CtrlK
BlogDocsLog inGet started
Tessl Logo

cursor-indexing-issues

Troubleshoot Cursor codebase indexing: stuck indexing, empty search, @codebase failures, and performance issues. Triggers on "cursor indexing", "cursor index", "@codebase not working", "cursor search broken", "indexing stuck".

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

The body is concrete and highly actionable with minimal fluff, but two gaps hold it back: workflows involving destructive cache clearing lack explicit validation checkpoints, and the provided reference bundle is unused — its content is duplicated inline rather than split out and navigated to.

Suggestions

Add an explicit validation checkpoint to the destructive cache-clearing workflow (e.g., 'Confirm Cursor is fully quit before running rm -rf' and 'Verify a fresh re-index begins on restart') to lift workflow_clarity to 3.

Reference the bundle files from the body instead of duplicating their content — e.g., replace the inlined .cursorignore block with 'See [references/.cursorignore-configuration.md] for full patterns' and point troubleshooting detail to [references/common-indexing-issues.md] and [references/errors.md].

De-duplicate the .cursorignore patterns and the stuck-indexing / empty-search fixes that currently appear in both the body and the reference files so each topic lives in one place.

DimensionReasoningScore

Conciseness

The body is lean and action-oriented — mostly tables, commands, and config snippets — and does not explain concepts Claude already knows; it assumes competence throughout.

3 / 3

Actionability

Provides fully executable, copy-paste-ready guidance: `rm -rf` cache paths, `Cmd+Shift+P > Cursor: Resync Index`, sysctl commands, settings.json snippets, and complete .cursorignore/.cursorindexingignore examples.

3 / 3

Workflow Clarity

Steps are sequenced (Step 1/2/3, Check 1-4) but lack explicit validation checkpoints, and the destructive `rm -rf` cache-clearing step has no verify-before/after checkpoint — capping at 2 per the destructive-operations guideline.

2 / 3

Progressive Disclosure

Five bundle reference files exist (common-indexing-issues.md, errors.md, examples.md, index-verification.md, .cursorignore-configuration.md) but none are linked or signaled from the body, and their content is duplicated inline — matching the 'references present but not clearly signaled; content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities, gives explicit natural-language triggers, answers both 'what' and 'when', and occupies a clear niche. The only blemish is YAML folding artifacts (stray newlines mid-phrase) that slightly mar readability without changing meaning.

DimensionReasoningScore

Specificity

Names concrete capabilities via specific problem categories — 'stuck indexing, empty search, @codebase failures, and performance issues' under a clear 'Troubleshoot' action verb, matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what ('Troubleshoot Cursor codebase indexing: stuck indexing, empty search, @codebase failures, and performance issues') and when ('Triggers on ...'), with an explicit trigger clause in third person.

3 / 3

Trigger Term Quality

Explicit natural-language triggers ('cursor indexing', 'cursor index', '@codebase not working', 'cursor search broken', 'indexing stuck') cover the phrasings a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The 'Cursor codebase indexing' niche with '@codebase not working' / 'cursor search broken' triggers is distinct and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.