code-search-assistant

Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Use when finding related code, locating similar implementations, discovering code dependencies, or identifying code that performs similar operations. Outputs ranked file lists with matching code snippets and relevance scores.

Install with Tessl CLI

npx tessl i github:ArabelaTso/Skills-4-SE --skill code-search-assistant

What are skills?

Review — 81%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

41%

Find Related Order Processing Code

Three-dimensional similarity scoring and output format

Criteria

Without context

With context

Call chain dimension

50%

100%

Textual dimension

50%

100%

Functional dimension

70%

100%

Per-result score breakdown

20%

100%

Scoring formula applied

100%

Score range labels

100%

Why it matches explanation

100%

File path in results

100%

Code snippet included

100%

Structural element extraction

100%

Without context: $0.4736 · 4m 18s · 16 turns · 20 in / 9,557 out tokens

With context: $0.7889 · 5m 49s · 25 turns · 284 in / 13,326 out tokens

64%

14%

Find Similar Data Pipeline Functions

Ranking adjustments and result formatting

Criteria

Without context

With context

Same-directory boost

Test file penalty

50%

100%

Vendor/generated penalty

100%

Line numbers in results

100%

Top 10 limit

100%

Code snippet length

100%

Glob used for file discovery

Grep used for candidate search

33%

Results ranked by score

100%

Without context: $0.2939 · 2m 27s · 9 turns · 14 in / 5,999 out tokens

With context: $0.6429 · 5m 42s · 17 turns · 177 in / 12,436 out tokens

99%

Locate Similar Input Validation Code Across Services

Functional search categories and score range classification

Criteria

Without context

With context

Functional category identified

100%

Validation search terms used

100%

90%

Regex/conditional check pattern

100%

Score range tier applied

100%

Multiple tier levels present

100%

All three dimensions applied

50%

100%

Per-dimension sub-scores shown

100%

Functional element extraction

100%

Why it matches included

100%

Results in ranked order

100%

Without context: $0.4092 · 4m 12s · 10 turns · 13 in / 9,153 out tokens

With context: $0.5594 · 4m 30s · 18 turns · 273 in / 9,759 out tokens

Evaluated: about 11 hours ago
Agent: Claude Code

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.