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

75

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A tight, well-structured skill body that gives fully executable, copy-paste-ready guidance for a simple read-only task with an unambiguous workflow and clean section organization. No meaningful weaknesses relative to the rubric.

DimensionReasoningScore

Conciseness

A lean ~15-line body that assumes Claude's competence and adds only what isn't known; the emphatic 'do NOT summarize/collapse/paraphrase' lines are justified padding for a paste-verbatim instruction rather than concept explanation.

3 / 3

Actionability

Fully executable guidance — exact tool name 'mcp__context-mode__ctx_stats' with 'no parameters needed', a concrete example output sentence, and 'ctx_purge(confirm: true)' — copy-paste ready.

3 / 3

Workflow Clarity

A simple single-action skill with an unambiguous numbered sequence (call tool, paste full output, add one summary sentence); per the simple-skills note this scores 3 with no destructive operation requiring validation.

3 / 3

Progressive Disclosure

Under 50 lines with no need for external references, organized into clear 'Instructions' and 'Purge' sections; per the under-50-lines guideline this scores 3 on well-organized sections alone.

3 / 3

Total

12

/

12

Passed

Description

85%

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 concise, specific description that clearly states the skill's read-only stats purpose, provides an explicit trigger, and cleanly distinguishes itself from the related purge skill. Its main weakness is trigger-term coverage relying on the formal slash command rather than natural user phrasings.

Suggestions

Add natural-language trigger phrasings users might actually say (e.g. 'Use when the user asks how much context was saved, context stats, or token usage for the session') alongside the formal slash command.

Consider adding a short 'Use when...' clause to make the trigger guidance feel less like a command reference and more like natural invocation conditions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Displays token consumption, context savings ratio, and per-tool breakdown' and 'shows stats only, no reset capability' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Answers both what ('Show how much context window context-mode saved this session') and when via the explicit 'Trigger: /context-mode:ctx-stats' clause.

3 / 3

Trigger Term Quality

Has relevant keywords ('context-mode saved this session', 'Trigger: /context-mode:ctx-stats') but leans on the formal command path rather than natural phrasings a user would say, missing common variations.

2 / 3

Distinctiveness Conflict Risk

Explicitly scopes to read-only stats and distinguishes from ctx_purge ('To wipe the knowledge base entirely, use ctx_purge instead'), giving it a clear niche unlikely to conflict.

3 / 3

Total

11

/

12

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.