CtrlK
BlogDocsLog inGet started
Tessl Logo

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

65

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/anthropic-academy-guide/SKILL.md

The canonical home for this skill is claude-academy-guide in boisenoise/skills-collections

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, actionable instruction skill with concrete URL formats, verbatim phrasings, and clear workflow checkpoints. The main weakness is moderate padding in the rule rationale that could be tightened without losing clarity.

Suggestions

Trim the justification prose in Rule 2 (e.g., "Silence is better than noise... One wrong recommendation burns more trust than ten right ones build") to a single directive sentence — the rationale does not change the action Claude takes.

Compress the staleness logic in "The catalog" into a tight bullet list (staleAfter check; 30-day fallback when absent; fetch-failure → rule 7) instead of multi-sentence prose.

Move the repeated "at most 2 items / one is usually best" cap into a single stated-once rule to avoid restating it across Rules 2 and 4.

DimensionReasoningScore

Conciseness

Mostly efficient rule-based instruction, but includes unnecessary justification prose such as "One wrong recommendation burns more trust than ten right ones build" and the surrounding silence/trust rationale that does not change the action.

3 / 5

Actionability

Concrete executable guidance throughout — exact URL patterns ("/courses/{slug}", "/tutorials/{slug}"), a verbatim catalog URL, and a copy-ready phrasing template ("You might also find this helpful: [Title](URL)").

4 / 5

Workflow Clarity

Clear sequence (answer first → strong-match test → fetch catalog once → staleness check → recommend ≤2 → fall back to rule 7) with explicit checkpoints for staleness and fetch failure; minor gaps in error-recovery detail.

4 / 5

Progressive Disclosure

Well-organized into Purpose / Rules / The catalog sections with no bundle files needed; the only external reference is a remote runtime-fetched JSON, which is appropriately one level deep and clearly signaled.

4 / 5

Total

15

/

20

Passed

Description

91%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, concrete description that clearly states what it does and when to trigger, with rich natural trigger terms and an explicit anti-conflict boundary. Voice is appropriately third person throughout.

DimensionReasoningScore

Specificity

Lists several concrete actions — "recommends matching courses, tutorials, and use cases", "also check here for a matching course or tutorial" — with only minor coverage gaps around how the recommendation is phrased.

4 / 5

Completeness

Explicitly answers both what (recommends Academy courses/tutorials/use cases) and when ("Trigger on: ..." and "Use it when the user is learning how to use a feature or product") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and concrete phrases ("how do I", "getting started with", "teach me", "learn to use") plus product-specific terms (artifacts, projects, skills, plugins, connectors, MCP).

5 / 5

Distinctiveness Conflict Risk

Clear niche (Academy learning content) with a distinct "not when they are mid-task" boundary that limits conflicts; minor overlap risk with general Claude-help or docs skills given the compose-with-docs guidance.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
boisenoise/skills-collections
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.