CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lesson

Store a lesson learned from the current conversation. Triggered by /lesson command. Use when Master signals that the recent conversation contains a pitfall, fix, or key insight that should be persisted to long-term memory.

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary short-form instruction skill: lean, unpadded, with a clear five-step workflow, explicit verification, concrete entry templates with categories and importance thresholds, and sensible fallback behavior. The only notable gap is that the store-side tool invocation is implied by placeholder templates rather than given as an exact call syntax.

DimensionReasoningScore

Conciseness

The 22-line body is lean and efficient with zero padding: no explanation of what memory is, no concept tutorials, and every line either instructs an action or constrains it ("Keep entries short and atomic (< 500 chars each)"). It fully assumes the reader's competence, matching the anchor-5 example.

5 / 5

Actionability

Concrete, actionable guidance throughout: exact entry templates ("Pitfall: [symptom]. Cause: [root cause]. Fix: [solution]. Prevention: [how to avoid]."), explicit categories and importance thresholds (fact ≥ 0.8, decision ≥ 0.85), and a named verification tool (memory_recall). It stops short of fully executable anchor 5 because the placeholder templates and the store-side tool invocation syntax are not spelled out.

4 / 5

Workflow Clarity

A clear five-step sequence with an explicit validation checkpoint ("Verify — memory_recall with anchor keywords to confirm both entries retrievable") and a conditional fallback for the no-lesson case ("If no clear lesson is found in recent context, ask Master what to store"). The memory-store operation is non-destructive and non-batch, so no validation cap applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and the content is organized into clean Steps and Rules sections with no monolithic wall of text — per the rubric's simple-skill guideline this matches anchor 5 on well-organized sections alone.

5 / 5

Total

19

/

20

Passed

Description

70%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 solid description that clearly states both what the skill does and when to use it, with a command trigger and relevant keywords. Its main weakness is thin capability coverage — a single store action — and trigger phrasing that references the /lesson command and "Master signals" rather than natural user-language cues.

Suggestions

Expand the 'what' with 1-2 more concrete actions, e.g., "Store a lesson learned... as a short pitfall/fix/prevention entry and a decision principle, then verify it is retrievable."

Add natural user phrasings to the 'when' clause — e.g., "Use when the user says 'remember this', 'lesson learned', or asks to save a takeaway or pitfall for future sessions."

Add distinguishing cues (e.g., "persisted insights distilled from this conversation only, not general facts") to reduce overlap with other memory-logging skills.

DimensionReasoningScore

Specificity

"Store a lesson learned from the current conversation" names the domain and one concrete action (persist to long-term memory), but coverage is not comprehensive — it says nothing about what the stored lesson looks like or how it is structured. It does not list several specific actions, so anchor 3 fits better than 4.

3 / 5

Completeness

Both parts are answered: what ("Store a lesson learned... persisted to long-term memory") and when ("Use when Master signals that the recent conversation contains a pitfall, fix, or key insight"). The 'when' clause is explicit but leans on the /lesson command and Master's signal rather than the natural user phrases that anchor 5 exemplifies.

4 / 5

Trigger Term Quality

Natural keywords are present — "lesson learned", "pitfall", "fix", "key insight", "long-term memory", "/lesson" — and would plausibly match user phrasing. A few common variations are missing (e.g., "takeaway", "remember this", "save this note"), which keeps it below the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The memory-persistence niche is fairly distinct with a dedicated command trigger, but phrases like "pitfall, fix, or key insight... persisted to long-term memory" have minor overlap risk with other memory-logging skills. This matches "mostly distinct; minor overlap risk with closely related skills" rather than the fully distinct anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

CortexReach/memory-lancedb-pro

Path

skills/lesson/SKILL.md

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.