CtrlK
BlogDocsLog inGet started
Tessl Logo

route-by-query-shape

When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.

57

Quality

66%

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/route-by-query-shape/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-organized, concise, and clearly conveys an unambiguous automated mechanism. Its main weakness is actionability: it describes behavior and a source path but offers no concrete, executable steps or examples for Claude to apply.

Suggestions

Add a concrete example showing a sample relationship query and the resulting rerouted graph-backend call, so the behavior is observable rather than only described.

If any manual invocation or configuration is possible, include an explicit command or snippet; otherwise clarify that the interceptor is fully automatic and Claude need take no action.

Tighten the slight redundancy between the opening paragraph and the 'What you'll see' section to reach a fully lean token budget.

DimensionReasoningScore

Conciseness

The body is lean and mostly assumes competence, explaining only the non-obvious why (vector search misses relationship answers); minor redundancy between the intro and 'What you'll see' keeps it just below the fully lean 5 anchor.

4 / 5

Actionability

Provides concrete details about the mechanism (file path, fire limit, reroute behavior) but no executable code or commands Claude can run, fitting 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The single automated action is described as an unambiguous sequence (watch -> detect -> extract -> re-route) before execution; no validation is needed since it is non-destructive, though it reads as a passive mechanism description rather than an explicit workflow, so not a 5.

4 / 5

Progressive Disclosure

A short (<50 line) skill with no need for external reference docs, organized into clear sections (title, 'What you'll see', 'Implementation'), which the simple-skill exception rates at 5 for well-organized structure.

5 / 5

Total

16

/

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 clearly states a specific routing behavior and includes an explicit when-trigger with a natural example phrase, but it covers only a single action and a narrow trigger set. It is solid and distinct but not comprehensive.

Suggestions

Broaden the trigger-term coverage with additional natural phrasings users would say (e.g., 'who worked with me on', 'connections between', 'relationships involving').

State the 'Use when...' trigger as an explicit user-facing clause in addition to the agent-internal memory_search condition.

Mention the complementary actions the skill performs (e.g., entity extraction and pre-execution rerouting) to raise specificity beyond a single routing action.

DimensionReasoningScore

Specificity

Names a concrete domain and a single concrete action ("redirect to the knowledge_graph backend") triggered by "calls memory_search with a relationship-shaped query", but lists only one routing action rather than several, matching the anchor for 1-2 concrete actions.

3 / 5

Completeness

Explicitly answers what ("redirect to the knowledge_graph backend") and when ("When the agent calls memory_search with a relationship-shaped query") with a concrete trigger phrase, but the trigger set is singular and slightly abstract, so it is not the fully comprehensive 5 anchor.

4 / 5

Trigger Term Quality

Includes one natural user phrase ("who did I talk to about X") alongside technical terms (memory_search, knowledge_graph), but coverage is narrow with no synonyms or variations, fitting 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

Targets a narrow, specific niche (relationship-shaped memory_search routing to the graph backend) with distinct triggers, though the slightly fuzzy 'relationship-shaped query' detection leaves minor overlap risk with other memory skills rather than minimal conflict.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
Bitterbot-AI/bitterbot-desktop
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.