CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Quality

63%

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/similarity-search-patterns/SKILL.md

The canonical home for this skill is similarity-search-patterns in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

32%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 lean and well-sectioned but hollow: it defers all real content to 'resources/implementation-playbook.md', a file that is missing from the bundle, leaving only generic boilerplate instructions. As written, the skill provides no actionable similarity-search guidance at all.

Suggestions

Add concrete, executable content to the Instructions section — e.g., specific indexing patterns (HNSW/IVF parameter trade-offs), query examples with a named vector library, and hybrid semantic+keyword search code — instead of abstract bullets like 'Apply relevant best practices and validate outcomes'.

Fix the broken progressive disclosure: either include the referenced 'resources/implementation-playbook.md' file in the bundle, or remove the dangling references in both the Instructions and Resources sections.

Give the workflow a real sequence with validation checkpoints (e.g., verify recall@k against a ground-truth set before tuning index parameters) and replace the vacuous 'Do not use this skill when' bullets with meaningful boundary conditions.

DimensionReasoningScore

Conciseness

The body is short and free of concept over-explanation, assuming Claude's competence. Not 5 because some tokens do not earn their place: the vacuous 'Do not use this skill when' bullets ('The task is unrelated to similarity search patterns') and boilerplate instruction bullets ('Apply relevant best practices and validate outcomes') could be trimmed or replaced with substance. Not 3 because there is no noticeable padding or unnecessary explanation of known concepts.

4 / 5

Actionability

The Instructions section is entirely abstract: 'Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes' — no concrete code, commands, patterns, or specific steps, despite the skill claiming to provide 'Patterns for implementing efficient similarity search'. This matches the anchor-1 example style ('only describes rather than instructs'). Not 2 because even high-level hints toward specific steps are absent, and the sole concrete pointer ('open resources/implementation-playbook.md') targets a file that does not exist in the bundle.

1 / 5

Workflow Clarity

The instruction bullets imply a rough sequence (clarify goals, apply practices, validate outcomes) but steps are poorly defined and validation is only mentioned generically with no checkpoint or method. Fits 'Rough sequence present but many gaps; steps poorly defined; validation absent'; not 1 because a rough sequence does exist, and not 3 because there is no real checklisting or explicit validation of outcomes.

2 / 5

Progressive Disclosure

Sections are well organized and the reference to 'resources/implementation-playbook.md' is clearly signaled in both Instructions and Resources, but the referenced file does not exist — no resources/ directory or any bundle files are present. The only path to the skill's actual substance is a dead end, defeating navigation entirely. Not 3 because a broken primary reference delivers less usable structure than merely imperfect organization; not 1 because the SKILL.md itself is not a monolithic wall of text and the reference is one level deep and clearly labeled.

2 / 5

Total

9

/

20

Passed

Description

78%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 clearly states what the skill does and when to use it, with natural trigger phrases. Slightly limited capability coverage and minor overlap risk from the broad 'optimizing retrieval performance' trigger.

DimensionReasoningScore

Specificity

Names the domain ('similarity search', 'vector databases') with 1-2 concrete actions ('Implement efficient similarity search', 'implementing nearest neighbor queries'), but lists no further capabilities such as indexing, hybrid search, or tuning. Matches 'Names domain and 1-2 concrete actions, but not comprehensive'; not 4 because it does not list several specific actions, and not 2 because it goes beyond naming the domain alone.

3 / 5

Completeness

Explicitly answers both: what it does ('Implement efficient similarity search with vector databases') and when to use it via a concrete 'Use when' clause with three trigger scenarios. Matches the anchor-5 good example structure; not 4 because the 'when' is already explicit and specific, not merely present.

5 / 5

Trigger Term Quality

Contains several natural trigger phrases users would actually say: 'building semantic search', 'implementing nearest neighbor queries', 'optimizing retrieval performance', 'vector databases'. Not 5 because common synonyms and variations are missing (e.g., 'RAG', 'embeddings', 'vector search', 'ANN search'); not 3 because keyword coverage is genuinely good, not merely 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The niche (vector similarity search, nearest neighbor, semantic search) is mostly distinct with clear triggers, but 'optimizing retrieval performance' is broad and could overlap with general RAG/database-optimization skills. Not 5 due to that overlap risk; not 3 because the core triggers are specific to similarity search rather than broadly generic.

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/similarity-search-patterns/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.