CtrlK
BlogDocsLog inGet started
Tessl Logo

cursor-context-management

Optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy. Triggers on "cursor context", "context window", "context limit", "cursor memory", "context management", "@-mentions", "context pills".

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/cursor-pack/skills/cursor-context-management/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A concrete, well-organized guide with strong copy-paste examples and configs. Its biggest gap is progressive disclosure: seven reference files exist but are entirely orphaned, with their content duplicated inline rather than linked from the overview.

Suggestions

Link the seven references/ files from the body (e.g., a '## Further reading' section pointing to advanced-techniques.md, best-practices.md, examples.md, errors.md, conversation-context.md, managing-large-codebases.md) so the overview stays lean and the bundle is discoverable.

Move the inlined advanced/best-practice material (layered context, context priming, @-mention strategy advice) into the corresponding reference files and summarize one-liners in SKILL.md to reduce duplication.

Move the time-sensitive model token-limit table into a reference (or mark it as approximate/current) so the main body avoids date-sensitive facts, improving conciseness.

DimensionReasoningScore

Conciseness

The body is largely lean and product-specific (Cursor UI mechanics), but includes a time-sensitive model token-limit table not placed in a deprecated section and some mild explanatory prose ("managing it well is the single biggest lever"), so it could be tightened.

2 / 3

Actionability

It supplies concrete, copy-paste-ready @-mention prompt templates per task type, a full .cursorignore block, and a .cursor/rules .mdc example, giving specific executable guidance rather than vague direction.

3 / 3

Workflow Clarity

Content is organized by task category with per-task patterns, but there is no sequenced multi-step workflow with validation checkpoints; this is acceptable for a non-destructive guide, yet the structure is advisory rather than a clear procedural sequence.

2 / 3

Progressive Disclosure

The body is sectioned (not a wall of text), but the seven files in references/ (advanced-techniques, best-practices, conversation-context, errors, examples, managing-large-codebases, context-optimization-strategies) are never linked or signaled from the body, and overlapping content is inlined, fitting the 'references present but not clearly signaled; content that should be separate is inline' anchor.

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.

A well-formed description with explicit trigger guidance and a clear Cursor-specific niche. Its main weakness is specificity, relying on one abstract verb plus a list of mechanisms rather than multiple concrete actions.

DimensionReasoningScore

Specificity

The description names the domain and three mechanisms ("@-mentions, context pills, and conversation strategy") but uses a single abstract verb ("Optimize context window usage") rather than listing multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It states what the skill does ("Optimize context window usage in Cursor...") and provides explicit trigger guidance ("Triggers on..."), answering both what and when rather than only implying when.

3 / 3

Trigger Term Quality

The 'Triggers on' list covers natural terms a user would say ("cursor context", "context window", "context limit", "context management", "@-mentions", "context pills"), giving good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

The Cursor-specific niche and distinct triggers ("cursor context", "context pills", "@-mentions") make it 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.