ctx-index

Index a local file or directory into context-mode's persistent FTS5 knowledge base so future ctx_search calls can retrieve focused snippets without rereading raw files. Trigger: /context-mode:ctx-index

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

87%

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 lean, actionable, well-structured overview with concrete MCP and CLI examples and a clear numbered workflow. Its only gap is the absence of an explicit validation/retry feedback loop for what is a batch indexing operation.

Dimension	Reasoning	Score
Conciseness	The ~37-line body is lean and well-organized with no padding or explanation of concepts Claude already knows; every section (Instructions, Safety) earns its place and assumes competence.	3 / 3
Actionability	It provides executable, copy-paste-ready guidance: a concrete ctx_index MCP call with specific parameters (maxDepth: 5, maxFiles: 200), a CLI fallback command, and a ctx_search example.	3 / 3
Workflow Clarity	Steps are clearly numbered 1–6 with a reporting step (step 6), but indexing a repository is a batch operation and the workflow lacks an explicit validate→fix→retry feedback loop, which caps batch-operation workflows at 2.	2 / 3
Progressive Disclosure	At under 50 lines with no bundle files and no need for external references, the well-organized Instructions/Safety sections meet the simple-skill bar for progressive disclosure.	3 / 3
	Total	11 / 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 is specific and well-scoped to a distinct niche, but it leans on technical jargon and a slash-command trigger rather than natural user phrasing and an explicit 'Use when…' clause. It answers 'what' clearly but leaves 'when' only implied.

Suggestions

Add an explicit 'Use when…' clause naming the natural situations that call for indexing (e.g., 'Use when the user wants to make project files searchable for later focused retrieval without rereading raw files').

Broaden trigger-term coverage with natural phrases users would actually say (e.g., 'index my project', 'make files searchable', 'search codebase later') alongside the technical terms.

Consider listing the concrete outcome actions more explicitly (e.g., 'Index files or directories, then retrieve focused snippets via ctx_search') to reach the multi-action specificity anchor.

Dimension	Reasoning	Score
Specificity	It names the domain ('context-mode's persistent FTS5 knowledge base') and a concrete action ('Index a local file or directory'), but presents essentially one action with a purpose clause rather than a list of multiple distinct actions, so it stops short of the top anchor.	2 / 3
Completeness	It clearly answers 'what' (index files into the FTS5 KB for later retrieval) but 'when' is only implied via the slash-command trigger line; there is no explicit 'Use when…' clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	'index a local file or directory' is a natural phrase, but the description is dominated by technical jargon ('FTS5 knowledge base', 'ctx_search calls') and the only trigger guidance is a slash command ('Trigger: /context-mode:ctx-index'), missing common natural variations.	2 / 3
Distinctiveness Conflict Risk	The scoped terms ('context-mode's persistent FTS5 knowledge base', 'ctx_search') carve out a clear, distinct niche that is unlikely to trigger for unrelated skills.	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.