continual-learning

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

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./continual-learning/skills/continual-learning/SKILL.md

Quality

Content

78%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 an exemplary lean orchestration-only skill: concise, well-sectioned, with clear trigger guidance and sensible guardrails. Its main gap is actionability — it never explains how to invoke the subagent or what to do when the updater fails.

Suggestions

Specify the invocation mechanism for `agents-memory-updater` (e.g. which tool or agent type to use, and what prompt/arguments to pass it).

Add a brief handling step for updater failure or empty results so the two-step workflow has an explicit checkpoint.

Clarify what 'Return the updater result' means (raw output vs. a summarized confirmation) so the parent flow's output is deterministic.

Dimension	Reasoning	Score
Conciseness	The body is ~20 lean lines with zero explanation of concepts Claude already knows; every line (trigger, two-step workflow, guardrails) earns its place. This matches anchor 5 exactly; nothing could be trimmed without losing information.	5 / 5
Actionability	"1. Call `agents-memory-updater`. 2. Return the updater result." names the concrete action but never specifies the mechanism for calling it (Agent tool, Skill invocation, command), and no input or context to pass. This is some concrete guidance with missing key details (anchor 3), short of anchor 4's 'mostly executable' and above anchor 2's high-level-only hints.	3 / 5
Workflow Clarity	As a simple single-purpose skill, the two-step sequence is clear and unambiguous, and the guardrails prevent drift; no validation is required since the parent flow is non-destructive and read-only. It does not reach anchor 5 because there is no checkpoint for handling a failed or empty updater result, and the 'call' step itself is under-specified.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-task, and needs no external references; the Trigger / Workflow / Guardrails sections are well-organized and easy to navigate. Per the simple-skill guideline, this matches anchor 5 with just well-organized sections.	5 / 5
	Total	17 / 20 Passed

Description

53%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.

The description gives a clear, concise statement of what the skill does and is appropriately third-person, but it lacks any 'when to use' trigger guidance and leans on the subagent name rather than enumerating capabilities. Trigger-term coverage is thin, with no natural user phrasings or synonyms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to mine prior chats, update AGENTS.md, or run the continual-learning loop.'

Surface a few natural trigger terms users would actually say (e.g. 'update AGENTS.md', 'learn from past sessions', 'memory update') so the skill is discoverable by phrasing rather than only by jargon.

Briefly enumerate what the delegated flow covers (transcript mining, applying updates, summarizing changes) instead of relying solely on the agents-memory-updater name.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ("delegating transcript mining and AGENTS.md updates") but the actual capability is hidden behind the subagent name, so coverage is not comprehensive. It does not reach anchor 4 because it does not list several specific actions, and it is above anchor 2 because the actions named are concrete rather than generic.	3 / 5
Completeness	The 'what' is clear (orchestrate continual learning by delegating to agents-memory-updater), but there is no 'Use when...' clause or equivalent trigger guidance in the description, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Relevant keywords are present ("continual learning", "transcript mining", "AGENTS.md") but common natural phrasings and synonyms users would actually say are missing. It sits between anchor 3 and 4: coverage exists but is thin, with no user-facing variations.	3 / 5
Distinctiveness Conflict Risk	The niche is clear (AGENTS.md maintenance via a specifically named subagent) and unlikely to trigger the wrong skill, giving minor overlap risk. It falls short of anchor 5 because the description itself contains no distinct trigger phrases to fully separate it from general memory/notes-maintenance skills.	4 / 5
	Total	13 / 20 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
Path: continual-learning/skills/continual-learning/SKILL.md
Commit: c47b128

Reviewed: 2 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.