teach

Teach the user a new skill or concept, within this workspace.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/thinking-and-docs/teach/SKILL.md

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 skill body is a well-organized instructional framework with mostly efficient prose and good in-section structure, but it relies on abstract pedagogical guidance and references several format files and directories that are not present in the bundle. This leaves it at the middle anchor across conciseness, actionability, workflow clarity, and progressive disclosure.

Suggestions

Provide the referenced bundle files (MISSION-FORMAT.md, RESOURCES-FORMAT.md, LEARNING-RECORD-FORMAT.md) and the ./reference, ./lessons, ./learning-records directories so the signaled progressive disclosure actually resolves.

Tighten the philosophical sections (Philosophy, Fluency vs Storage Strength) into concise actionable rules so every token earns its place.

Consolidate the workflow into one explicit numbered sequence with validation checkpoints (e.g., verify MISSION.md is populated before designing a lesson; confirm with the user before recording mission changes).

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is mostly genuine workspace-specific guidance, but includes discursive pedagogical philosophy (e.g., "To learn at a deep level, the user needs three things") that could be tightened, matching the mostly-efficient-but-could-tighten anchor.	2 / 3
Actionability	Concrete file/format conventions are given (e.g., lessons titled "0001-<dash-case-name>.html", quiz answers "exactly the same number of words"), but much of the core lesson-design guidance remains abstract principle rather than fully concrete, executable steps, fitting the some-concrete-but-incomplete anchor.	2 / 3
Workflow Clarity	A recoverable multi-step workflow exists (populate MISSION.md, gather resources, find the zone of proximal development, design a lesson, record learning) with some checkpoints like "Confirm with the user before changing the mission", but it is distributed across sections rather than presented as one explicit numbered sequence with validation feedback loops.	2 / 3
Progressive Disclosure	The body is well-sectioned and clearly signals one-level-deep references to MISSION-FORMAT.md, RESOURCES-FORMAT.md, and LEARNING-RECORD-FORMAT.md, but none of these referenced bundle files or the ./reference, ./lessons, ./learning-records directories actually exist, so the disclosure is signaled but not delivered.	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 clearly states what the skill does but lacks any explicit "when to use" trigger guidance and lists only a single action, so it sits at the middle anchor across all dimensions. It is specific enough to avoid being purely generic but not comprehensive enough to reach the top anchor.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to learn or be taught a new skill or concept over multiple sessions.'

List the concrete actions the skill performs (e.g., "creates lessons, reference docs, and learning records") to raise specificity and distinctiveness.

Include natural trigger terms a user would say ("teach me", "I want to learn", "help me understand") to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	The phrase "Teach the user a new skill or concept" names the learning domain and one concrete action ("Teach"), but does not list multiple specific actions, matching the anchor for naming a domain with some actions that are not comprehensive.	2 / 3
Completeness	The "what" is present (teach a new skill or concept) but there is no "Use when..." clause or equivalent explicit trigger guidance for "when", which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	"Teach" and "skill or concept" are natural terms a learner might use, but the description omits common variations and explicit trigger phrasing, fitting the anchor for some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	The qualifier "within this workspace" gives it a niche, but "teach a new skill or concept" is broad and could overlap with similar skills, matching the anchor for being somewhat specific yet still overlapping.	2 / 3
	Total	8 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: mishatojk/davidskills
Commit: 66860fb

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.