CtrlK
BlogDocsLog inGet started
Tessl Logo

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

61

Quality

72%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ctx-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

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-crafted, concise skill that efficiently teaches Claude how to search an FTS5 knowledge base. It provides concrete, executable examples for both MCP and CLI paths, handles the empty-index edge case, and respects token budget. The only minor gap is the lack of guidance on interpreting or handling search results (e.g., no results, low relevance).

Suggestions

Add brief guidance on what to do when search returns no results or low-relevance results (e.g., broaden query terms, try alternative scopes).

DimensionReasoningScore

Conciseness

Every line serves a purpose. No unnecessary explanations of what FTS5 is, what searching means, or how MCP tools work. The skill assumes Claude's competence and delivers only the delta knowledge needed.

3 / 3

Actionability

Provides executable code for both the MCP tool call and the CLI fallback, with concrete parameter examples (source, queries, limit). The fallback path and empty-index guidance are specific and actionable.

3 / 3

Workflow Clarity

The steps are clearly sequenced (prefer MCP → batch queries → scope → use short queries → fallback → handle empty index), but there's no validation or feedback loop for handling cases like no results returned or partial matches, which would improve robustness.

2 / 3

Progressive Disclosure

For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections and appropriate brevity. No bundle files are needed for this scope.

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 identifies a clear niche (searching a specific FTS5 knowledge base within context-mode) and is unlikely to conflict with other skills. However, it lacks an explicit 'Use when...' clause, relies on technical jargon rather than natural user language, and describes only a single action rather than enumerating specific capabilities.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to search, find, or recall previously indexed project content, documentation, or session notes.'

Include natural language trigger terms users would actually say, such as 'find', 'look up', 'recall', 'search my notes', 'what was indexed', alongside the slash command trigger.

DimensionReasoningScore

Specificity

Names the domain (FTS5 knowledge base search) and a general action (search previously indexed content), but doesn't list multiple concrete actions—it's essentially one action (search) with some context about what's being searched.

2 / 3

Completeness

The 'what' is addressed (search a persistent FTS5 knowledge base for indexed content), but the 'when' is only implied through the trigger command rather than explicitly stated with a 'Use when...' clause. Per the rubric, a missing explicit trigger guidance caps completeness at 2.

2 / 3

Trigger Term Quality

Includes some relevant terms like 'knowledge base', 'documentation', 'session memory', 'project content', but these are somewhat technical. Missing natural user phrases like 'find', 'look up', 'recall', 'what did I index', or 'search notes'. The slash command trigger '/context-mode:ctx-search' is useful but not a natural language term.

2 / 3

Distinctiveness Conflict Risk

The description is quite specific to a particular system ('context-mode's persistent FTS5 knowledge base') and includes a unique slash command trigger, making it clearly distinguishable from other search or documentation skills.

3 / 3

Total

9

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

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.