CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentdb-advanced

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/agentdb-advanced/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.

A well-organized, mostly executable reference for AgentDB's advanced features with strong code and CLI coverage, weakened by re-explaining standard distance-metric math and QUIC basics, lacking validation steps for batch database operations, and shipping dead 'docs/' references in a single monolithic file. The strongest dimension is actionability; conciseness and workflow structure are the clear improvement areas.

Suggestions

Cut the distance-metric formulas, ranges, and Use Cases lists plus the 'What is QUIC Sync?' explainer — Claude already knows cosine/Euclidean/dot math — and de-duplicate the QUIC configuration and env-var blocks (conciseness).

Add verification steps around batch/destructive CLI operations, e.g., compare pattern counts or run a smoke query after merge/import/reindex before declaring success (workflow_clarity).

Remove or fix the dead 'docs/quic-synchronization.pdf' and 'docs/hybrid-search-guide.md' references, and move bulk reference material (env vars, CLI operations) into a real references/ file to slim the monolithic body (progressive_disclosure).

DimensionReasoningScore

Conciseness

Re-teaches concepts Claude already knows — 'cos(θ) = (A · B) / (||A|| × ||B||)', 'Range: [-1, 1] (1 = identical, -1 = opposite)', per-metric Use Cases lists, and the 'What is QUIC Sync?' explainer — and duplicates content (QUIC config in both 'Enable QUIC Sync' and 'QUIC Configuration', env vars repeated across three node blocks and the Environment Variables section). The dense code blocks keep it above the 'noticeably verbose' 2 anchor, but the padding is more than minor.

3 / 5

Actionability

Most guidance is concrete and executable — 'npx agentdb@latest query ./vectors.db "[0.1,0.2,...]" -m cosine', complete multi-node env-var blocks, filter syntax like 'year: { $gte: 2023 }'. Gaps keep it below 5: the first insertPattern uses '// ... pattern data' placeholders, and the custom distance metric ends with '// Use in search (requires custom implementation)' offering no actual integration path for a headline feature.

4 / 5

Workflow Clarity

The body is a feature reference rather than a sequenced workflow, and batch/destructive database operations — 'npx agentdb@latest merge ./db1.sqlite ./db2.sqlite ./merged.sqlite', VACUUM, reindex, import/export — include no validation or verification steps, capping this dimension at 3. The Troubleshooting section is reactive (fix-after-failure) rather than providing explicit checkpoints.

3 / 5

Progressive Disclosure

Section headers and horizontal rules make the ~550-line body navigable, but all detail is inlined in SKILL.md with no bundle files, and the only outward references — 'docs/quic-synchronization.pdf' and 'docs/hybrid-search-guide.md' — point to files that do not exist in any references/ directory. This matches 'some structure, content that should be separate is inline, references not clearly backed'.

3 / 5

Total

13

/

20

Passed

Description

75%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 solid description that names the specific tool and five concrete feature areas, and pairs a clear what with an explicit 'Use when' clause containing natural trigger phrases. It sits comfortably at the 'mostly specific, both what and when present' level across all dimensions, falling just short of the top anchors on trigger synonym coverage and action phrasing.

DimensionReasoningScore

Specificity

Enumerates 'QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration' — several concrete feature areas with only minor gaps, though these are topic nouns under the vague verb 'Master' rather than the concrete executable actions of the 5 anchor.

4 / 5

Completeness

Both parts are explicit: the what ('Master advanced AgentDB features including...') and the when ('Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications'). The when-clause is present and concrete but could be more specific with additional trigger phrases, matching anchor 4 rather than 5.

4 / 5

Trigger Term Quality

'Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications' supplies natural phrases a user would say; a few natural terms (e.g., 'database sync', 'hybrid search' as a trigger) are missing, so below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

'AgentDB' names a specific tool, giving a clear niche with distinct triggers; broad phrases like 'distributed systems integration' and 'advanced vector search applications' leave minor overlap risk with general vector-database skills, so not the minimal-conflict 5.

4 / 5

Total

16

/

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

skill_md_line_count

SKILL.md is long (551 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

ruvnet/ruflo

Path

.claude/skills/agentdb-advanced/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.