CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 efficient, well-sequenced tutor procedure with genuine validation checkpoints (preflight, pending evidence states, lock/unlock rules, quiz-answer hygiene) and concrete commands, paths, and formats. Its only weaknesses are minor: an inline progress template that could be split out and per-lesson command detail delegated to the manifest.

DimensionReasoningScore

Conciseness

The body is dense imperative guidance with no concept explanations Claude already knows ("Read the manifest before choosing a lesson", "Never assume the process cwd is the installed bundle"). It is not a 5 because the ~30-line progress-file template and the host table carry some tokens that could be tightened, though the template is needed for reproducibility.

4 / 5

Actionability

Concrete, executable guidance throughout: exact commands ("node --version", "npx --version", "python3 --version"), a fetchable URL pattern, exact file names, status values, and a literal reply format ("Reply with one letter: <A|B|C|D>"). Not 5 because the actual per-lesson commands are delegated to the external manifest rather than shown, leaving small execution gaps.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced — preflight, locate-or-create progress, prerequisite gating before Lesson 26, teach steps 1–8, close — with explicit validation gates: "Mark the row Done only after the checkpoint and quiz are complete", "Never describe that fallback as a real host pass", "record it as unverified instead of inferring support", and Pending/Locked feedback states for error recovery. This matches the anchor-5 pattern of sequence plus explicit validation and failure handling.

5 / 5

Progressive Disclosure

The skill has no bundle files (references/, scripts/, assets/ are absent), and its external dependency is clearly signaled one level deep ("learning-paths/agent-skills.json" plus the raw.githubusercontent URL). Sections are well organized, but the 30-line progress template inlined in SKILL.md could arguably live in a bundled reference file, so it sits at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

87%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: it states a concrete tutoring capability, an explicit resume/start trigger enumerating natural verbs, and a distinct niche tied to a named learning path. Only minor gains available from adding synonyms a user might actually type (e.g., skill bundle, SKILL.md).

DimensionReasoningScore

Specificity

The description lists several concrete actions — "create, discover, invoke, secure, evaluate, package, or port Agent Skills", "Teaches one lesson per invocation and records evidence in AGENT-SKILLS-LEARNING.md" — with only minor gaps; verbs like "secure" and "evaluate" are less artifact-concrete than a level-5 example. It clearly exceeds the 1–2-action coverage of anchor 3.

4 / 5

Completeness

Both 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") are explicitly and concretely stated with trigger phrases. Not 4: the 'when' clause is fully explicit, not weakly implied.

5 / 5

Trigger Term Quality

"create, discover, invoke, secure, evaluate, package, or port Agent Skills" plus "start or resume this route" are phrases a learner would naturally say, giving good keyword coverage. It falls short of anchor 5 because it omits synonyms a user might use such as "SKILL.md", "skill bundle", or specific host names.

4 / 5

Distinctiveness Conflict Risk

"the Agent Skills Engineering path in AI Engineering from Scratch" names a specific niche with distinct, unlikely-to-collide triggers (Agent Skills, SKILL.md-adjacent vocabulary). Minimal conflict risk with generic skills; it is clearly distinguishable, matching anchor 5.

5 / 5

Total

18

/

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
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.