CtrlK
BlogDocsLog inGet started
Tessl Logo

cursor-custom-prompts

Create effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and reusable templates. Triggers on "cursor prompts", "prompt engineering cursor", "better cursor prompts", "cursor instructions", "cursor prompt templates".

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

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 highly actionable and token-efficient, packed with concrete templates and executable rule examples. Its weaknesses are the absence of any end-to-end workflow with validation checkpoints and, more notably, a progressive-disclosure failure where the SKILL.md body duplicates content that already lives in eight orphaned reference files it never cites.

Suggestions

Turn SKILL.md into an overview that links to the existing references/ files — e.g., 'See [prompt-templates.md](references/prompt-templates.md)' and 'See [advanced-techniques.md](references/advanced-techniques.md)' — and move the duplicated template/technique detail out of the body so the references stop being orphaned.

Add a short sequenced workflow with a checkpoint, e.g., 1) identify task type, 2) pick the matching template, 3) fill context/constraints, 4) test the generated output against the constraints before storing, 5) optionally promote to .cursor/rules/ — so the skill guides end-to-end use rather than only cataloging patterns.

Trim the inline five-template and four-technique sections once their detail is offloaded to references, keeping only one representative example of each in SKILL.md to reduce body length and the duplication that hurts progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean instructional prose — mostly templates, code blocks, and a compact anti-pattern table — and assumes Claude's competence without explaining basic concepts; it does not earn a 2 because there is no padded explanatory prose comparable to the anchor-2 example.

3 / 3

Actionability

It provides copy-paste-ready concrete guidance: five filled prompt templates with placeholders, two executable .cursor/rules YAML blocks, and worked CoT/few-shot examples, matching the anchor-3 "fully executable, copy-paste ready" criterion.

3 / 3

Workflow Clarity

Content is organized topic-by-topic (anatomy → templates → storage → advanced → anti-patterns) but presents no end-to-end sequenced workflow with validation checkpoints, so it sits at anchor-2 (sequence present but checkpoints missing) rather than 3; it avoids a 1 because the sections do provide loose ordering.

2 / 3

Progressive Disclosure

Eight reference files exist in ./references/ (templates, advanced techniques, examples, errors, fundamentals, etc.) but the body never links to any of them, while the body duplicates that same material inline — matching anchor-2 (references present but not signaled; content that should be separate is inline) rather than 3.

2 / 3

Total

10

/

12

Passed

Description

90%

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 well-formed, third-person description with an explicit trigger clause and a clear Cursor-specific niche. Its only weakness is that the capability statement rests on a single action verb with listed means rather than enumerating several distinct concrete actions.

DimensionReasoningScore

Specificity

It names the domain ("custom prompts for Cursor AI") and lists concrete means ("project rules, prompt engineering patterns, and reusable templates"), but the single action verb "Create effective custom prompts" is one action with modifiers rather than multiple distinct concrete actions like the anchor-3 example; "effective" is mild fluff.

2 / 3

Completeness

It explicitly answers what ("Create effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and reusable templates") and when via an explicit "Triggers on ..." trigger clause, satisfying the anchor-3 requirement of both what and explicit when.

3 / 3

Trigger Term Quality

The "Triggers on" clause lists natural phrases a user would say or search — "cursor prompts", "cursor instructions", "cursor prompt templates" — giving good coverage of common variations even if "prompt engineering cursor" has slightly awkward word order.

3 / 3

Distinctiveness Conflict Risk

The scope is tightly narrowed to Cursor AI with Cursor-specific trigger terms ("cursor prompts", "cursor instructions"), giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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.