CtrlK
BlogDocsLog inGet started
Tessl Logo

continual-learning

Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.

61

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is concise and well-structured for a simple orchestration skill, with a clear trigger and clean guardrails. Its main weakness is actionability: the workflow does not specify what to pass to the subagent or how to handle its result.

Suggestions

Add concrete detail on how to invoke `agents-memory-updater` (e.g. what context or prior-chat range to pass) and what the returned result looks like.

Optionally include a short example of the updater result and how it should be surfaced back to the user.

DimensionReasoningScore

Conciseness

The body is lean (~20 lines) with well-organized sections and no padding or explanation of concepts Claude already knows; every token earns its place.

3 / 3

Actionability

Steps name a concrete subagent ('Call agents-memory-updater') and an explicit return action, but miss key details such as what context to pass the subagent and how to format or surface its result.

2 / 3

Workflow Clarity

This is a simple orchestration skill with an unambiguous two-step sequence; because the work is delegated, no destructive/batch validation checkpoint is required, so the clear sequence earns a 3.

3 / 3

Progressive Disclosure

Under 50 lines with no bundle files and no need for external references; the body is well-organized into Trigger, Workflow, and Guardrails sections, which satisfies the simple-skill bar.

3 / 3

Total

11

/

12

Passed

Description

57%

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 specific and distinct, using proper third-person voice, but it omits an explicit 'Use when...' trigger clause and relies on slightly technical trigger phrasing. Adding natural user-facing trigger terms and an explicit usage clause would raise completeness and trigger quality.

Suggestions

Append a 'Use when...' clause to the description, e.g. 'Use when the user asks to mine prior chats, maintain AGENTS.md, or run the continual-learning loop.'

Add natural user phrasings such as 'review past chats', 'update my memory', or 'keep AGENTS.md up to date' alongside 'transcript mining'.

Clarify the skill's own value beyond delegation, e.g. noting it coordinates the loop rather than just forwarding to the subagent.

DimensionReasoningScore

Specificity

Names the domain ('continual learning') and concrete actions ('transcript mining', 'AGENTS.md updates'), but the skill is a thin orchestration wrapper so its own action set is narrow rather than comprehensive.

2 / 3

Completeness

Clearly states what the skill does ('Orchestrate continual learning by delegating...'), but the description lacks a 'Use when...' clause; the trigger guidance lives only in the body, capping completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

Includes some relevant keywords ('continual learning', 'transcript mining', 'AGENTS.md updates'), but 'transcript mining' is jargon and common user phrasings like 'review past chats' or 'update my memory' are missing.

2 / 3

Distinctiveness Conflict Risk

The continual-learning loop with explicit delegation to a named subagent is a clear niche with distinct triggers, unlikely to fire for unrelated skills.

3 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cursor/plugins
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.