Tessl • The package manager for agent skills

Blog Docs Log inGet started

SkillPublic

code-deduplication

Prevent semantic code duplication with capability index and check-before-write

Quality

60%

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/code-deduplication/SKILL.md

Quality

Content

52%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 skill delivers genuinely actionable anti-duplication guidance with concrete code, templates, and a clear decision workflow. Its main weaknesses are token bloat from a massive illustrative index and duplicated language templates, and the complete absence of progressive disclosure — everything lives inline in one long file with no bundle references.

Suggestions

Move the full example CODE_INDEX.md and the Vector DB Integration section into references/ (e.g. references/index-template.md, references/vector-search.md) and link to them from SKILL.md.

Collapse the parallel TypeScript/Python file-header and function-doc templates into one canonical example, and trim the example index to 2-3 rows per category.

Provide the actual scripts (or define the behavior) behind '/update-code-index' and '/audit-duplicates', and specify a concrete audit cadence (e.g. after every N commits or on demand).

Dimension	Reasoning	Score
Conciseness	The body inlines a ~100-line fully-populated example CODE_INDEX.md, ASCII-art boxes, and parallel TypeScript/Python versions of the same docstring templates — several sections are padded with illustrative data Claude could infer from a few rows.	2 / 5
Actionability	Concrete, executable guidance throughout: grep commands, decision tree, bad/good code pairs, and runnable ChromaDB/LanceDB snippets. Minor gap: '/update-code-index' and '/audit-duplicates' are invoked as commands but no scripts are provided in the bundle.	4 / 5
Workflow Clarity	The check-before-write sequence is clearly laid out (describe, check index, evaluate, extend-or-create) with checkpoints like 'Only create new if confirmed nothing suitable exists' and 'check for breaking changes'. The periodic audit lacks a defined cadence or explicit feedback loop, keeping it below 5.	4 / 5
Progressive Disclosure	This is a 535-line monolithic SKILL.md with no reference files at all; the full example index, vector-DB setup, and audit output format clearly belong in separate referenced files, matching the anchor for content inlined that should be separate.	2 / 5
	Total	12 / 20 Passed

Description

53%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 concise and names a distinct niche, with a clear 'what' anchored by the capability-index mechanism. However, it lacks any 'Use when...' trigger guidance and offers only a thin set of concrete actions, limiting both completeness and trigger discoverability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating new utility functions, shared code, or helper modules, or when the user mentions duplicate or redundant code.'

Enumerate 1-2 more concrete capabilities, e.g. 'maintains CODE_INDEX.md, checks for existing implementations before writing, and audits for semantic overlap.'

Include natural user phrasings such as 'duplicate code', 'code reuse', and 'existing utility functions' so the skill triggers on how users actually describe the need.

Dimension	Reasoning	Score
Specificity	The description names the domain ('semantic code duplication') and a mechanism ('capability index and check-before-write'), but these constitute only 1-2 concrete actions rather than a comprehensive list of capabilities.	3 / 5
Completeness	It has a clear 'what' ('Prevent semantic code duplication with capability index and check-before-write') but no 'Use when...' clause or equivalent trigger guidance in the description itself, capping completeness at 3.	3 / 5
Trigger Term Quality	'code duplication', 'capability index', and 'check-before-write' are relevant keywords, but common natural phrasings users would say ('duplicate code', 'reuse existing functions', 'refactor utilities') are missing.	3 / 5
Distinctiveness Conflict Risk	'Semantic code duplication' and 'capability index' carve out a fairly distinct niche that is unlikely to trigger for unrelated skills, though it could overlap with general refactoring or code-review skills.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (544 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: alinaqi/maggy
Path: skills/code-deduplication/SKILL.md
Revision: 55aabe2

Reviewed: 20 days ago

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.

code-deduplication

Table of Contents

Is this your skill?