songshgeo-skills

SongshGeo's Skills — engineering + academic

My personal agent-skills library. It's a fork of mattpocock/skills (Matt Pocock's engineering skills, tracked as a live fork and kept in sync) with an academic research layer (skills/academic/, adapted from feynman) layered on top — literature review, paper writing, replication, scholarly search, and reproducible manuscripts.

• Engineering — Matt Pocock's skills, unchanged and synced from upstream. Please ⭐ his repo and sign up to his newsletter.
• Academic — my own layer: skills/academic/.
• Maintenance — how the two upstreams are merged/adapted: MAINTAINING.md.

Install

This is a fork I maintain, so the simplest install is clone + the link scripts — they symlink every skill (all buckets, including my academic/ layer) and the subagents into your Claude Code dirs, and a git pull keeps them current:

git clone https://github.com/SongshGeo/skills.git
cd skills
bash scripts/link-skills.sh    # skills   → ~/.claude/skills, ~/.agents/skills
bash scripts/link-agents.sh    # subagents → ~/.claude/agents

Optional: set SCHOLAR_EMAIL (repo-root .env or a real env var) so scholar-search can use the polite API pools; and register the upstream remote to pull Matt's updates later — git remote add upstream https://github.com/mattpocock/skills.git (see MAINTAINING.md).

You can also point the skills.sh installer at this fork — npx skills@latest add SongshGeo/skills — but that's the consumer path (a selectable subset driven by the plugin manifest, so the non-promoted academic/ skills won't come through it); the clone + link route above installs the whole set.

Matt's original Quickstart below is the upstream flow for his engineering skills.

Quickstart (30-second setup)

1. Run the skills.sh installer:

npx skills@latest add mattpocock/skills

2. Pick the skills you want, and which coding agents you want to install them on. Make sure you select /setup-matt-pocock-skills.

3. Run /setup-matt-pocock-skills in your agent. It will:

   • Ask you which issue tracker you want to use (GitHub, Linear, or local files)
   • Ask you what labels you apply to tickets when you triage them (/triage uses labels)
   • Ask you where you want to save any docs we create

4. Bam - you're ready to go.

Why These Skills Exist

I built these skills as a way to fix common failure modes I see with Claude Code, Codex, and other coding agents.

#1: The Agent Didn't Do What I Want

"No-one knows exactly what they want"

David Thomas & Andrew Hunt, The Pragmatic Programmer

The Problem. The most common failure mode in software development is misalignment. You think the dev knows what you want. Then you see what they've built - and you realize it didn't understand you at all.

This is just the same in the AI age. There is a communication gap between you and the agent. The fix for this is a grilling session - getting the agent to ask you detailed questions about what you're building.

The Fix is to use:

• /grill-me - for non-code uses
• /grill-with-docs - same as /grill-me, but adds more goodies (see below)

These are my most popular skills. They help you align with the agent before you get started, and think deeply about the change you're making. Use them every time you want to make a change.

#2: The Agent Is Way Too Verbose

With a ubiquitous language, conversations among developers and expressions of the code are all derived from the same domain model.

Eric Evans, Domain-Driven-Design

The Problem: At the start of a project, devs and the people they're building the software for (the domain experts) are usually speaking different languages.

I felt the same tension with my agents. Agents are usually dropped into a project and asked to figure out the jargon as they go. So they use 20 words where 1 will do.

The Fix for this is a shared language. It's a document that helps agents decode the jargon used in the project.

Example

Here's an example CONTEXT.md, from my course-video-manager repo. Which one is easier to read?