search
Search your MemPalace — semantic search across all mined memories, projects, and conversations.
48
51%
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/search/SKILL.mdQuality
Discovery
50%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 communicates the core function (semantic search over a memory store) and names the specific system ('MemPalace'), but lacks an explicit 'Use when...' clause and doesn't enumerate concrete actions beyond searching. It would benefit from natural trigger terms users would actually say and clearer guidance on when Claude should select this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to recall, find, or look up past conversations, stored memories, or project context.'
Include natural trigger term variations such as 'find', 'recall', 'look up', 'remember', 'query memories' to improve matching.
List additional concrete actions if applicable, e.g., 'Search, filter, and retrieve stored memories, project notes, and conversation history.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('MemPalace') and a core action ('semantic search'), and mentions what is searched ('mined memories, projects, and conversations'), but it doesn't list multiple concrete actions beyond searching. | 2 / 3 |
Completeness | The 'what' is reasonably clear (semantic search across memories/projects/conversations), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'search', 'memories', 'projects', 'conversations', and 'MemPalace', but 'MemPalace' is a proprietary term users may not naturally say. Missing common variations like 'find', 'recall', 'look up', 'query'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'MemPalace' branding and 'mined memories' give it some distinctiveness, but 'search across projects and conversations' is broad enough to potentially overlap with other search or knowledge-retrieval skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
52%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 a CLI command's runtime output. While maximally concise, it provides almost no actionable information for Claude to understand the search tool's capabilities, parameters, expected inputs/outputs, or error handling. Claude would be entirely dependent on parsing CLI output at runtime with no prior context.
Suggestions
Add a brief summary of what `mempalace instructions search` does, including key parameters/flags (e.g., query syntax, filters, output format) so Claude has context before running the command.
Include at least one concrete example showing a search query and expected output format so Claude knows what to expect.
Add basic error handling guidance — what to do if the command fails, returns no results, or if mempalace is not installed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely lean — just a command to run and an instruction to follow the output. No unnecessary explanation or padding. | 3 / 3 |
Actionability | It provides a concrete command to run, but all actual guidance is deferred to the CLI output. Claude has no information about what the search tool does, what arguments it accepts, what output to expect, or how to interpret results — making it only partially actionable. | 2 / 3 |
Workflow Clarity | There is no workflow described at all. The skill entirely delegates to an external CLI's runtime instructions, providing no sequence, no validation steps, and no error handling guidance. Claude has no way to know what steps are involved. | 1 / 3 |
Progressive Disclosure | The skill is short and well-organized for its minimal content, but it delegates everything to a CLI without any overview of what the search capability entails, what parameters are available, or what to expect — making navigation and discovery poor. No bundle files support it either. | 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 |
|---|---|---|
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.