|B|C|D>.". For an instruction-only skill this fully matches the anchor-5 expectation of concrete, specific guidance covering the common cases.

5 / 5

Workflow Clarity

The "Teach one lesson" section is a numbered 8-step sequence with explicit validation gates ("Mark the row Done only after the checkpoint and quiz are complete"), a real-lab preflight, prerequisite locking ("Keep Lesson 26 Locked until Lesson 25 is Done and the knowledge preflight is Confirmed"), and fallback loops when the runtime is unavailable. Install/update/uninstall operations carry confirmation and evidence requirements, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

Sections are clearly headed and all references are one level deep ("learning-paths/agent-skills.json", "docs/en.md", "quiz.json", the raw.githubusercontent URL), with no nested references and no bundle files to mis-signal. It stays at anchor 4 rather than 5 because everything — including the 30-line template and per-lesson checkpoint lists — lives inline in one ~170-line file rather than being split across reference files.

4 / 5

Total

18

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concise, and specific, with an explicit when-clause containing natural trigger phrases and a concrete artifact name. Its only gaps are minor — a few missing synonyms (e.g., SKILL.md, skill files) and slightly thin coverage of the skill's own operational actions beyond teaching and recording evidence.

DimensionReasoningScore

Specificity

Quotes "Teaches one lesson per invocation and records evidence in AGENT-SKILLS-LEARNING.md" plus the concrete verb set "create, discover, invoke, secure, evaluate, package, or port" — several specific actions with a named artifact file. It is not 5 because the skill's own operational actions are only two or three, with the remaining verbs describing topical scope rather than what the skill does.

4 / 5

Completeness

It explicitly answers both questions: what — "Focused interactive tutor … Teaches one lesson per invocation and records evidence in AGENT-SKILLS-LEARNING.md" — and when — "Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills". This matches the anchor-5 example (explicit what and when with concrete trigger phrases), and the missing-trigger cap does not apply because equivalent explicit trigger guidance is present.

5 / 5

Trigger Term Quality

The clause "when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills" supplies natural phrases a user would actually say, giving good keyword coverage. It falls short of 5 because common synonyms such as "SKILL.md", "skill files", or ".skill" are absent, and it is clearly above 3 since coverage is broad rather than partial.

4 / 5

Distinctiveness Conflict Risk

The niche is tightly anchored ("Agent Skills Engineering path in AI Engineering from Scratch") with distinct triggers around Agent Skills, so overlap risk is minor. It is not 5 because the generic "tutor" / "start or resume" framing could partially overlap with sibling learning-route skills in the same ecosystem, though far less than the anchor-3 case.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

rohitg00/ai-engineering-from-scratch

Path

.claude/skills/learn-agent-skills/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.