recall
Fan-out search across all memory sources when context is unclear or vaguely referenced. Triggers on: 'from earlier', 'remember when', 'what we discussed', 'that thing with', 'the conversation about', 'did we ever', 'what happened with', 'you mentioned', 'we talked about', 'earlier today', 'last session', 'the other day', or any vague reference to past context that needs resolution before the agent can act.
92
91%
Does it follow best practices?
Impact
96%
1.41xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger term coverage and clear completeness, explicitly listing both what the skill does and when it should be used. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., querying multiple memory stores, ranking results, disambiguating). Overall it would serve well in a multi-skill selection scenario.
Suggestions
Add more specific concrete actions beyond 'fan-out search' — e.g., 'queries conversation logs, knowledge bases, and session history; ranks and returns matching context snippets' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('fan-out search across all memory sources') and one key action (resolving vague references to past context), but doesn't list multiple concrete actions like querying specific memory stores, returning ranked results, or disambiguating between matches. | 2 / 3 |
Completeness | Clearly answers both 'what' (fan-out search across all memory sources when context is unclear) and 'when' (explicit trigger phrases plus the general condition 'any vague reference to past context that needs resolution before the agent can act'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'from earlier', 'remember when', 'what we discussed', 'that thing with', 'the other day', etc. These are highly realistic conversational phrases that map well to user intent. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche — vague past-context resolution via memory search — with highly specific trigger phrases that are unlikely to conflict with other skills. The 'fan-out search across all memory sources' framing distinguishes it from single-source memory lookups or other retrieval skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that provides concrete, executable guidance for a complex fan-out search operation. It excels at actionability with real commands and paths, has a clear workflow with error handling, and respects Claude's intelligence by not over-explaining. The only minor weakness is that all content lives in one file, though the skill's length makes this a marginal concern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose — trigger detection, search sources, workflow, timeouts, anti-patterns. There's no explanation of what grep does or how memory works conceptually. The trigger list is necessarily verbose but earns its place as a reference. | 3 / 3 |
Actionability | Fully executable bash commands for each memory source, specific file paths, concrete tool invocations (session_context, redis-cli, slog), and copy-paste ready examples with good/bad patterns. The keyword extraction step includes a concrete example transformation. | 3 / 3 |
Workflow Clarity | Clear 5-step workflow with explicit sequencing (extract → fan out → synthesize → present → handle failure). Includes mandatory timeout validation, an explicit 'if nothing found' error path, and anti-patterns that serve as guardrails. The fan-out search is numbered and prioritized (fastest first). | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections and headers, but all content is inline in a single file. The 8 search sources could potentially be split into a reference file, and the trigger phrase list could be externalized. However, for a skill of this size (~90 lines of meaningful content), keeping it in one file is borderline acceptable. | 2 / 3 |
Total | 11 / 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
- joelhooks/joelclaw
- Commit
825972c
- 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.