iterative-retrieval
tessl i github:ysyecust/everything-claude-code --skill iterative-retrievalPattern for progressively refining context retrieval to solve the subagent context problem
Validation
81%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 13 / 16 Passed | |
Implementation
85%This is a well-structured skill that clearly explains a useful pattern for iterative context retrieval. The workflow is exceptionally clear with good visual aids and practical examples. The main weakness is that the guidance is more conceptual than executable - it describes the pattern rather than providing copy-paste implementation code.
Suggestions
Add executable code showing how to implement the DISPATCH phase (e.g., actual glob/search function calls)
Provide a concrete implementation snippet for the EVALUATE scoring logic rather than just criteria descriptions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a purpose - the problem statement is brief, the solution is clearly diagrammed, and examples are practical without padding. | 3 / 3 |
Actionability | While the pattern is well-explained with concrete examples, the guidance is more conceptual than executable. The examples show the pattern in action but aren't copy-paste ready code - they're structured pseudocode/workflow descriptions rather than actual implementation. | 2 / 3 |
Workflow Clarity | The 4-phase loop is clearly sequenced with explicit stopping conditions (3+ high-relevance files, no critical gaps, max cycles). The diagram and phase descriptions make the workflow unambiguous, and the examples demonstrate the feedback loop in action. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections progressing from problem to solution to examples to integration. For a self-contained pattern document of this size, no external references are needed - all content is appropriately inline and easy to navigate. | 3 / 3 |
Total | 11 / 12 Passed |
Activation
7%This description is too abstract and pattern-focused rather than action-oriented. It fails to explain what concrete tasks Claude can perform, uses technical jargon users wouldn't naturally use, and lacks any explicit trigger guidance for when to select this skill.
Suggestions
Replace abstract 'pattern' language with specific actions (e.g., 'Retrieves and refines context for subagent tasks by querying knowledge bases, filtering results, and iteratively narrowing scope')
Add a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when spawning subagents, delegating tasks, or when subagents need access to conversation history')
Define the 'subagent context problem' in user-friendly terms so Claude knows when this skill applies versus general context or retrieval skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract language like 'pattern' and 'progressively refining context retrieval' without listing any concrete actions. It describes a concept rather than specific capabilities. | 1 / 3 |
Completeness | Missing both clear 'what' (no concrete actions listed) and 'when' (no explicit trigger guidance or 'Use when...' clause). The description only vaguely hints at a problem domain. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('subagent context problem', 'context retrieval') that users would not naturally say. No common user-facing keywords are present. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'subagent context problem' provides some specificity to a niche domain, but 'context retrieval' is generic enough to potentially overlap with other retrieval or search-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
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.