run-learning-retrospective

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

The body is a clean, well-structured retrospective skeleton that respects token budget, but its steps stay at a directive level without concrete methods or validation checkpoints. It is well organized for a simple skill.

Suggestions

Make steps more actionable by specifying how (e.g. 'Compare completed work against the target outcomes checklist and flag any unmet criteria').

Add a validation checkpoint, such as confirming identified blockers with the learner before adjusting the plan.

Give one concrete example of a 'measurable checkpoint' so the next-milestone step is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanation of concepts Claude already knows; every line (Trigger, numbered Workflow, Tools, Output) earns its place.	3 / 3
Actionability	The workflow steps name clear intents ('Prioritize what to reinforce versus what to defer', 'Set next milestone and measurable checkpoint') but give no concrete method or examples for how to measure or decide, fitting 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	The five steps are clearly sequenced, but there are no validation or feedback checkpoints (e.g. confirm blockers with the learner before reprioritizing), matching the 'sequence present but checkpoints missing' anchor.	2 / 3
Progressive Disclosure	The skill is under 50 lines, single-purpose, and needs no external references; its well-organized sections qualify for the simple-skill exception to score 3.	3 / 3
	Total	10 / 12 Passed

Description

60%

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 names three concrete actions, but it omits an explicit trigger ('Use when...') and relies on only moderately distinctive terms. It answers 'what' well but leaves 'when' only implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a learner completes a milestone and needs a data-driven adjustment to their learning plan.'

Broaden trigger-term coverage with natural variations a user might say ('retrospective', 'review my progress', 'what went wrong', 'adjust my plan').

Sharpen distinctiveness by naming the retrospective framing (e.g. 'Run a learning retrospective') so it is less likely to collide with generic planning skills.

Dimension	Reasoning	Score
Specificity	The description lists three concrete actions — 'Evaluate learning progress', 'identify blockers', and 'adjust the learning plan' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' but has no 'Use when...' clause or equivalent trigger, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes relevant natural terms ('learning progress', 'blockers', 'learning plan') but lacks common variations, fitting 'some relevant keywords but missing common variations' rather than the full coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	The learning-retrospective niche is somewhat specific but could still overlap with general planning or productivity skills, matching the 'somewhat specific but could overlap' anchor rather than a clearly distinct niche.	2 / 3
	Total	9 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Commit: 0452e08

Reviewed: 14 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.