continual-learning

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

Quality

41%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./continual-learning/skills/continual-learning/SKILL.md

Quality

Content

64%

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

This is a very concise orchestration skill that clearly defines its boundaries and guardrails. However, it lacks concrete invocation details for the subagent call and has no error handling or validation steps. The reference to `agents-memory-updater` is unsupported by any linked file or bundle.

Suggestions

Add a concrete example of how to invoke `agents-memory-updater` (e.g., the exact tool call or subagent dispatch syntax).

Add a brief error-handling step: what should happen if the subagent fails or returns an unexpected result.

Include a reference or link to the `agents-memory-updater` skill definition so the dependency is navigable.

Dimension	Reasoning	Score
Conciseness	Extremely lean — every line serves a purpose. No unnecessary explanations of what subagents are or how orchestration works. Assumes Claude's competence throughout.	3 / 3
Actionability	The workflow says 'Call agents-memory-updater' but provides no concrete invocation syntax, tool call format, or example of how to actually call the subagent. The guidance is directional but not copy-paste executable.	2 / 3
Workflow Clarity	The two-step workflow is clear in sequence, but there are no validation checkpoints — no guidance on what to do if the subagent fails, returns errors, or produces unexpected results. For an orchestration skill that delegates to a subagent, error handling/feedback loops would be expected.	2 / 3
Progressive Disclosure	The skill references `agents-memory-updater` as a subagent but provides no link or path to its definition. No bundle files are provided to support the reference. A well-signaled pointer to the subagent's skill file would improve navigation.	2 / 3
	Total	9 / 12 Passed

Description

17%

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 overly jargon-heavy and lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill. While it references specific artifacts (AGENTS.md, agents-memory-updater), the core purpose and trigger conditions remain unclear. It needs more natural language trigger terms and explicit guidance on when to activate.

Suggestions

Add an explicit 'Use when...' clause describing trigger conditions, e.g., 'Use when the user asks to update agent memory, save learnings from conversations, or refresh AGENTS.md with new knowledge.'

Replace jargon like 'orchestrate continual learning' and 'transcript mining' with natural terms users would say, such as 'update memory', 'learn from past conversations', or 'extract insights from transcripts'.

Clarify the concrete actions performed—what does 'orchestrate' mean in practice? Specify steps like 'extracts key information from conversation transcripts and delegates updates to agents-memory-updater to modify AGENTS.md'.

Dimension	Reasoning	Score
Specificity	Names a domain (continual learning) and some actions (delegating transcript mining, AGENTS.md updates), but the description is somewhat abstract—'orchestrate continual learning' is vague, and the concrete mechanics of what this skill actually does beyond delegation are unclear.	2 / 3
Completeness	The description provides a partial 'what' (orchestrate learning via delegation) but has no explicit 'when' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	The terms used ('orchestrate continual learning', 'transcript mining', 'agents-memory-updater') are highly technical and internal jargon. A user would not naturally say any of these phrases when needing this skill; common trigger terms like 'update memory', 'learn from conversations', or 'save notes' are absent.	1 / 3
Distinctiveness Conflict Risk	The mention of a specific tool ('agents-memory-updater') and 'AGENTS.md' gives it some distinctiveness, but 'continual learning' and 'transcript mining' are vague enough that overlap with other memory or knowledge management skills is plausible.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: cursor/plugins
Commit: cfd81b3

Reviewed: 3 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.