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

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/ctx-purge/SKILL.md

Quality

Content

86%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, highly actionable runbook: exact tool calls, a clear destructive-operation workflow with a user-confirmation checkpoint, and well-organized sections. The only soft spot is minor redundancy and the absence of an error-recovery loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no padding about what FTS5 or a knowledge base is), with only minor redundancy such as 'There is no undo' restating 'destructive and cannot be undone'.	4 / 5
Actionability	It gives the exact MCP tool name and copy-paste-ready parameter objects for both scopes plus the deprecated bare form, covering the common cases fully.	5 / 5
Workflow Clarity	A clear decide-scope → warn-user → call-tool → report sequence includes an explicit user-warning checkpoint and the required confirm:true gate, but there is no error-recovery feedback loop if the call fails.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed, the body is cleanly organized into Instructions, Schema rules, When to Use, and Important sections, satisfying the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

57%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 clearly states a destructive, irreversible purge action with a distinct slash-command trigger, but it lacks a use-case 'when to use it' clause and only lightly covers the project/session scope distinction. It is clear and distinct but not comprehensive on triggers or use cases.

Suggestions

Add a 'Use when...' clause naming concrete scenarios (e.g. stale knowledge base, switching projects, isolating a polluted session) to lift completeness above 3.

Expand the action list to mention the two scopes (project wipe vs. single-session wipe) so specificity reflects the skill's main capability.

Include natural-language trigger synonyms like 'clear', 'wipe', or 'reset the knowledge base' alongside the slash command.

Dimension	Reasoning	Score
Specificity	Names the domain ('context-mode knowledge base') and two concrete actions ('Permanently deletes all indexed content', 'resets session stats'), but does not enumerate the project-vs-session scopes that are the skill's core feature, so it is not comprehensive.	3 / 5
Completeness	The 'what' is clear, but there is no 'Use when...' use-case clause; the only trigger guidance is the invocation slash command, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords ('purge', 'context-mode knowledge base') plus an explicit slash-command trigger are present, but natural-language synonyms a user might say (e.g. 'clear', 'wipe', 'reset') are missing.	3 / 5
Distinctiveness Conflict Risk	'Purge the context-mode knowledge base' names a tightly scoped niche with a dedicated slash-command trigger, giving it minimal overlap with other skills.	5 / 5
	Total	14 / 20 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
Path: skills/ctx-purge/SKILL.md
Commit: 3bad0f4

Reviewed: 4 days 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.