ctx-search

Search context-mode's persistent FTS5 knowledge base for previously indexed local project content, documentation, or session memory. Trigger: /context-mode:ctx-search

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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 compact, highly actionable set of instructions with executable MCP and CLI examples and clear conditional handling. It is well-organized for a simple single-purpose skill with no wasted context.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a one-line purpose statement plus tightly scoped numbered guidance with no padded explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	It provides fully executable, copy-paste-ready examples for both the MCP tool (ctx_search call with concrete arguments) and the CLI fallback (context-mode search with flags), meeting the level-3 anchor.	3 / 3
Workflow Clarity	The numbered sequence is clear with explicit conditional branches (MCP unavailable -> CLI fallback; empty index -> direct user to index first); as a simple, non-destructive search skill it is unambiguous and well-sequenced.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed, the content is organized into a clear purpose line and a single well-structured Instructions section, satisfying the simple-skill anchor for level 3.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 identifies a distinct niche and a concrete action, but relies on a slash-command trigger instead of natural 'Use when...' guidance and does not enumerate multiple specific actions. It is solid but leaves the situational trigger and capability breadth underspecified.

Suggestions

Add an explicit 'Use when ...' clause naming natural situations (e.g. when the user wants to recall previously indexed project content, docs, or session memory without rereading source files).

Broaden the action list beyond a single 'Search' verb to concrete capabilities (e.g. retrieve, scope, batch-query indexed content).

Expand trigger terms with common user phrasings like 'search indexed docs', 'find session memory', or 'look up indexed project content'.

Dimension	Reasoning	Score
Specificity	Names the domain ('context-mode's persistent FTS5 knowledge base') and a concrete action ('Search ... for previously indexed local project content, documentation, or session memory'), but lists only a single action rather than multiple specific concrete actions, so it does not reach level 3.	2 / 3
Completeness	The 'what' is clearly stated, but the 'when' is conveyed only via a slash-command trigger ('Trigger: /context-mode:ctx-search') rather than a 'Use when...' situational clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant keywords appear ('search', 'documentation', 'session memory', 'indexed ... content') and an explicit slash trigger is given, but coverage of natural terms a user would say is limited and missing common variations, so it sits at level 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	The narrow niche of context-mode's persistent FTS5 knowledge base plus a namespaced slash trigger makes it clearly distinguishable and unlikely to fire for the wrong skill.	3 / 3
	Total	9 / 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.