code-deduplication

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The skill is highly actionable with executable examples, templates, and clear sequencing, but it is verbose for its context window budget, lacks validation feedback loops in its workflows, and is monolithic rather than progressively disclosed across files.

Suggestions

Move the optional Vector DB integration (ChromaDB/LanceDB) and the full sample CODE_INDEX.md into separate reference files, leaving SKILL.md a lean overview with one-level-deep pointers.

Collapse the repeated ASCII "check before you write" boxes into a single concise statement and trim the illustrative index tables to a small representative sample.

Add explicit validation checkpoints, e.g. after updating CODE_INDEX.md verify the entry's signature matches the real function, and after merging duplicate functions confirm no consumers broke before proceeding.

Dimension	Reasoning	Score
Conciseness	At ~535 lines the body restates the core "check before you write" message in multiple ASCII boxes and pads with ~100 lines of illustrative index tables plus duplicated TypeScript/Python examples, so while real instruction is present it could be tightened considerably; this fits 'mostly efficient but includes unnecessary explanation' rather than the lean score-3 anchor.	2 / 3
Actionability	The body provides executable TypeScript/Python code, concrete commands (/audit-duplicates, /update-code-index, grep -r), copy-paste templates, and a decision tree, matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	Steps (check-before-write, decision tree, session-start/before/after-writing, audit checklist) are clearly sequenced, but validation/verification checkpoints are missing — no verify step after updating CODE_INDEX.md and no feedback loop confirming merged code does not break consumers — capping this at 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is a single monolithic ~535-line SKILL.md with content that should be split (the optional Vector DB section and the large sample CODE_INDEX.md) kept inline, fitting 'some structure but content that should be separate is inline'; it is not the under-50-line simple-skill case that would allow a 3.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and occupies a clear, low-conflict niche, but it omits an explicit in-description trigger clause and lacks breadth of natural trigger terms, leaving completeness and trigger coverage at the middle level.

Suggestions

Add an explicit "Use when..." clause directly in the description (e.g., "Use when adding utility functions, shared helpers, or noticing duplicated logic") to raise completeness above 2.

Broaden trigger-term coverage with natural phrasings users actually say, such as "duplicate code", "DRY", "refactor", or "shared utilities".

Keep the concrete mechanisms but consider folding the when-to-use guidance into the description so the trigger is not isolated in a separate field.

Dimension	Reasoning	Score
Specificity	The phrase "Prevent semantic code duplication with capability index and check-before-write" names the domain plus multiple concrete mechanisms (capability index, check-before-write), matching the 'lists multiple specific concrete actions' anchor rather than the score-2 'some actions, not comprehensive'.	3 / 3
Completeness	The description answers "what" (prevent duplication via index + check-before-write) but contains no "Use when..." clause; the trigger guidance lives only in the separate when-to-use field, so per the guideline a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	"code duplication" and "semantic duplication" are relevant terms, but common natural variations a user would say (e.g., "duplicate code", "DRY", "refactor", "utilities", "shared code") are missing, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche of "semantic code duplication" addressed via a capability index and check-before-write is distinct and unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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/claude-bootstrap
Commit: 9896dec

Reviewed: 1 day 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.