iterative-retrieval

Pattern for progressively refining context retrieval to solve the subagent context problem. Use when a subagent lacks the context it needs and retrieval must be refined across passes.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/iterative-retrieval/SKILL.md

The canonical home for this skill is tdg-personal/iterative-retrieval

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers a well-structured, actionable 4-phase retrieval loop with executable code and illustrative examples. It is slightly padded by an ASCII diagram and introductory framing, and lacks external reference files despite being over 50 lines.

Suggestions

Trim the ASCII diagram and the "Standard approaches fail" exposition; the code and Best Practices already convey the rationale, saving significant tokens.

Define or stub the helper functions (retrieveFiles, scoreRelevance, extractPatterns, identifyGaps) so the examples are copy-paste runnable rather than relying on implied APIs.

Move the longer worked examples or the per-phase code into a reference file under ./references/ and link from the body, improving progressive disclosure for a 200+ line skill.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and examples, but the decorative ASCII diagram and the "Standard approaches fail" / "Problem" exposition restate things Claude could infer and could be tightened.	3 / 5
Actionability	Each phase ships concrete JavaScript (evaluateRelevance, refineQuery, iterativeRetrieve) with real logic and worked examples; minor gaps are the undefined helpers (retrieveFiles, scoreRelevance, extractPatterns).	4 / 5
Workflow Clarity	The 4-phase loop is clearly sequenced with an explicit max-3-cycles limit and a sufficiency checkpoint (highRelevance >= 3 && !hasCriticalGaps), though error-recovery guidance beyond "refine and continue" is light.	4 / 5
Progressive Disclosure	No bundle files exist, so all content is inline, but it is well-sectioned (When to Activate, Problem, Solution, Examples, Best Practices, Related) with clearly signaled outbound links; minor gap is that the larger code/diagram blocks could live in reference files.	4 / 5
	Total	15 / 20 Passed

Description

78%Weight 40%Scale 1-5

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 cleanly answers both what the skill does and when to use it with a concrete trigger clause, avoiding vague fluff. It is slightly abstract on specific actions and could add a couple more natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ("progressively refining context retrieval") and the concrete action of refining retrieval across passes, but the phrasing stays abstract rather than enumerating multiple specific operations.	3 / 5
Completeness	It explicitly states what ("Pattern for progressively refining context retrieval to solve the subagent context problem") and when ("Use when a subagent lacks the context it needs and retrieval must be refined across passes") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural trigger phrases like "a subagent lacks the context it needs" and "retrieval must be refined across passes" map well to what a user would say, though synonyms like RAG or multi-agent are absent.	4 / 5
Distinctiveness Conflict Risk	The "subagent context problem" framing carves a clear niche with minimal conflict risk, though "context retrieval" is broad enough to slightly overlap with general RAG skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/iterative-retrieval/SKILL.md
Commit: 06c5e11

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.