hybrid-search-implementation

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hybrid-search-implementation/SKILL.md

The canonical home for this skill is hybrid-search-implementation in rmyndharis/antigravity-skills

Quality

Content

28%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 has a clean, lean section structure and avoids padding, but it provides no executable guidance — only generic platitudes — and its single reference points to a missing file. The skill reads as a stub rather than an actionable playbook.

Suggestions

Replace the generic Instruction bullets with concrete, executable steps — e.g. specific code snippets for combining vector + keyword scores (reciprocal rank fusion, weighted scoring) and example queries — so the skill is actionable without the missing playbook.

Create `resources/implementation-playbook.md` (or correct the path) so the referenced deeper content actually exists, since the only progressive-disclosure pointer is currently a broken link.

Remove the tautological "Do not use this skill when" entries and add a real validation checkpoint (e.g. how to verify recall/precision improved) to give the workflow concrete sequence and error recovery.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining concepts Claude already knows, but it contains generic boilerplate that does not earn its place — e.g. the tautological "Do not use this skill when - The task is unrelated to hybrid search implementation" and abstract instructions — so it is mostly efficient but could be tightened.	3 / 5
Actionability	The Instructions are entirely abstract — "Clarify goals, constraints, and required inputs", "Apply relevant best practices and validate outcomes", "Provide actionable steps and verification" — with no concrete code, commands, or specific guidance, and the one concrete pointer (`resources/implementation-playbook.md`) targets a file that does not exist in the bundle.	1 / 5
Workflow Clarity	The instruction bullets form only a rough, generic sequence (clarify → apply → provide steps → verify) with poorly defined steps and no explicit validation checkpoints or feedback loops, matching the anchor for a rough sequence with many gaps and absent validation.	2 / 5
Progressive Disclosure	Sections are reasonably organized and the detailed material is signaled as one level deep in both Instructions and Resources, but the referenced `resources/implementation-playbook.md` is a broken pointer (no resources/ directory exists), so the structure is present yet does not actually deliver navigation to deeper content.	3 / 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 concise, well-formed description that clearly states both capability and trigger conditions with natural phrasing. Its main limitation is specificity — it describes one combined action rather than enumerating the concrete techniques it covers.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action — "Combine vector and keyword search for improved retrieval" — but stops at a single high-level action rather than listing multiple specific capabilities, matching the anchor that names 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	It explicitly answers both what ("Combine vector and keyword search for improved retrieval") and when ("Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases like "implementing RAG systems", "building search engines", and "vector and keyword search" give good keyword coverage a user would actually say, though a few common synonyms (e.g. "semantic search", "BM25", file-free context) are missing.	4 / 5
Distinctiveness Conflict Risk	Hybrid search is a clear, mostly distinct niche with explicit triggers, but it could still overlap with general RAG-skills or pure vector-search skills, so it sits at mostly-distinct with minor overlap risk rather than minimal conflict.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hybrid-search-implementation/SKILL.md
Commit: 57c135b

Reviewed: 4 days ago

Table of Contents

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.