mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
35
31%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex-plugin/skills/mine/SKILL.mdQuality
Discovery
32%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 conveys a general sense of purpose — extracting and storing memories from projects or conversations — but relies on metaphorical branding ('MemPalace') rather than concrete specifics. It lacks an explicit 'Use when...' clause, which significantly hurts completeness, and the trigger terms don't cover the natural language users would employ when wanting to save or recall information.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases like 'remember this', 'save this for later', 'store context', 'take notes from this conversation'.
Specify concrete actions more clearly, e.g., 'Extracts key facts, decisions, and action items from conversations or codebases and stores them as structured memories for future retrieval.'
Include common user-facing keywords and file/context types to improve trigger term coverage, such as 'notes', 'knowledge base', 'context saving', 'project history'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a domain (memory extraction/storage) and some actions ('mine', 'extract', 'store', 'retrieve'), but the actions are not concretely specified — what exactly is being extracted, what format, what kind of memories? The language is somewhat metaphorical ('MemPalace') rather than concrete. | 2 / 3 |
Completeness | It describes what the skill does (extract and store memories) but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also somewhat vague, so this falls to 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'memories', 'extract', 'store', 'retrieval', and 'MemPalace' (product-specific). However, it misses common natural user phrases like 'remember this', 'save this for later', 'take notes', 'knowledge base', or 'context'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'MemPalace' branding adds some distinctiveness, and the memory extraction concept is somewhat niche. However, it could overlap with note-taking, knowledge management, or general context-saving skills due to the vague framing. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a stub that delegates all content to an external CLI command. While it is maximally concise, it provides no actionable guidance, no workflow clarity, and no structured content for Claude to follow. If the CLI tool is unavailable or returns unexpected output, Claude has no fallback information.
Suggestions
Include at least a summary of what the 'mine' process does (e.g., what memories are extracted, how they are stored) so Claude has context even before running the command.
Add concrete steps or examples of the mining workflow inline — e.g., what inputs are expected, what outputs are produced, and how to validate results.
Provide fallback instructions or key details from the CLI's output directly in the SKILL.md so the skill is self-contained enough to be useful if the command is unavailable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely lean — just two lines of instruction with no unnecessary explanation. Every token earns its place. | 3 / 3 |
Actionability | The skill delegates all actual guidance to an external CLI command ('mempalace instructions mine') and provides zero concrete steps, examples, or executable guidance within the skill itself. Claude has no actionable information if the command fails or is unavailable. | 1 / 3 |
Workflow Clarity | There is no workflow described — no steps, no validation, no sequence. The entire process is deferred to an external tool's output, leaving Claude with no understanding of what the mining process entails. | 1 / 3 |
Progressive Disclosure | There are no bundle files, no referenced documents, and no structure beyond a single command. The skill is not a well-organized overview pointing to detailed materials — it's an empty shell pointing to a runtime CLI output. | 1 / 3 |
Total | 6 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- milla-jovovich/mempalace
- Commit
db1fbe8
- 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.