CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

search-hierarchy

Search Tool Hierarchy

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/archive/search-hierarchy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 is a tight, well-structured decision aid with executable examples and a clear tool-selection workflow; it assumes Claude's knowledge and avoids padding. The main gaps are minor redundancy between the tree and table, pseudo-syntax for two tool examples, and a referenced hook script that is not bundled.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explanations of what grep or tokens are), but the Decision Tree and the Token Efficiency Comparison table overlap on tool output sizes, so a few tokens could be trimmed; not a 5 because of that redundancy.

4 / 5

Actionability

The Examples section gives concrete executable commands for AST-grep and LEANN, but the 'Grep pattern=...' and 'Read file_path=...' entries use tool-call pseudo-syntax rather than exact CLI invocations, leaving minor gaps.

4 / 5

Workflow Clarity

The Decision Tree provides a clear selection workflow and the Optimal Flow section sequences the steps (AST-grep -> Read top match -> skip irrelevant), but there are no explicit validation checkpoints or feedback loops; this is acceptable since search selection is not destructive, so it sits just below 5.

4 / 5

Progressive Disclosure

Content is well-organized into clearly signaled sections (Decision Tree, comparison table, DO/DON'T, Examples, Optimal Flow) with no nested references, but the body references a 'grep-to-leann.sh' hook that is not present in the bundle, a minor dangling-reference gap.

4 / 5

Total

16

/

20

Passed

Description

28%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 is essentially a title with no action verbs, no trigger guidance, and no use-when clause, so it fails to tell a user or Claude when to invoke it. It names a real domain but is far below the quality of the good examples.

Suggestions

Rewrite as a third-person capability statement with concrete actions, e.g. 'Selects the most token-efficient search tool (AST-grep, LEANN, Grep, Read) for a given query type.'

Add an explicit trigger clause: 'Use when searching code for structural patterns, conceptual questions, or exact identifiers.'

Include natural trigger terms users actually say (grep, find, code search, AST-grep) to improve trigger term quality and distinctiveness.

DimensionReasoningScore

Specificity

The description 'Search Tool Hierarchy' names the domain (search tools) but contains no action verbs at all, matching the anchor 'names the domain but actions are minimal or generic'; it is not a 1 because it does specify a concrete domain rather than being entirely abstract.

2 / 5

Completeness

It offers only a vague 'what' (a hierarchy of search tools) and entirely lacks a 'when/Use when...' clause, which per the guidelines caps completeness at 3 and here matches 'has a vague what and no when'.

2 / 5

Trigger Term Quality

Only the single generic keyword 'search' appears, with none of the natural phrases or synonyms (grep, find, code search, AST-grep) a user would actually say, fitting 'one or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

'Search' is a broadly applicable task that overlaps with many search-related skills, but the framing as a tool-selection hierarchy is somewhat specific, fitting 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

9

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

parcadei/Continuous-Claude-v3

Path

.claude/skills/archive/search-hierarchy/SKILL.md

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.