continual-learning
Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
46
33%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./continual-learning/skills/continual-learning/SKILL.mdQuality
Discovery
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 technical and internally-focused, using jargon that wouldn't match natural user requests. It lacks an explicit 'Use when...' clause and the concrete actions are described at a meta-orchestration level rather than specifying tangible outcomes. The mention of specific tools (agents-memory-updater, AGENTS.md) provides some distinctiveness but doesn't compensate for poor trigger coverage and missing usage guidance.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to update agent memory, learn from conversation transcripts, or refresh AGENTS.md with new knowledge.'
Replace abstract orchestration language with concrete actions, e.g., 'Extracts key learnings from conversation transcripts and updates AGENTS.md with new patterns, preferences, and instructions.'
Include natural user-facing keywords like 'update memory', 'learn from conversations', 'save preferences', 'agent configuration' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a domain (continual learning) and some actions (delegating transcript mining, AGENTS.md updates), but the actions are somewhat abstract—'orchestrate' and 'delegating' are meta-level rather than concrete end-user-facing capabilities. | 2 / 3 |
Completeness | Describes a rough 'what' (orchestrate learning via delegation) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is vague enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | Uses technical/internal jargon like 'orchestrate continual learning', 'transcript mining', 'agents-memory-updater', and 'AGENTS.md' which are not terms a user would naturally say when requesting this functionality. | 1 / 3 |
Distinctiveness Conflict Risk | References specific artifacts like 'agents-memory-updater' and 'AGENTS.md' which provide some distinctiveness, but the broader framing of 'continual learning' and 'transcript mining' could overlap with other memory or knowledge management skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is admirably concise and well-structured as a thin orchestration layer, but it sacrifices actionability by providing almost no concrete detail on how to invoke the subagent — no tool call syntax, parameters, or expected response format. The guardrails are useful constraints, but the lack of error handling and missing navigable references to the subagent weaken the overall utility.
Suggestions
Add a concrete example of how to invoke `agents-memory-updater` (e.g., the exact tool call or dispatch syntax with any required parameters).
Include basic error handling: what to do if the subagent call fails or returns unexpected results.
Add an explicit link/path to the `agents-memory-updater` skill definition so Claude can navigate to it (e.g., `See [agents-memory-updater/SKILL.md](../agents-memory-updater/SKILL.md)`).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — every line serves a purpose. No unnecessary explanation of what subagents are or how AGENTS.md works. Assumes Claude's competence throughout. | 3 / 3 |
Actionability | The workflow is essentially 'call agents-memory-updater and return the result' with no concrete details on how to invoke the subagent (tool call syntax, parameters, expected input/output). This is vague direction rather than executable guidance. | 1 / 3 |
Workflow Clarity | The two-step sequence is clear and the guardrails provide useful constraints, but there is no validation or error handling — what happens if the subagent fails? For an orchestration skill that delegates to a subagent, some feedback loop or success/failure check 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. With no bundle files provided, there's no way to navigate to the referenced subagent's details. A clear reference (e.g., 'See [agents-memory-updater/SKILL.md]') would improve discoverability. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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
7dd9fea
- 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.