CtrlK
BlogDocsLog inGet started
Tessl Logo

knowledge-distillation

Compile one or more OpenViking knowledge bases or document collections into topic-organized, evidence-grounded high-level knowledge, including cross-source findings, trends, changes, drivers, comparisons, implications, and uncertainties. Use with ov compile when the user asks to distill or synthesize a knowledge base, compare multiple collections, or derive higher-order insights such as changes across financial reports; do not use for document-by-document summaries.

70

Quality

85%

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

77%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-structured, actionable instruction-only skill with a clear sequenced workflow and an explicit validation checklist. The main weakness is conciseness — several prose sections are denser than necessary and could be trimmed without losing clarity.

Suggestions

Tighten the Distillation standard and Workflow prose: the evidence-level definitions and repeated path-naming guidance restate the same constraints multiple times and can be consolidated.

Consider trimming the 'Output model' section's detailed rules into a shorter checklist, since the financial-report example already conveys the shape concretely.

The Quality gate duplicates some constraints from earlier sections (no index by default, valid OKF frontmatter); deduplicate so the gate reads as a true final check rather than a restatement.

DimensionReasoningScore

Conciseness

The instruction-only prose assumes Claude's competence and avoids explaining basic concepts, but at roughly 200 lines several passages are over-elaborated (e.g., repeated naming guidance, lengthy evidence-level definitions) and could be tightened.

3 / 5

Actionability

Provides concrete, specific guidance — an OKF frontmatter template, an output-tree shape, named claim-card fields (subject, predicate, scope, time, evidence, status), and explicit path examples — leaving only minor gaps such as the absence of an executable verification command.

4 / 5

Workflow Clarity

Sequences a clear multi-step workflow (Frame → Survey → Build topics → Normalize evidence → Derive findings → Write with provenance → Integrate existing) and closes with an explicit Quality-gate checklist of validation checkpoints, addressing the batch/destructive risk of overwriting target pages.

5 / 5

Progressive Disclosure

No bundle files exist and the skill is self-contained; the body is well-organized into clearly labeled sections (Goal, Output model, Distillation standard, Workflow, Quality gate), which per the rubric's simple-skill guidance merits a top score without external references.

5 / 5

Total

17

/

20

Passed

Description

92%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 strong, specific description that clearly states both what the skill does and when to use it, with natural trigger phrases and an explicit negative boundary. The only minor gap is synonym/extension coverage in the trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and output types — 'topic-organized, evidence-grounded high-level knowledge, including cross-source findings, trends, changes, drivers, comparisons, implications, and uncertainties' — giving comprehensive coverage of what the skill produces.

5 / 5

Completeness

Explicitly answers both what ('Compile … into topic-organized, evidence-grounded high-level knowledge') and when ('Use with ov compile when the user asks to distill or synthesize … compare multiple collections … derive higher-order insights'), with a concrete negative boundary ('do not use for document-by-document summaries').

5 / 5

Trigger Term Quality

Includes natural user phrases ('distill or synthesize a knowledge base', 'compare multiple collections', 'derive higher-order insights', 'changes across financial reports') plus the command 'ov compile', but stops short of exhaustive synonym/extension coverage that would merit a 5.

4 / 5

Distinctiveness Conflict Risk

Tied to a specific command (ov compile) and a distinct niche (higher-order distillation, explicitly contrasted against document-by-document summaries), giving a clear niche with minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
volcengine/OpenViking
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.