CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rt-personalization-validation

Validates RT Personalization Entity payloads before creation to prevent common API errors. MUST be invoked proactively during rt-setup-personalization workflow at Step 9c before making the entity creation API call. Also use when encountering "Attribute payload can't be blank" errors or when reviewing personalization entity JSON.

Quality

81%

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

70%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 highly actionable with production-tested templates, explicit validation gates, and error-recovery loops — genuinely useful operational knowledge Claude could not infer. Its weaknesses are repetition (the empty-array rule and near-duplicate templates) and a monolithic structure with no progressive disclosure into bundle files.

Suggestions

Move the three JSON templates to references/templates.md and the bash validation function to scripts/validate_payload.sh, keeping only rule summaries and a one-line pointer in SKILL.md.

Consolidate the empty-array rule to a single statement (Rule #1) and drop the redundant restatements in the checklist and quick-fix guide, or merge Templates 1 and 2 into one template with an optional stringBuilder block.

Fix the grep/sed patterns to use POSIX-compatible classes (e.g., '[[:space:]]*' or grep -E) so the validation function and quick fixes actually match on standard grep/sed.

DimensionReasoningScore

Conciseness

The content is almost entirely non-obvious domain knowledge (misleading API errors, feature-flagged payloads), but the empty-array rule is restated five times (Rule #1, the common-errors table, the checklist, the bash function, and the quick-fix guide) and Templates 1 and 2 are ~80% duplicated. It fits 'mostly efficient but could be tightened' rather than the 'minor instances of over-explanation' anchor above.

3 / 5

Actionability

Three complete JSON templates, a copy-paste bash validation function, and concrete sed/tdx fix commands give mostly executable guidance. A minor gap: the grep/sed patterns use '\s*' which standard BRE grep/sed does not support, so the validator and fixes may silently fail to match on default installations.

4 / 5

Workflow Clarity

The reactive path is a sequenced error-recovery loop (see error → check stringBuilder first → sed fix → verify at least one payload has content), the proactive path is gated on a bash validator with '|| exit 1', and a pre-creation checklist covers the complex process. This matches the top anchor: explicit validation steps, feedback loops, and checklists.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so a 365-line monolith inlines three full JSON templates, a bash script, and field-validation tables that belong in separate files. Section headers keep it navigable ('some structure'), but content that should be separate is inline, matching anchor 3 rather than the well-split anchor 4.

3 / 5

Total

15

/

20

Passed

Description

82%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: it clearly states what the skill does and gives explicit, concrete invocation triggers including an exact error message users would encounter. The only weakness is that it names just one action (validation) rather than enumerating several specific capabilities.

DimensionReasoningScore

Specificity

"Validates RT Personalization Entity payloads before creation" names the domain and one concrete action, but no additional specific capabilities are listed; "prevent common API errors" is a purpose statement rather than an action. This matches the 'names domain and 1-2 concrete actions' anchor and falls short of the 'lists several specific actions' anchor above.

3 / 5

Completeness

The description explicitly answers both questions: what ("Validates RT Personalization Entity payloads before creation to prevent common API errors") and when ("MUST be invoked proactively during rt-setup-personalization workflow at Step 9c... Also use when encountering 'Attribute payload can't be blank' errors or when reviewing personalization entity JSON") with concrete trigger phrases. It clearly matches the top anchor and exceeds the 'when could be more explicit' anchor below.

5 / 5

Trigger Term Quality

Strong natural triggers include the exact user-facing error string "Attribute payload can't be blank", "rt-setup-personalization workflow", and "reviewing personalization entity JSON". A few natural variations are missing (e.g., 'entity creation fails', 'CDP personalization payload'), so it does not reach the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Highly niche scope ("RT Personalization Entity payloads", "rt-setup-personalization workflow at Step 9c", a product-specific error message) gives it a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

17

/

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

treasure-data/td-skills

Path

realtime-skills/rt-personalization-validation/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.