weknora-rag-search

Use when retrieving from or asking questions against a WeKnora knowledge base via the `weknora` CLI — and especially when unsure whether to use `chat`, `session ask`, or `search chunks` for a given goal.

Quality

91%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable decision guide with a clear sequenced workflow and copy-paste commands. Its single weakness is progressive disclosure: one of the two reference files (chat.md) is not signaled or linked from the overview, leaving a navigation dead-end.

Suggestions

Add an explicit pointer to references/chat.md from the chat/session ask coverage — e.g. in the Safety/Gotchas chat bullet, append 'Details: references/chat.md' — so both reference files have a clear entry point from the overview.

Consider a one-line 'References' index near the end listing references/chat.md and references/search-chunks.md together, making both detail files discoverable in a single glance.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: it delegates background to the weknora-shared skill, uses a compact decision table, never explains what RAG or a knowledge base is, and keeps every section dense and purposeful — every token earns its place. Not level 2 because there is no padded explanation or tightening opportunity.	3 / 3
Actionability	Fully executable copy-paste commands throughout — the decision table maps goals to exact commands, the Quick examples are runnable bash, and Safety/Gotchas gives precise flags (--reference, --verbose, --format ndjson, --limit, --vector-threshold) and recovery commands (session stop/resume).	3 / 3
Workflow Clarity	'The three decisions that matter' is a clearly sequenced selection checklist (answer vs raw context → chat vs session ask → one-shot vs multi-turn), with explicit recovery guidance for the stalled-stream gotcha; no batch/destructive feedback loop is needed here, so the cap-at-2 rule does not apply.	3 / 3
Progressive Disclosure	The overview is well organized and references/search-chunks.md is clearly signaled ('Details: references/search-chunks.md'), but the second bundle file references/chat.md exists with no link or entry point from the SKILL.md body — matching the anchor-2 condition of 'references present but not clearly signaled.' Not level 3 because navigation to chat.md is not provided from the overview.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 tightly scoped, trigger-rich description that clearly states both what it does and when to use it, with natural keywords and a distinct product-bound niche. Its only weakness is that the action verbs are generic and the capability list is not fully comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain ('WeKnora knowledge base via the weknora CLI') and enumerates concrete commands ('chat, session ask, or search chunks'), but the action verbs ('retrieving from or asking questions against') are generic and only 3 of the 6 available commands are mentioned, so it is not comprehensive — not a level 3 multi-action list like 'extract, fill, merge'.	2 / 3
Completeness	Clearly answers both what (retrieval/Q&A against a WeKnora KB via chat/session ask/search chunks) and when, with an explicit 'Use when…' trigger clause plus the 'especially when unsure whether to use…' guidance.	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say — 'retrieving', 'asking questions against a knowledge base', and 'search' — alongside the command names, giving good natural-language coverage rather than pure technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to a named product (WeKnora) and a specific command-selection decision, giving it a clear niche with distinct triggers that would not conflict with unrelated skills.	3 / 3
	Total	11 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: Tencent/WeKnora
Path: cli/skills/weknora-rag-search/SKILL.md
Commit: c64a486

Reviewed: about 11 hours 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.