CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

principle-boundary-discipline

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

72

Quality

90%

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

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.

An exemplarily lean instruction-only skill: it states a design principle, justifies it briefly, gives concrete application rules, and closes with two sharp self-check questions. The only improvement space is a tiny worked example to sharpen the boundary/redundancy line in actionability.

DimensionReasoningScore

Conciseness

The 34-line body is lean with zero padding: it never explains concepts Claude already knows, and every section (Why, The pattern, Applications, The tests) earns its place — 'Scattered validation is noisy, redundant, and gives a false sense of safety' justifies the rule in one sentence rather than lecturing.

5 / 5

Actionability

Concrete directives like 'Validate config at parse time (the boundary), not inside business logic', 'Store raw data at boundaries; parse lazily at use-site', and the two decision tests give mostly executable guidance for an instruction-only skill. The minor gap is the absence of a worked before/after example (e.g., a boundary parse function vs. a redundant internal nil check) that would make the boundary line unmistakable.

4 / 5

Workflow Clarity

This is a simple, single-purpose principle skill under 50 lines with no multi-step process; the single action (place guards at boundaries, extract pure logic) is unambiguous, and the closing tests ('Is this data crossing a system boundary right now?', 'Can this be a pure function that the shell just calls?') function as explicit decision checkpoints. No destructive or batch operations exist to require validation loops.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ bundles exist), and the body is organized into clearly labeled sections (pattern, applications grouped by validation/error handling and code organization, tests), matching the simple-skill exception for a top score.

5 / 5

Total

19

/

20

Passed

Description

83%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 that explicitly pairs a concrete what with a concrete when-should-this-apply clause, uses third-person imperative voice, and stays concise. Weakest points are minor: missing a few natural synonyms in the trigger surface and slight under-enumeration of the boundary actions themselves.

DimensionReasoningScore

Specificity

It lists several specific directives — 'Concentrate guards at system boundaries (CLI, config, network, external APIs)', 'trust internal types', 'keep business logic in pure functions' — with only minor gaps. Not 5 because the boundary actions themselves (validate, return errors, handle defensively) are left to the body rather than enumerated here; clearly above the 1-2-actions level 3 anchor.

4 / 5

Completeness

It explicitly answers both: what ('Concentrate guards at system boundaries... trust internal types and keep business logic in pure functions') and when ('Apply when wiring validation, error handling, or framework adapters') with concrete trigger phrases. Matches the level 5 anchor; the when-clause is already specific, so level 4's 'when could be more explicit' does not apply.

5 / 5

Trigger Term Quality

Natural trigger terms are well covered: 'validation', 'error handling', 'framework adapters', 'CLI', 'config', 'network', 'external APIs'. Not 5 because common phrasings users would actually say — 'input validation', 'defensive programming', 'sanitize input', 'adapters' — are missing; well above level 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

The boundary-discipline framing ('guards at system boundaries (CLI, config, network, external APIs)') carves a clear niche with distinct triggers. Not 5 because 'wiring validation, error handling' is a broad trigger surface with minor overlap risk against general validation/error-handling guidance; comfortably above level 3's 'could still overlap with similar skills'.

4 / 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

adamsardo/pstack-claude

Path

plugins/pstack/skills/principle-boundary-discipline/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.