run-learning-retrospective

Evaluate learning progress, identify blockers, and adjust the learning plan

Quality

27%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./teaching/skills/run-learning-retrospective/SKILL.md

Quality

Content

29%

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

This skill is essentially a high-level outline that describes what a learning retrospective should accomplish without providing any concrete, actionable guidance on how to do it. It lacks templates, example questions to ask the learner, rubrics for evaluating progress, or criteria for making adjustment decisions. Claude would gain almost nothing from this skill that it wouldn't already know how to do.

Suggestions

Add a concrete retrospective template with specific questions to ask the learner (e.g., 'What concept was hardest this week? Rate your confidence 1-5 on each topic covered.')

Include decision criteria for adjusting the plan — e.g., 'If confidence < 3 on a prerequisite topic, insert a reinforcement exercise before advancing.'

Provide an example output showing what a progress retrospective and updated learning plan actually look like, with specific structure and measurable checkpoints.

Add a validation step such as confirming the updated plan with the learner before finalizing, creating a feedback loop.

Dimension	Reasoning	Score
Conciseness	The content is relatively brief and doesn't over-explain concepts Claude already knows, but the workflow steps are generic and vague enough that they don't add much value — they describe what Claude would naturally do without specific, novel guidance.	2 / 3
Actionability	The skill provides only abstract, high-level descriptions ('identify recurring blockers,' 'adjust pacing') with no concrete examples, templates, rubrics, question frameworks, or specific criteria for evaluation. There is nothing executable or copy-paste ready.	1 / 3
Workflow Clarity	The five steps are vaguely sequenced but lack any validation checkpoints, decision criteria, or feedback loops. There's no guidance on how to determine if blockers are correctly identified, how to measure progress, or what constitutes a good adjustment.	1 / 3
Progressive Disclosure	For a simple, short skill with no bundle files, the content is organized into clear sections (Trigger, Workflow, Tools, Output) and doesn't need external references. The structure is appropriate for its scope.	3 / 3
	Total	7 / 12 Passed

Description

25%

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 provides a basic sense of what the skill does—evaluating learning progress and adjusting plans—but lacks specificity in its actions, omits explicit trigger guidance, and is too generic to be reliably distinguished from other learning-related skills. It needs concrete details about its capabilities and clear 'Use when' triggers to be effective in a multi-skill selection context.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user asks to review their learning progress, feels stuck, wants to check milestones, or needs to update their study plan.'

Increase specificity by listing concrete actions, e.g., 'Compares completed topics against planned milestones, diagnoses knowledge gaps through targeted questions, and reprioritizes upcoming lessons.'

Improve distinctiveness by clarifying the scope—specify what kind of learning plan (e.g., structured curriculum, self-study roadmap) and how this differs from initial plan creation or general tutoring.

Dimension	Reasoning	Score
Specificity	Names the domain (learning) and lists some actions (evaluate progress, identify blockers, adjust plan), but the actions are somewhat generic and lack concrete details about how these are performed or what outputs are produced.	2 / 3
Completeness	Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only moderately clear, warranting a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'learning progress', 'blockers', and 'learning plan', but misses common user variations such as 'study plan', 'stuck', 'review progress', 'check-in', or 'how am I doing'.	2 / 3
Distinctiveness Conflict Risk	Very generic phrasing around 'learning' could easily conflict with other education, tutoring, study planning, or coaching skills. Nothing distinguishes this from a general learning assistant or study planner.	1 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Commit: cfd81b3

Reviewed: 3 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.