CtrlK
BlogDocsLog inGet started
Tessl Logo

weknora-shared

Use when driving a WeKnora RAG server through the `weknora` CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora-* skill.

77

Quality

98%

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

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 lean, highly actionable shared-base skill with concrete commands, a clear output/exit-code contract, and strong validation feedback loops for destructive and batch operations. Its only weakness is that all content lives in one inline file rather than being split into reference bundles.

Suggestions

Consider extracting the §3 output-contract field table and §4 exit-code table into a references/ file (e.g. OUTPUT_CONTRACT.md) so the main SKILL.md stays a lean overview, which would lift progressive_disclosure to a 5.

The §8 resource-model command map is reference material that could live in its own bundle file with a one-line pointer, keeping the base skill focused on workflow and contracts.

DimensionReasoningScore

Conciseness

Dense and agent-focused; it assumes Claude's competence (never explains JSON, RAG, or exit codes generically) and every line carries CLI-specific contract detail, matching the lean score-5 anchor.

5 / 5

Actionability

Provides copy-paste-ready bash throughout (profile add, auth login --with-token, kb create chaining with --jq, dry-run), plus a concrete exit-code table and JSON envelope field spec — fully executable guidance covering common cases.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced (two-step auth with "order matters", numbered §7a tool-approval loop) with strong validation checkpoints and feedback loops for destructive/batch ops (exit-10 approval hard rule, dry-run-before-acting, batch/wait exit-code branching).

5 / 5

Progressive Disclosure

Well-organized into numbered sections with a Common-mistakes table and one well-signaled sibling-skill reference ("see the `weknora-rag-search` skill for the decision table"), but it remains a single 211-line inline file with no bundle split — good structure with minor organization gaps rather than the multi-file split of the score-5 anchor.

4 / 5

Total

19

/

20

Passed

Description

100%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, trigger-rich description that clearly states what the skill does and when to use it, with concrete capability verbs and product-specific keywords. It is comprehensive and distinctive with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the CLI surface — "authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes" — which is comprehensive coverage of the capability set, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both: "what" (driving the CLI as an agent — authenticating, managing resources, running search/chat, interpreting envelopes/exit codes) and "when" ("Use when driving a WeKnora RAG server..."), plus an extra trigger cue ("Read this before any other weknora-* skill").

5 / 5

Trigger Term Quality

Surfaces natural, product-specific terms a user would say — "WeKnora RAG server", "`weknora` CLI", "knowledge bases", "search", "chat", "agent" — covering the domain comprehensively with the product name and primary verbs.

5 / 5

Distinctiveness Conflict Risk

Product-specific niche (WeKnora RAG CLI) with distinct triggers; the "Read this before any other weknora-* skill" clause explicitly disambiguates it from sibling skills, minimizing conflict risk.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
Tencent/WeKnora
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.