What’s inside

One SKILL.md (the playbook) + one starter template. A preview:

Terminal Coder

When to use

• You have a repo and want to build a feature or fix a bug by describing it in plain language
• You want builds, tests, and lint run for you, with results summarized instead of terminal-scrolling
• PRs need drafting from plain-language instructions, and review before they're created
• You want read-only exploration — codebase tours, "where is X handled?" — without touching anything
• Repetitive safe shell chores (batch renames, cleanup checks, listing open PRs) you don't want to type yourself

Workflow

1. Point and describe (input: repo path + plain-language task → output: task plan)
   Tell the AI where the code lives and what to build or fix in ordinary words. It should read the relevant code first and sketch a plan — what it will change and why — before touching anything.
2. Read before writing (input: task plan → output: confirmed understanding)
   The AI reads the relevant files and confirms its understanding: which files it will touch and why. Blind edits are how regressions happen; the read-first step is what separates this from autocomplete.
3. Edit, then verify (input: edits → output: diff + test results)
   The AI makes the changes, then runs the build and test commands to verify. "It looks right" is not done; tests passing is done. It shows you a summary of every change as a diff — you review the diff, not just the claim.
4. Respect the permission ladder (input: command intent → output: approved or declined execution)
   Reads run automatically. Anything that writes, moves, deletes, or hits the network asks first. Destructive commands (rm -rf, database wipes, force pushes) need explicit approval every time — no blanket "do whatever it takes," and "clean up everything" is never an approval.
5. Ship with review (input: verified changes → output: draft PR)
   When tests pass, the AI drafts the PR — title, description, change summary, test evidence — and waits for your confirmation to create it. Nothing is committed or pushed without your go-ahead.
6. Parallelize when it helps (input: large task → output: split subtasks + integration)
   For big tasks, split the work into independent subtasks handled by parallel sub-agents with a complexity budget, then integrate the results. Useful for large repos or batch work like "fix lint across all files." One real case ran eight sub-agents in parallel on separate C programs.

Output spec

Template preview

Terminal Coder — Task Brief Template

One brief per task. The AI reads first, edits second, and shows the diff before anything ships.

Task: {plain-language description}

Repo path: {absolute path} Branch: {branch name — work on a feature branch, not main}

Plan (AI fills in before editing — you confirm)

Files to touch: {list with one-line reason each} Approach: {2–3 sentences: what it will do} Won't touch: {files/areas explicitly out of scope}

[ ] Plan confirmed — proceed [ ] Revise plan

Permission ladder for this task

Result

Diff summary: {files changed, what changed and why}

Buy the full skill pack — $4.99 Pro — all 471 skills