CtrlK
BlogDocsLog inGet started
Tessl Logo

capture-learnings

Capture and apply accumulated knowledge via structured memory. Use when the user gives feedback, shares preferences, corrects a mistake, or when you discover something worth remembering for future conversations.

72

Quality

91%

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

100%

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

A concise, highly actionable single-file skill with concrete commands, clear read-before-merge workflow checkpoints, and well-organized sections that need no external references.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: compact tables, terse bullets, and no padded explanation of concepts Claude already knows; every section earns its place.

3 / 3

Actionability

Provides fully concrete, executable commands ('save-memory --name <name> --type <type> ...', 'resource-read --path memory/<name>.md', 'resource-list --prefix memory/') and specific scope guidance, copy-paste ready.

3 / 3

Workflow Clarity

Clear sequenced guidance with explicit feedback/checkpoint steps ('Read before updating — read it first and merge, don't overwrite') and scoped write instructions, and a 'Don't Capture' guardrail section catching errors.

3 / 3

Progressive Disclosure

Well-organized single-file skill under ~80 lines with clear sectioning (How to, Types, When to Capture, Key Rules, Graduation); no external references needed, and the structure itself supports easy navigation.

3 / 3

Total

12

/

12

Passed

Description

82%

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 well-formed description with an explicit 'Use when' clause and natural trigger terms. It could be more specific about the concrete memory operations and sharper in distinguishing itself from general assistance.

Suggestions

Name concrete memory actions (e.g., 'save, read, merge, and delete memories') in the description to lift specificity.

Tighten trigger terms to memory-specific phrasing to reduce overlap with generic follow-up behavior.

DimensionReasoningScore

Specificity

Names the domain ('structured memory') and several concrete trigger actions ('gives feedback, shares preferences, corrects a mistake'), but does not list specific memory operations like save/read/merge; closest to the 'names domain and some actions' anchor.

2 / 3

Completeness

Explicitly answers what ('Capture and apply accumulated knowledge via structured memory') and when ('Use when the user gives feedback...') with an explicit 'Use when' clause, matching the top anchor.

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say ('gives feedback', 'shares preferences', 'corrects a mistake') plus 'discover something worth remembering', giving good coverage of natural trigger language.

3 / 3

Distinctiveness Conflict Risk

'Capture learnings' targets a clear memory niche, but the trigger conditions (feedback, preferences, corrections) are broad and could overlap with general conversational follow-up skills rather than being sharply distinct.

2 / 3

Total

10

/

12

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.

Validation14 / 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
BuilderIO/agent-native
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.