lesson

Save a correction or hard-won rule as a confidence-weighted lesson that resurfaces before similar work. Use when the user corrects your approach, says "learn this", "always" or "never do X", or you notice yourself repeating a past mistake.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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.

The body is well-structured and highly actionable, with a concrete JSON example, named commands, and clear sequencing. Minor room remains to tighten the opening/Why prose and to add an explicit error-recovery loop to the workflow.

Suggestions

Tighten the opening line and the "Why" section so the body leads with the actionable Quick start rather than restating the user's intent.

Add a short validate-fix-retry note to the workflow (e.g., what to do if memory_lesson_save is unavailable or rejects the content), turning step 6's veto into a fuller feedback loop.

Consider moving the confidence-decay mechanism detail out of "Why" or condensing it, since it explains system internals rather than guiding action.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the opener ("The user wants a lesson recorded...") and some explanatory "Why" prose could be trimmed without losing actionable guidance.	4 / 5
Actionability	Provides a copy-paste JSON example with all fields and realistic values, concrete confidence heuristics (0.7 / 0.5), named tool commands, and a Wrong/RIGHT contrast that fully specifies execution.	5 / 5
Workflow Clarity	Six clearly sequenced steps with a veto checkpoint and a closing checklist, but there is no explicit error-recovery feedback loop; the save is a one-shot with confirmation rather than validate-fix-retry.	4 / 5
Progressive Disclosure	Well-organized into focused sections with a single clearly-signaled one-level reference (../_shared/TROUBLESHOOTING.md) and a See-also list, giving easy navigation without nested references.	5 / 5
	Total	18 / 20 Passed

Description

95%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 description that clearly states the skill's purpose and gives multiple concrete, natural-language trigger phrases a user would actually say. The only minor weakness is that the action surface is described as one primary verb with properties rather than a list of distinct operations.

Dimension	Reasoning	Score
Specificity	Names the domain (lessons) and concrete mechanics ("confidence-weighted", "resurfaces before similar work"), but the description centers on one primary action (save) with descriptive properties rather than enumerating multiple distinct actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("Save a correction or hard-won rule as a confidence-weighted lesson that resurfaces") and when ("Use when the user corrects your approach, says \"learn this\"...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes the exact natural phrases users say ("learn this", "always", "never do X", "corrects your approach", "repeating a past mistake"), giving comprehensive coverage of likely utterances.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (behavior rules with confidence weighting that resurface) distinct from fact-storing memory skills, with triggers unlikely to fire for the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rohitg00/agentmemory
Path: plugin/skills/lesson/SKILL.md
Commit: e04ba88

Reviewed: 4 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.