jetxu-llm/docmason/validation-repair

Claude Code and agent skill by jetxu-llm/docmason

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Validate the staged or published DocMason knowledge base and repair blocking issues until the quality gate passes.

Install

npx vskill@latest install jetxu-llm/docmason/validation-repair

SKILL.md

Validation Repair

Use this skill when the knowledge base needs validation, repair, or publication follow-through.

This is an internal follow-on workflow behind knowledge-base-sync. Ordinary users should not need to invoke it by name.

Required Capabilities

  • local file access
  • shell or command execution
  • ability to read machine-readable validation reports

If the agent cannot run docmason validate-kb or inspect the reported errors, stop and explain that reliable repair is not possible.

Procedure

  1. Use staging as the default validation target unless the task explicitly says otherwise.
  2. Run docmason validate-kb --json.
  • keep DocMason workspace commands sequential inside one live workspace session
  • do not overlap validate-kb with sync, status, retrieve, or trace against the same workspace while leases may still be active
  1. Inspect the blocking_errors, warnings, and per-source reports in knowledge_base/<target>/validation_report.json.
  2. Fix the staged source or interaction-memory files that caused the failures:
  • missing or stale knowledge.json
  • missing or malformed summary.md
  • unresolved citations
  • unresolved artifact_id citations
  • invalid related-source links
  • missing or malformed artifact_index.json
  • missing or malformed pdf_document.json
  • missing or malformed semantic_overlay/*.json
  • invalid render_page_span, artifact refs, or sidecar asset references
  • placeholder or incomplete bilingual content
  1. Rerun docmason validate-kb --json until the result is valid or warnings.
  2. When staged validation is no longer blocking, return control to the main agent so it can rerun docmason sync --json for final publication.

Escalation Rules

  • If validation reveals a capability or evidence gap that cannot be repaired honestly, stop and surface that blocker instead of weakening the quality gate.
  • If a fix would require changing derived retrieval or trace artifacts directly, do not hand-edit them. Regenerate them through the supported workflows.
  • If the failure is in deterministic sidecars such as artifact_index, visual_layout, spreadsheet_*, or pdf_document, repair the upstream staged source inputs or rerun the supported compiler path instead of hand-editing the derived files.
  • Final publication remains a main-agent step.

Completion Signal

  • The workflow is complete when validation reaches valid or warnings, or when a concrete unrecoverable blocker has been surfaced to the main agent.

Notes

  • Blocking errors prevent publication.
  • Warnings are acceptable only when the evidence manifest records partial extraction failure clearly and the surviving evidence still exists.
  • Do not hand-edit derived graph, retrieval, or trace files unless you are explicitly regenerating them through the supported DocMason commands.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
135
Repository forks
35
7-day trend score
25

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 12 Sep 2026, a month ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jetxu-llm/docmason/validation-repair/badge)](https://verified-skill.com/skills/jetxu-llm/docmason/validation-repair)

Something wrong with this skill or its page? Tell us.