CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

biblaigo

Knowledge organizer for the Biodoia ecosystem. Indexes Markdown/text documents into a FTS5 Knowledge Base, runs sub-millisecond semantic/keyword search, exposes stats/TUI/web, and serves gRPC+REST+MCP+A2A. Use for knowledge organization, KB indexing, retrieval, research memory. (Not a database: store is FTS5; PostgreSQL+pgvector lives in memogo.)

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skill/biblaigo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 short and cleanly sectioned with a concrete command table, but it under-delivers operationally: commands are duplicated instead of elaborated, no example invocations or expected outputs are given, integration and rules sections are non-executable name-dropping, and the batch indexing operation has no verification step. Mixed Italian/English ('Scopo', 'Server completo', 'creato 2026-11-20') further hurts consistency.

Suggestions

Replace the duplicated command listing with one canonical table plus a worked example, e.g. `biblaigo index ~/notes/` followed by `biblaigo search "vector db"` with expected output.

Add a verification step after batch indexing — e.g. 'After indexing, run `biblaigo stats` and confirm document count matches the source directory' — to satisfy the batch-operation validation requirement.

Make 'Integration with FGT-SDK' and 'Rules' actionable: give the actual command or endpoint for each integration (gofainder, memogo, aigoproxy) and unify the language (Italian/English mix) to one.

DimensionReasoningScore

Conciseness

The command set is duplicated — a 4-line code block in 'What' and again as the 7-row 'Commands' table — and the footer '*Skill Biblaigo — creato 2026-11-20*' is time-sensitive padding, so the body could clearly be tightened despite being short, matching anchor 3.

3 / 5

Actionability

The command table gives concrete, real syntax (`biblaigo index <path>`, `biblaigo search <query>`, `biblaigo serve`), but there are no example invocations with actual arguments or expected output, and 'Integration with FGT-SDK' and 'Rules' name-drop tools (gofainder, goleciave, gogatewai, aigoproxy) without any commands or usage details, fitting anchor 3's 'concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The 'What' code block only implies an order (index → search → stats → serve); no explicit sequencing is stated and validation checkpoints are entirely absent — notable because `index` is a batch operation, which the rubric caps at 3 without verification steps. Matches anchor 3: sequence present but implicit, checkpoints missing.

3 / 5

Progressive Disclosure

There are no bundle files and the body is under 50 lines with well-organized sections (What / Commands / Integration / Rules) and no need for external references, which the rubric's simple-skill guideline states qualifies for full credit.

5 / 5

Total

14

/

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 about capabilities and includes an explicit use-for clause with a clear disambiguation against memogo. Its main weaknesses are trigger-term coverage — heavy on protocol jargon, light on natural user phrasing and synonyms — and a when-clause that is generic rather than trigger-anchored.

Suggestions

Expand the 'Use for' clause with natural trigger phrases and synonyms users would actually say, e.g. 'Use when the user asks to find, search, or organize notes, documents, Markdown (.md) files, or research material'.

Anchor the when-clause to concrete mentions: 'when the user mentions a knowledge base, KB, or asks to index or retrieve documents'.

Trim protocol laundry lists (gRPC+REST+MCP+A2A) in favor of one or two capability-oriented terms that double as natural keywords.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Indexes Markdown/text documents into a FTS5 Knowledge Base", "runs sub-millisecond semantic/keyword search", "exposes stats/TUI/web", "serves gRPC+REST+MCP+A2A" — but coverage has minor gaps (e.g., trust scores and pending-item staging appear only in the body), matching anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

Both a clear "what" (indexing, search, stats, serving) and an explicit "Use for..." when-clause are present, but the when-clause is generic and lacks concrete trigger phrasing (e.g., "when the user mentions..."), matching anchor 4 rather than 5.

4 / 5

Trigger Term Quality

The trigger clause "Use for knowledge organization, KB indexing, retrieval, research memory" includes some relevant keywords, but the description is dominated by technical jargon (FTS5, gRPC, MCP, A2A) and misses natural phrases users would actually say, such as "find my notes", "search documents", or ".md files", fitting anchor 3.

3 / 5

Distinctiveness Conflict Risk

The explicit boundary "(Not a database: store is FTS5; PostgreSQL+pgvector lives in memogo)" carves a distinct niche, but broad trigger terms like "knowledge organization", "retrieval", and "research memory" carry minor overlap risk with other memory/search skills, matching anchor 4.

4 / 5

Total

15

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository

biodoia/readmago

Path

skill/biblaigo/SKILL.md

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.