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

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ctx-purge/SKILL.md

Quality

Content

85%

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

This is a well-structured skill for a destructive operation. It clearly differentiates between two scopes, provides exact tool call parameters, and includes appropriate safety warnings. Minor verbosity in repeating scope descriptions across sections and explaining things Claude already knows (like what /clear does) prevents a perfect conciseness score.

Suggestions

Consolidate the scope descriptions — the intro, step 2, and schema rules all partially restate the same information about project vs session scope. A single definitive table or list would be more token-efficient.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but has some redundancy — the scope descriptions are repeated across the intro, instructions, and schema rules sections. The 'Important' section restates things Claude would know (e.g., explaining what /clear and /compact don't do). Could be tightened.	2 / 3
Actionability	Provides concrete MCP tool call parameters with exact JSON shapes for each scope variant, clear schema validation rules (what's rejected, what's required), and specific parameter combinations. Copy-paste ready for tool invocation.	3 / 3
Workflow Clarity	Clear 4-step sequence with an explicit confirmation/warning checkpoint before the destructive operation. The workflow includes scope decision, user warning, tool call with exact parameters, and result reporting. The schema rules section acts as a validation checkpoint by specifying rejection conditions for ambiguous inputs.	3 / 3
Progressive Disclosure	For a single-purpose destructive operation skill under 50 lines with no need for external references, the content is well-organized into logical sections (Instructions, Schema rules, When to Use, Important) that are easy to scan and navigate.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 clear and specific about what the skill does, with strong distinctiveness due to the explicit command trigger. Its main weaknesses are the lack of an explicit 'Use when...' clause and limited natural language trigger terms that users might employ outside of the exact command syntax.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user wants to clear, wipe, or reset the context-mode knowledge base, or invokes /context-mode:ctx-purge'.

Include natural language trigger variations such as 'clear knowledge base', 'delete all context', 'reset indexed content', 'wipe context data' to improve matching when users don't use the exact command.

Dimension	Reasoning	Score
Specificity	Lists specific concrete actions: 'purge the context-mode knowledge base', 'permanently deletes all indexed content', 'resets session stats'. Also clearly states the destructive and irreversible nature of the operation.	3 / 3
Completeness	The 'what' is clearly answered (deletes indexed content, resets stats). However, the 'when' is only implied through the trigger command rather than explicitly stated with a 'Use when...' clause. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes the explicit command trigger '/context-mode:ctx-purge' and terms like 'purge', 'knowledge base', 'indexed content', but these are fairly technical. Missing natural language variations a user might say like 'clear knowledge base', 'delete context', 'reset context mode', 'wipe data'.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive with a specific command trigger '/context-mode:ctx-purge' and a very narrow, well-defined action (purging a specific knowledge base). Unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: mksglu/context-mode
Commit: e174272

Reviewed: about 22 hours 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.