Tessl • The management layer for AI agent skills

SkillPublic

db-extractor-sqlite

Extract SQLite database content to text-readable formats (CSV, JSON, Markdown) for LLM processing and content synthesis. Use when working with SQLite databases (.db, .sqlite, .sqlite3) from course materials, datasets, or applications that need to be converted to text formats for analysis, synthesis, or inclusion in LLM context windows. Routed from db-router skill.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A concise, highly actionable body whose commands are accurate against the bundled script, with clean section organization. Its weaknesses are the absence of any output-validation step for a batch extraction operation (capping workflow clarity) and an unreferenced references/format_guide.md that duplicates inline content instead of being linked.

Suggestions

Add a verification step after extraction (e.g., "Check the output directory lists one file per expected table" or "Review _schema.md to confirm all tables were captured") so the batch workflow includes a validation checkpoint.

Link references/format_guide.md from the Output Formats section (e.g., "See [format_guide.md](references/format_guide.md) for token-cost tradeoffs") instead of duplicating its content inline, making the existing bundle file discoverable.

Consider trimming the overlap between Common Workflows and the CLI Reference by letting the CLI Reference carry the full flag detail and keeping workflows to task-oriented recipes.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven: no explanation of what SQLite is, no library background, and compact sections (Quick Start, a 3-row format table, CLI reference). Every section and token earns its place; the slight repetition of flags between workflows and the CLI reference serves lookup purposes rather than padding.	5 / 5
Actionability	All commands are fully executable copy-paste invocations, and the CLI Reference flags (-o, -f, --tables, --exclude, --schema, --max-rows, -q) were verified to match the actual argparse definitions in scripts/db_extract.py. The Quick Start and Common Workflows cover the common cases (format choice, table filtering, large-DB limits).	5 / 5
Workflow Clarity	The single-command usage is unambiguous, but this is a batch operation (extracting all tables of a database) and the body includes no validation or verification step (e.g., checking that expected output files were produced or reviewing _schema.md to confirm tables). The rubric explicitly caps batch skills without validation at 3, taking precedence over the simple-skill exception.	3 / 5
Progressive Disclosure	The bundle contains references/format_guide.md, but the body never links to it; the "Output Formats" table inlines a condensed duplicate of that guide instead of pointing to it. The scripts/db_extract.py path is used consistently and correctly, but the orphaned, unsignaled reference file matches the anchor of references present but not clearly signaled.	3 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong description that clearly states concrete capabilities and provides an explicit, trigger-rich "Use when" clause with file extensions and usage contexts. It is highly specific to the SQLite-to-text niche with negligible conflict risk; the only improvement space is slightly broader action and synonym coverage.

Dimension	Reasoning	Score
Specificity	"Extract SQLite database content to text-readable formats (CSV, JSON, Markdown) for LLM processing and content synthesis" lists several concrete actions with named formats. Minor gaps remain (schema documentation, selective table extraction from the body are never mentioned), keeping it below the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both: what ("Extract SQLite database content to text-readable formats (CSV, JSON, Markdown)") and when ("Use when working with SQLite databases (.db, .sqlite, .sqlite3) from course materials, datasets, or applications"), with concrete trigger phrases matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	"SQLite databases (.db, .sqlite, .sqlite3)", "datasets", and "converted to text formats" give good natural keyword coverage including file extensions. A few natural phrasings users might say (e.g., "export database", "dump database") are missing, so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clear niche (SQLite extraction to text formats) with distinct extension-based triggers (.db, .sqlite, .sqlite3) and explicit routing context ("Routed from db-router skill"), giving minimal overlap risk with other data skills.	5 / 5
	Total	18 / 20 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: KennethJefferson/cc_sdk_knowledge_extractor
Path: skills/db-extractor-sqlite/SKILL.md
Revision: 6d9d92a

Reviewed: 5 days ago

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.

db-extractor-sqlite

Table of Contents

Is this your skill?