CtrlK
BlogDocsLog inGet started
Tessl Logo

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

61

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ctx-index/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 content is concise, well-structured, and gives concrete executable examples, but its workflow for a batch indexing operation lacks an explicit validation/verification feedback loop, capping workflow clarity. Adding a verify-and-retry step would raise the workflow score.

Suggestions

Add an explicit verification step after indexing, e.g., confirm the source label registered and run a sample ctx_search to validate retrievability before reporting done.

Include error-recovery guidance for the batch case (what to do if ctx_index fails, indexes zero files, or hits the maxFiles cap), forming a validate->fix->retry loop.

Replace generic placeholders with a brief note on how to choose the source label value so the code examples are closer to copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean (~35 lines), assumes Claude's competence (no explanation of what FTS5 or indexing is), and every line earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

It provides concrete, mostly executable guidance — a real ctx_index call with bounds, a CLI fallback, and a ctx_search example — but uses placeholders like <name> and ['...'], leaving it just short of fully copy-paste-ready.

4 / 5

Workflow Clarity

Steps 1-6 are clearly sequenced with a reporting checkpoint, but directory/repo indexing is a batch operation and the workflow lacks an explicit validate->fix->retry feedback loop, so the batch-operation cap of 3 applies.

3 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and well-organized into Instructions and Safety sections with no need for external bundle files (none are present), meeting the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

62%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 is specific and appropriately scoped to a distinct niche with explicit trigger guidance, but it relies on technical jargon and a slash command rather than natural user-language trigger phrases. Adding a 'Use when...' clause with everyday terms would lift completeness and trigger quality.

Suggestions

Add a 'Use when...' clause with natural-language triggers users would actually say (e.g., 'Use when the user wants to make a folder or project searchable for later retrieval, or mentions indexing a codebase for search').

Include everyday synonyms alongside the technical terms (e.g., 'index my project', 'make this directory searchable') so the description matches natural user phrasing, not only 'FTS5 knowledge base' and 'ctx_search'.

Optionally name one more concrete action (e.g., 're-index' or 'update an existing source') to broaden specificity beyond the single index action.

DimensionReasoningScore

Specificity

Names the domain ('context-mode's persistent FTS5 knowledge base') and one to two concrete actions ('Index a local file or directory', 'retrieve focused snippets'), but does not enumerate several distinct actions, so it sits at the domain-plus-1-2-actions anchor rather than 4.

3 / 5

Completeness

It has a clear 'what' ('Index a local file or directory...') and explicit 'when' guidance via 'Trigger: /context-mode:ctx-index', but the when is a slash command rather than concrete natural-language trigger phrases, so it is above the missing-when anchor but below the explicit-trigger-phrases anchor.

4 / 5

Trigger Term Quality

Relevant keywords ('index', 'search', 'file or directory', 'snippets') appear, but the language leans technical ('FTS5 knowledge base', 'ctx_search calls', a slash-command trigger) and omits the natural phrases a user would actually say, matching the some-keywords-but-missing-variations anchor.

3 / 5

Distinctiveness Conflict Risk

The FTS5-indexing niche tied to a specific slash command is mostly distinct with minimal conflict risk, though there is minor overlap potential with the sibling context-mode search skill, placing it just below the clear-niche-minimal-conflict anchor.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mksglu/context-mode
Reviewed

Table of Contents

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.