cursor-codebase-indexing

Set up and optimize Cursor codebase indexing for semantic code search and @Codebase queries. Triggers on "cursor index", "codebase indexing", "index codebase", "cursor semantic search", "@codebase", "cursor embeddings".

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/cursor-pack/skills/cursor-codebase-indexing/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

The body is highly actionable with concrete, executable examples and a useful troubleshooting table. Its weaknesses are moderate verbosity from concept explanation and content duplication, missing validation checkpoints in the destructive re-index workflow, and orphaned reference files that are never linked from the overview.

Suggestions

Replace the explanatory 'How Indexing Works' diagram/text with a one-line summary; Claude already understands embeddings and chunking.

Add an explicit validation checkpoint to the Re-Indexing workflow (e.g., 'Confirm status bar shows Indexed before relying on @Codebase') since cache deletion is destructive.

Link the existing references/ files from the relevant body sections (e.g., 'See references/configuration.md for full .cursorignore templates') and move the duplicated inline blocks into those references to avoid redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful and actionable, but the 'How Indexing Works' section explains embeddings/chunking concepts Claude already knows, and Configuration/Optimization/Troubleshooting content is duplicated verbatim in spirit by the references/ files. Not score 3 because of this redundant and explanatory padding; not score 1 because the bulk is concrete guidance rather than vague prose.	2 / 3
Actionability	Provides copy-paste-ready .cursorignore/.cursorindexingignore blocks, real bash/sysctl commands, concrete @Codebase query examples, and a troubleshooting table with specific fixes. Not below 3 because guidance is fully executable rather than abstract.	3 / 3
Workflow Clarity	Initial Setup and Re-Indexing are clearly sequenced with numbered steps, but the cache-deletion/re-index workflow is destructive yet lacks an explicit validation checkpoint or feedback loop before proceeding. Capped at 2 per the destructive-operation guideline; not score 1 because sequences are present and clear.	2 / 3
Progressive Disclosure	The body has good section structure, but full Configuration/Optimization/Troubleshooting content is inlined while parallel reference files (configuration.md, optimization-for-large-projects.md, troubleshooting.md) exist and are never linked from the body, leaving them orphaned and un-signaled. Not score 3 because references are not clearly signaled and content that should be separate is inline; not score 1 because the body is organized into coherent sections rather than a monolithic wall.	2 / 3
	Total	9 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 clearly defines a distinct niche and supplies explicit trigger terms, with proper third-person voice. Its main weakness is specificity: it names the domain and a few actions but does not enumerate a broad set of concrete capabilities.

Suggestions

Expand the 'what' clause with a few more concrete actions (e.g., 'configure .cursorignore, optimize monorepo indexing, troubleshoot stale results') to lift specificity.

Keep the explicit trigger list; consider adding '@Codebase' alongside the lowercase '@codebase' variation already present.

Dimension	Reasoning	Score
Specificity	Names the domain ('Cursor codebase indexing') and a couple of actions ('Set up and optimize', 'semantic code search', '@Codebase queries'), but the action list is narrow rather than a comprehensive set of concrete capabilities. Not score 3 because it does not list multiple specific concrete actions; not score 1 because the domain and intent are concrete, not vague.	2 / 3
Completeness	States what it does ('Set up and optimize Cursor codebase indexing for semantic code search and @Codebase queries') and explicitly when to use it via the 'Triggers on ...' clause. Not score 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	Explicit trigger list ('cursor index', 'codebase indexing', 'index codebase', 'cursor semantic search', '@codebase', 'cursor embeddings') covers the natural phrases a user would actually say. Not below 3 because coverage of common variations is strong and on-domain.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly scoped to Cursor's codebase indexing with distinctive triggers, making conflict with other skills unlikely. Not score 2 because the triggers are specific enough to avoid overlap with generic search/indexing skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/cursor-pack/skills/cursor-codebase-indexing/SKILL.md
Commit: 0540a62

Reviewed: about 23 hours 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.