docling-upstream-upgrade
Reproducible workflow to upgrade and port local changes for Docling upstream sources.
Install
mkdir -p .claude/skills/docling-upstream-upgrade && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9753" && unzip -o skill.zip -d .claude/skills/docling-upstream-upgrade && rm skill.zipInstalls to .claude/skills/docling-upstream-upgrade
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Run the one-command Docling upstream upgrade workflow: fetch latest upstream, port local delta, validate, and record baseline metadata.Key capabilities
- →Fetch upstream dependencies
- →Port local deltas
- →Validate upstream changes
- →Record baseline metadata
How it works
It automates the process of fetching, porting, and validating upstream changes.
Inputs & outputs
When to use docling-upstream-upgrade
- →Upgrading upstream dependencies
- →Porting local deltas
- →Validating upstream changes
- →Updating changelogs
About this skill
Docling Upstream Upgrade
Trigger phrases
- "fetch latest and port changes over"
- "upgrade docling upstream"
- "port latest docling-parse changes"
Purpose
Make upstream upgrades reproducible and auditable for ignored upstream sources.
Primary command
powershell -ExecutionPolicy Bypass -File .\scripts\fetch-latest-and-port-docling-parse.ps1
What this skill enforces
- Refresh the tracked upstream delta patch.
- Fetch latest upstream refs (unless intentionally skipped).
- Reapply local port delta onto target upstream commit.
- Run validation gates (tests, smoke, parity, patch check).
- Update baseline metadata (
patches/docling-parse/upstream-baseline.json). - Log outcomes in
docs/operations/progress.md. - Update docs/changelog when workflow/script behavior changes.
Safe debug modes
- Preflight only, no workspace mutation:
-DryRun
- Offline/local preflight:
-SkipFetch
- Faster command-path verification:
-SkipValidation
- Keep temp workspace on failure:
-KeepTempOnFailure
Required evidence after run
- Validation command outcomes recorded in
docs/operations/progress.md. - Baseline metadata file updated.
docs/CHANGELOG.mdupdated for workflow/script changes.
When not to use it
- →When no upstream changes exist
- →For non-Docling projects
Prerequisites
Limitations
- →Requires baseline metadata update
- →Log outcomes in progress.md
How it compares
It makes upstream upgrades reproducible and auditable.
Compared to similar skills
docling-upstream-upgrade side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| docling-upstream-upgrade (this skill) | 0 | 5mo | No flags | Intermediate |
| bazel-build-optimization | 14 | 2mo | No flags | Advanced |
| github-workflow-automation | 11 | 2mo | Review | Advanced |
| wolf-scripts-core | 5 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by sparkeh9
View all by sparkeh9 →You might also like
bazel-build-optimization
wshobson
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
github-workflow-automation
ruvnet
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
wolf-scripts-core
Nice-Wolf-Studio
Core automation scripts for archetype selection, evidence validation, quality scoring, and safe bash execution
github-actions-templates
wshobson
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
bash-defensive-patterns
wshobson
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.
hooks-automation
ruvnet
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.