CtrlK
BlogDocsLog inGet started
Tessl Logo

ctx-stats

Show how much context window context-mode saved this session. Displays token consumption, context savings ratio, and per-tool breakdown. Read-only — shows stats only, no reset capability. To wipe the knowledge base entirely, use ctx_purge instead. Trigger: /context-mode:ctx-stats

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/ctx-stats/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

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

The body is a tight, fully executable single-purpose skill with a clear workflow and clean section structure; the only weakness is minor scope-bleed where the Purge section repeats cross-skill guidance already in the description.

DimensionReasoningScore

Conciseness

Lean numbered list and bullet section with no concept over-explanation, but the '## Purge' section duplicates the description's ctx_purge pointer and bleeds slightly into another skill's scope.

4 / 5

Actionability

Fully executable: names the exact MCP tool mcp__context-mode__ctx_stats with no parameters, mandates verbatim copy-paste of output, and gives concrete example summary sentences with real numbers.

5 / 5

Workflow Clarity

A clear, unambiguous 3-step sequence for a simple read-only single task; the primary workflow is non-destructive so no validation checkpoint is required, satisfying the simple-skill exception.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references, organized into well-signaled '## Instructions' and '## Purge' sections, meeting the rubric's simple-skill threshold for full marks.

5 / 5

Total

19

/

20

Passed

Description

58%Weight 40%Scale 1-5

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 distinguishes itself from the destructive ctx_purge sibling, but it relies on a literal trigger command rather than natural-language 'Use when...' guidance, capping completeness at 3.

Suggestions

Add a natural-language trigger clause, e.g. 'Use when the user wants to see context savings, token usage, or context-mode stats for the current session.'

Include synonyms users might say, such as 'context window usage', 'how much context did I save', or 'token usage breakdown', to improve trigger-term coverage.

Consider whether the cross-skill ctx_purge guidance belongs only in the body to keep the description focused on this skill's own capabilities.

DimensionReasoningScore

Specificity

Names the domain (context window savings) and lists several concrete outputs — 'token consumption, context savings ratio, and per-tool breakdown' — with only minor gaps in coverage.

4 / 5

Completeness

The 'what' is clear, and a 'Trigger:' command gives invocation guidance, but there is no natural-language 'Use when...' clause; per the rubric this caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords like 'context window', 'token consumption', and 'context savings' appear plus a literal trigger command, but common natural-language variations or synonyms a user would say are missing.

3 / 5

Distinctiveness Conflict Risk

Distinct single-session stats niche with an explicit boundary ('use ctx_purge instead') that disambiguates from the destructive sibling skill; minor overlap risk with the related purge skill.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mksglu/context-mode
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.