ctx-purge

Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 well-structured, actionable, and concise skill body for an irreversible destructive operation, with explicit confirmation checkpoints and exact tool-call guidance. The only minor blemish is an internal issue reference that adds no user-facing value.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence — no basic-concept explanations, every section earns its place, with only minor internal noise like 'issue #520'.	3 / 3
Actionability	Gives the exact MCP tool name and copy-paste-ready parameter objects ('{ confirm: true, sessionId: "<id>" }', '{ confirm: true, scope: "project" }').	3 / 3
Workflow Clarity	Clear sequence (decide scope → warn → call tool → report) with an explicit pre-destruction checkpoint (warn user + confirm:true required) and documented rejections in Schema rules.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed; well-organized sections (Instructions, Schema rules, When to Use, Important) suffice for a single-purpose skill.	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 with explicit trigger guidance and a clear niche. Its main weakness is relying on a slash-command trigger rather than enumerating natural-language terms users would say.

Suggestions

Add natural-language trigger phrasings (e.g. 'Use when the user wants to wipe the context-mode knowledge base, reset session stats, or start fresh') alongside the slash command.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Permanently deletes all indexed content and resets session stats' — rather than vague language.	3 / 3
Completeness	Answers both what it does (deletes indexed content, resets stats, destructive) and when via explicit trigger guidance ('Trigger: /context-mode:ctx-purge').	3 / 3
Trigger Term Quality	Provides a slash-command trigger ('Trigger: /context-mode:ctx-purge') and terms like 'purge' and 'knowledge base', but lacks a spread of natural phrasings a user would say.	2 / 3
Distinctiveness Conflict Risk	Tied to a specific context-mode purge command and knowledge base, giving it a clear niche unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mksglu/context-mode
Commit: f267bda

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.