Kp content validation
Skill Tibsfox/gsd-skill-creator/infra/packs/knowledge/skills/kp-content-validation
Introduces a comprehensive agent-based framework for guided software development (GSD)
npx -y skills add Tibsfox/gsd-skill-creator --skill kp-content-validationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Validates knowledge pack content against runtime schemas: .skillmeta against KnowledgePackSchema, modules against ModulesFileSchema, activities against PackActivitySchema. Checks cross-pack references, learning outcome uniqueness, and file completeness. Use when validating pack content after generation.
SKILL.md
3.4 KB, 506 tokens by cl100k_base, as published. Nobody here has run it
Content Validation
Purpose
Validates all generated pack content against the runtime schemas defined in src/knowledge/types.ts. This is the quality gate skill used by the KP-05 validator agent after each batch of packs is generated. It catches schema violations, missing files, broken cross-pack references, and duplicate learning outcome codes before content reaches the review stage.
Capabilities
- .skillmeta YAML validation against KnowledgePackSchema via parseSkillmeta
- Modules YAML validation against ModulesFileSchema
- Activities JSON validation against PackActivitySchema (per-entry)
- Vision document structure validation (required sections present)
- Assessment framework structure validation (rubric levels present)
- Resource catalog validation (links resolve, categories present)
- Cross-pack dependency reference validation (pack_id exists in registry)
- Learning outcome code uniqueness across all registered packs
- File completeness check (all 6 required files per pack directory)
- Batch validation: run all checks across 5 packs in a single pass
Key Modules
| Module | Purpose |
|---|---|
src/knowledge/content-validator.ts | Pack content validation engine |
src/knowledge/skillmeta-parser.ts | .skillmeta YAML parsing with Zod validation |
src/knowledge/registry.ts | Pack registry for cross-reference checking |
src/knowledge/dependency-resolver.ts | Prerequisite chain validation with cycle detection |
src/knowledge/prerequisite-validator.ts | Entry requirement checking |
Usage Examples
Validate a single pack:
import { validatePack } from './content-validator.js';
const result = await validatePack('src/knowledge/packs/math-101');
// result.valid: boolean
// result.errors: string[] (empty if valid)
// result.warnings: string[] (non-blocking issues)
Validate a batch:
After Phase 245 completes, run validation across all 5 generated packs:
- MATH-101, SCI-101, TECH-101, ENGR-101, PHYS-101
Check cross-pack references resolve within the batch and against previously registered packs.
Dependencies
- Pack runtime API (src/knowledge/) -- all parsers and validators
- Registry with previously registered packs for cross-reference resolution
Token Budget Rationale
1.0% budget reflects the validation module references and schema knowledge needed for comprehensive checking. The validator operates on the runtime API, not on raw content, keeping context requirements moderate.
Gives 0 of the 12 instructions most quality gates skills give in 506 tokens
Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-06
- read the output and check the exit codein 55 of 1195, across 14 files
- verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
- identify the verification command proving the claimin 53 of 1195, across 12 files
- run the full verification commandin 51 of 1195, across 11 files
- verify output confirms the claimin 49 of 1195, across 10 files
- check version control diff after agent delegationin 45 of 1195, across 5 files
- state claim with evidencein 43 of 1195, across 3 files
- run the test suitein 32 of 1195, across 24 files
- keep state in memory by defaultin 27 of 1195, across 6 files
- make prototype runnable with one commandin 26 of 1195, across 5 files
- detect the package manager from lockfilesin 24 of 1195, across 5 files
- produce a verification reportin 23 of 1195, across 12 files
Said here and by no other author read
- validate .skillmeta YAML against KnowledgePackSchema
- validate modules YAML against ModulesFileSchema
- validate activities JSON against PackActivitySchema per entry
- validate vision document required sections are present
- validate assessment framework rubric levels are present
- validate resource catalog links resolve and categories exist
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.