CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

db-router

Route database files to appropriate extraction method based on identification from db-identify. Decides between DBeaver CLI (for supported formats) or db-extractor-* skills (for unsupported formats). Use AFTER db-identify to determine extraction workflow.

Quality

79%

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/db-router/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 body is a lean, well-structured router reference: executable verified commands, complete routing and decision tables, and a clear agent workflow with error paths mapped. Remaining gaps are small — trimmable diagram/output redundancy, an undocumented --confidence flag, and inconsistent script path conventions.

DimensionReasoningScore

Conciseness

The body is efficient with no re-teaching of known concepts — tables, commands, and a tight workflow section. Not 5 because the 16-line ASCII decision diagram restates the binary decision already expressed in the Decision Types table, and the sample Output block partially duplicates the routing table.

4 / 5

Actionability

Quick Start and Agent Workflow commands are copy-paste ready and the documented flags match the actual script's argparse interface. Not 5 because of minor gaps: the script's --confidence flag is undocumented in the CLI Reference, and the same script is referenced with inconsistent paths ('scripts/db_route.py' vs 'db-router/scripts/db_route.py').

4 / 5

Workflow Clarity

This is a single-action router skill and the action is unambiguous: every decision type maps to a concrete next action, including error paths ('unknown_format' → 'Manual investigation', 'skill_needed' → 'Need to build extractor', plus a fallback extractor). Routing is non-destructive, so the missing-validation cap for destructive/batch operations does not apply.

5 / 5

Progressive Disclosure

The bundle (one script, scripts/db_route.py) is referenced with a valid relative path, sections are well organized, and nothing clearly belongs in a separate file. Not 5 because the dual path convention for the same script across Quick Start and Agent Workflow is a minor navigation/organization gap.

4 / 5

Total

17

/

20

Passed

Description

67%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, uses third person, and clearly states both the decision logic (DBeaver CLI vs db-extractor-*) and an explicit ordering trigger tied to db-identify. Its main weakness is trigger-term coverage: it lacks the natural format keywords (sqlite, Access, dbf, .db) users would say when needing this skill, leaving it at 'some relevant keywords' level.

Suggestions

Add natural trigger keywords for the formats handled, e.g. 'Use when a database file (sqlite, Access, dbf, Berkeley DB, Redis RDB) has been identified and needs an extraction method.'

Include concrete user-facing 'when' phrasing alongside the pipeline ordering, e.g. 'Use when the user mentions extracting or exporting an identified database file.'

Name one or two concrete formats in the capability sentence (e.g. 'for formats like sqlite or Access') to sharpen specificity and distinctiveness from the db-extractor-* family.

DimensionReasoningScore

Specificity

"Route database files to appropriate extraction method" and "Decides between DBeaver CLI (for supported formats) or db-extractor-* skills" name several concrete actions with specific tools. Not 5 because coverage is narrow — no specific database formats are named; not 3 because the decision mechanism and both target tools are explicit.

4 / 5

Completeness

The 'what' is clear (routing database files to DBeaver CLI vs db-extractor-* skills) and an explicit trigger clause exists ("Use AFTER db-identify to determine extraction workflow"), so the missing-trigger cap at 3 does not apply. Not 5 because the 'when' is pipeline-ordering guidance rather than concrete user-facing trigger phrases.

4 / 5

Trigger Term Quality

Relevant keywords are present ("database files", "extraction", "DBeaver", "db-identify") but natural terms a user would actually say — format names like sqlite, Access, dbf, or file extensions like .db/.rdb — are missing. Fits the 'some relevant keywords but missing common variations or synonyms' anchor better than the 4 anchor's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"Route database files to appropriate extraction method based on identification from db-identify" carves a clear routing niche, and the "Use AFTER db-identify" ordering reduces wrong-skill triggers. Not 5 because 'database' and 'extraction' overlap heavily with its own sibling skill family (db-identify, db-extractor-*), a minor conflict risk with closely related skills.

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

KennethJefferson/cc_sdk_knowledge_extractor

Path

skills/db-router/SKILL.md

Revision

6d9d92a

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill