CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dt-sec-semantic-mapping

Suggest and validate semantic dictionary (SD) mappings for new security integrations using vendor API samples or live events. Use when: mapping a new security vendor data to Dynatrace SD; checking required fields; validating namespaces; highlighting discrepancies vs the semantic dictionary; proposing mapping improvements; running runtime validation against live tenant data.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 effective overview that routes three distinct workflows to specific, real reference files with clear mode detection and explicit approval/validation checkpoints. Its main weaknesses are duplicated file descriptions across sections, a referenced samples/ directory missing from the bundle, and one vague external-skill reference.

Suggestions

Merge the "Baseline Sources" and "References" sections into one list so each reference file is described exactly once, trimming the duplicated descriptions of semantic-reference.md, intake-and-constraints.md, and validation-policy-and-reporting.md (conciseness).

Fix the dangling "samples/" reference: either include the samples directory in the bundle or remove/reword the fallback-consultation instruction, since an agent following it will hit a nonexistent path (progressive_disclosure).

Replace the vague "A skill covering full SD access patterns and Grail-table documentation" bullet with the actual skill name or a resolvable path so the DQL-pattern reference is actionable (progressive_disclosure).

DimensionReasoningScore

Conciseness

The body is a lean, pointer-based overview with no explanation of concepts Claude already knows, but the References section re-describes three files already described under "Baseline Sources" (semantic-reference.md, intake-and-constraints.md, validation-policy-and-reporting.md) and "Scope" repeats the workflow list — trimmable duplication that keeps it below the top anchor.

4 / 5

Actionability

Concrete, instruction-only guidance: "Always run the intake checklist in references/intake-and-constraints.md before generating or validating a mapping", hard rules ("never require scan events for detection", "Do NOT raise critical/major issues for fields on that list"), and a mode table pointing to exact procedural sections; the executable detail lives in the reference files, leaving minor gaps versus fully copy-paste-ready guidance.

4 / 5

Workflow Clarity

Three modes are disambiguated by input in a table, with explicit checkpoints ("Phase 1 mapping table → user approval → Phase 2", "REQUIRED Step 0", and the partial-draft fallback when intake is incomplete), but the detailed validate→fix feedback loops are delegated to the reference files rather than sequenced here, so the 5 anchor's explicit in-body validation loops are not met.

4 / 5

Progressive Disclosure

Good one-level-deep structure where all five referenced references/*.md files exist and cited anchors resolve (#validation-rules, § Workflow A), but the body cites a "samples/" baseline-source directory that does not exist in the bundle and includes a vague unresolvable pointer ("A skill covering full SD access patterns and Grail-table documentation"), which are minor navigation gaps short of the top anchor.

4 / 5

Total

16

/

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 description: concrete third-person capabilities, an explicit multi-trigger "Use when" clause, and a well-defined Dynatrace security-mapping niche. The only weakness is incomplete synonym coverage — natural user phrasings like "findings", "security.events", or "field mapping" are absent.

DimensionReasoningScore

Specificity

"Suggest and validate semantic dictionary (SD) mappings... using vendor API samples or live events" plus a concrete action list ("checking required fields; validating namespaces; highlighting discrepancies...; proposing mapping improvements; running runtime validation against live tenant data") gives comprehensive, specific coverage of all three workflows, matching the top anchor rather than leaving minor gaps.

5 / 5

Completeness

It explicitly answers both questions: a clear third-person "what" ("Suggest and validate semantic dictionary (SD) mappings for new security integrations") and an explicit "Use when:" clause with six concrete trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

Natural domain terms are present ("semantic dictionary", "SD", "mapping", "Dynatrace", "vendor", "live tenant data") including the SD synonym, but common variations a user would actually say ("security.events", "findings", "vulnerability", "compliance", "field mapping") are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

"Dynatrace SD" security-mapping is a clear niche with distinct triggers (semantic dictionary, vendor API samples, tenant validation); overlap risk with generic validation or Dynatrace-adjacent skills is minimal.

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

Dynatrace/dynatrace-for-ai

Path

skills/dt-sec-semantic-mapping/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.