CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openviking-rule-search

Retrieve applicable OpenViking Rules and check compliance. Use when planning an action or response subject to task-specific constraints.

Quality

80%

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 ./examples/agent-hook-plugin/hosts/codebuddy/skills/openviking-rule-search/SKILL.md

The canonical home for this skill is openviking-rule-search in volcengine/OpenViking

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary lean, operational instruction set: a clear goal, a sequenced workflow with explicit validation and error-recovery feedback loops, and boundary rules that cover the real failure modes of a host-tool-dependent skill. The only meaningful gap is the absence of a concrete example of a `task_context` or a sample tool call, which keeps actionability just below fully executable.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no explanation of concepts Claude already knows; every line is operational (tool-name variants, `applies_when`/`exception` conditions, `delivery.complete` handling). This matches the anchor for lean, efficient content where every token earns its place.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: it names candidate tool registrations, specifies the exact Rule fields to evaluate (`applies_when`, `exception`), and defines precise failure behaviors. It stops short of anchor 5 because there is no example `task_context` or sample tool invocation covering the common case.

4 / 5

Workflow Clarity

The five-step workflow is clearly sequenced with an explicit validation checkpoint (step 3: independently review every returned Rule against its condition and exceptions) and feedback loops for error recovery (step 5 re-call on context change, plus boundary rules for failed requests, incomplete delivery, and compaction expiry). This is not a destructive or batch operation, so no cap applies, and it fits the anchor for clear sequence with explicit validation and feedback loops.

5 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and needs no external references; content is well-organized into Goal, Workflow, and Boundaries sections with no inlined material that belongs in separate files. Per the simple-skill guidance, this merits the top score on structure alone.

5 / 5

Total

19

/

20

Passed

Description

62%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.

The description correctly uses third person, states a clear what, and includes an explicit 'Use when...' clause, keeping conflict risk low through its distinctive domain name. Its weaknesses are limited action coverage (only two verbs) and abstract trigger phrasing that misses the natural terms and synonyms a user would actually say.

Suggestions

Expand the what-clause to enumerate the main actions the skill performs (e.g., 'Build task context, search registered Rules, validate the plan against each match, and re-check when context changes') to raise specificity from two actions to several.

Replace the abstract trigger 'planning an action or response subject to task-specific constraints' with concrete natural phrases users would say, e.g. 'Use when the task mentions rules, constraints, compliance requirements, or policy checks that must be satisfied before acting.'

Add a few synonyms or name variations for the domain (e.g., 'Rules', 'policy rules', 'compliance rules') so the trigger matches how users naturally refer to the constraint set.

DimensionReasoningScore

Specificity

The description names the domain ("OpenViking Rules") and exactly two concrete actions ("Retrieve applicable... Rules" and "check compliance"), matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not list several specific actions (anchor 4), nor is it generic (anchor 2).

3 / 5

Completeness

Both parts are present: a clear what ("Retrieve applicable OpenViking Rules and check compliance") and an explicit when ("Use when planning an action or response subject to task-specific constraints"), satisfying the 'Use when...' requirement. The when-clause is generic rather than concrete trigger phrases, so it falls short of anchor 5 but above anchor 3's missing/weak when.

4 / 5

Trigger Term Quality

Relevant keywords like "Rules", "compliance", and "constraints" appear, but the trigger phrasing "planning an action or response subject to task-specific constraints" is abstract rather than natural user language, and no synonyms or common variations are covered. This fits anchor 3 (some relevant keywords, missing variations) better than anchor 4's good natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

The "OpenViking Rules" domain establishes a mostly distinct niche unlikely to collide with unrelated skills, but the broad when-clause ("task-specific constraints") leaves minor overlap risk with generic compliance or constraint-checking skills. This matches anchor 4 rather than anchor 5's minimal-conflict clear triggers.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

volcengine/OpenViking

Path

examples/agent-hook-plugin/hosts/codebuddy/skills/openviking-rule-search/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.