CtrlK
BlogDocsLog inGet started
Tessl Logo

teach

在这个工作区中教用户一个新技能或概念。

46

Quality

50%

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/productivity/teach/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The content is a well-structured, mostly lean instruction-only framework for a stateful teaching workspace, with concrete naming and directory conventions. It falls short of top scores because it lacks explicit validation checkpoints, ships no example/format bundle files despite referencing them, and carries some philosophical exposition that could be trimmed.

Suggestions

Add a short numbered workflow with an explicit verification step (e.g. confirm MISSION.md is filled before producing lessons, validate lesson links resolve).

Provide the referenced *-FORMAT.md files as bundles, or inline minimal templates, so the signaled references actually resolve.

Trim the Philosophy / Fluency-vs-Storage exposition to the directive essentials to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly directive and assumes Claude knows basics (no explanations of HTML/CLI), but sections like Philosophy, Fluency vs Storage Strength, and Knowledge/Skills/Wisdom carry exposition that could be tightened; it is efficient but not maximally lean.

2 / 3

Actionability

Concrete guidance exists (file naming "0001-<dash-case-name>.html", directory layout, "先读取 ./assets/", open lesson via CLI), but output shapes rely on referenced *-FORMAT.md files that are not shipped, leaving key details incomplete.

2 / 3

Workflow Clarity

The process is organized by topic with some sequencing (e.g. ask for mission first), but there is no explicit validation/verification checkpoint or feedback loop; the sequence is implicit rather than a numbered workflow.

2 / 3

Progressive Disclosure

Sections are well-organized and references to MISSION-FORMAT.md / RESOURCES-FORMAT.md / LEARNING-RECORD-FORMAT.md are one-level-deep and signaled, but those files are not present as bundles, so navigation is effectively broken and a fair amount of framework content stays inline.

2 / 3

Total

8

/

12

Passed

Description

50%

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

The description is concise and third-person but generic: it conveys the what (teach a skill/concept) without any explicit when-to-use triggers or concrete action list. It clears the bar above pure fluff but stops at the middle band on every dimension.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to learn, be taught, or study a new skill or concept."

List a few concrete actions to raise specificity, e.g. "Designs interactive HTML lessons, builds reference docs, and tracks learning progress."

Cover the common "learn/学" trigger term alongside "teach/教" to improve natural keyword coverage.

DimensionReasoningScore

Specificity

The phrase "教用户一个新技能或概念" names a domain (skill/concept) and a single action (teach), but offers no comprehensive list of concrete actions, sitting just above pure vagueness like "Helps with documents".

2 / 3

Completeness

It states what the skill does (teach a new skill/concept in this workspace) but provides no "Use when..." clause or explicit trigger guidance, so the "when" is only implied — capping completeness at 2 per the guideline.

2 / 3

Trigger Term Quality

It includes natural terms a user might say ("教"/teach, "技能"/skill, "概念"/concept), but omits the most common phrasing "学"/learn despite the argument-hint using 学习, leaving common variations uncovered.

2 / 3

Distinctiveness Conflict Risk

"Teach a new skill or concept" is a broad educational niche that could overlap with many explanatory or tutoring skills; it is somewhat specific but lacks distinct enough triggers to rule out conflicts.

2 / 3

Total

8

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

description_field

'description' is very short (19 chars), consider making it more detailed

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 missing

Warning

Total

13

/

16

Passed

Repository
vinvcn/mattpocock-skills-zh-CN
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.