Add top-level README and missing productivity bucket README

CLAUDE.md requires every engineering/productivity/misc skill to be
referenced in a top-level README and every bucket to have its own
README, but neither existed for the top level or productivity bucket.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.claude-plugin/plugin.json

@@ -8,6 +8,14 @@
     "./skills/engineering/to-issues",
     "./skills/engineering/to-prd",
     "./skills/engineering/frontend-design",
+    "./skills/engineering/ask-matt",
+    "./skills/engineering/codebase-design",
+    "./skills/engineering/domain-modeling",
+    "./skills/engineering/implement",
+    "./skills/engineering/prototype",
+    "./skills/engineering/resolving-merge-conflicts",
+    "./skills/engineering/setup-matt-pocock-skills",
+    "./skills/engineering/triage",
     "./skills/productivity/grill-me",
     "./skills/productivity/grilling",
     "./skills/productivity/handoff"

README.md

@@ -0,0 +1,52 @@
+# Skills
+
+Personal Claude Code skills, organized into bucket folders under `skills/`. See [CLAUDE.md](./CLAUDE.md) for the rules that keep this index in sync with the skill folders and for the User-invoked vs Model-invoked split.
+
+## Engineering
+
+Skills I use daily for code work.
+
+**User-invoked**
+
+- **[ask-matt](./skills/engineering/ask-matt/SKILL.md)** — Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
+- **[grill-with-docs](./skills/engineering/grill-with-docs/SKILL.md)** — Grilling session that also builds your project's domain model, sharpening terminology and updating `CONTEXT.md` and ADRs inline.
+- **[triage](./skills/engineering/triage/SKILL.md)** — Move issues through a state machine of triage roles.
+- **[improve-codebase-architecture](./skills/engineering/improve-codebase-architecture/SKILL.md)** — Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
+- **[setup-matt-pocock-skills](./skills/engineering/setup-matt-pocock-skills/SKILL.md)** — Configure this repo for the engineering skills (issue tracker, triage labels, domain doc layout). Run once per repo.
+- **[to-issues](./skills/engineering/to-issues/SKILL.md)** — Break any plan, spec, or PRD into independently-grabbable issues using vertical slices.
+- **[to-prd](./skills/engineering/to-prd/SKILL.md)** — Turn the current conversation into a PRD and publish it to the issue tracker.
+- **[prototype](./skills/engineering/prototype/SKILL.md)** — Build a throwaway prototype — a runnable terminal app for state/logic questions, or several toggleable UI variations.
+- **[implement](./skills/engineering/implement/SKILL.md)** — Implement work from a PRD or set of issues: TDD at pre-agreed seams, typecheck and test as you go, then review and commit.
+
+**Model-invoked**
+
+- **[diagnosing-bugs](./skills/engineering/diagnosing-bugs/SKILL.md)** — Disciplined diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test.
+- **[tdd](./skills/engineering/tdd/SKILL.md)** — Test-driven development with a red-green-refactor loop. Builds features or fixes bugs one vertical slice at a time.
+- **[domain-modeling](./skills/engineering/domain-modeling/SKILL.md)** — Actively build and sharpen a project's domain model — challenge terms, stress-test with scenarios, update `CONTEXT.md` and ADRs inline.
+- **[codebase-design](./skills/engineering/codebase-design/SKILL.md)** — Shared discipline and vocabulary for designing deep modules: small interfaces, clean seams, testable through the interface.
+- **[resolving-merge-conflicts](./skills/engineering/resolving-merge-conflicts/SKILL.md)** — Work an in-progress git merge/rebase conflict hunk by hunk, resolving by intent, and always finish it (never `--abort`).
+- **[frontend-design](./skills/engineering/frontend-design/SKILL.md)** — Build distinctive, production-grade frontend UI that avoids generic "AI slop" aesthetics.
+
+## Productivity
+
+Daily non-code workflow tools.
+
+**User-invoked**
+
+- **[grill-me](./skills/productivity/grill-me/SKILL.md)** — Relentless interview to sharpen a plan or design, for non-code uses.
+- **[handoff](./skills/productivity/handoff/SKILL.md)** — Compact the current conversation into a handoff document so another agent can continue the work.
+
+**Model-invoked**
+
+- **[grilling](./skills/productivity/grilling/SKILL.md)** — Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved. The reusable loop behind `grill-me`.
+
+## Misc
+
+Tools I keep around but rarely use.
+
+**Model-invoked**
+
+- **[codex-debugging](./skills/misc/codex-debugging/SKILL.md)** — Investigate Codex CLI/app-server behavior, config parsing, tool behavior, prompts, and MCP wiring bugs.
+- **[git-guardrails-claude-code](./skills/misc/git-guardrails-claude-code/SKILL.md)** — Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
+- **[github-deep-review](./skills/misc/github-deep-review/SKILL.md)** — Evidence-first review of a bug or PR: read the code, find the real cause, decide the best fix, and say "not proven" when the trail is weak.
+- **[github-project-triage](./skills/misc/github-project-triage/SKILL.md)** — Triage a GitHub project's issues/PRs into maintainer-facing item cards: what it's about, risk, proof/test state, blockers, next action.

skills/engineering/README.md

@@ -14,6 +14,7 @@ Reachable only when you type them (`disable-model-invocation: true`).
 - **[to-issues](./to-issues/SKILL.md)** — Break any plan, spec, or PRD into independently-grabbable issues using vertical slices.
 - **[to-prd](./to-prd/SKILL.md)** — Turn the current conversation into a PRD and publish it to the issue tracker.
 - **[prototype](./prototype/SKILL.md)** — Build a throwaway prototype — a runnable terminal app for state/logic questions, or several toggleable UI variations.
+- **[implement](./implement/SKILL.md)** — Implement work from a PRD or set of issues: TDD at pre-agreed seams, typecheck and test as you go, then review and commit.
 
 ## Model-invoked
 
@@ -23,3 +24,5 @@ Model- or user-reachable (rich trigger phrasing so the model can reach for them)
 - **[tdd](./tdd/SKILL.md)** — Test-driven development with a red-green-refactor loop. Builds features or fixes bugs one vertical slice at a time.
 - **[domain-modeling](./domain-modeling/SKILL.md)** — Actively build and sharpen a project's domain model — challenge terms, stress-test with scenarios, update `CONTEXT.md` and ADRs inline.
 - **[codebase-design](./codebase-design/SKILL.md)** — Shared discipline and vocabulary for designing deep modules: small interfaces, clean seams, testable through the interface.
+- **[resolving-merge-conflicts](./resolving-merge-conflicts/SKILL.md)** — Work an in-progress git merge/rebase conflict hunk by hunk, resolving by intent, and always finish it (never `--abort`).
+- **[frontend-design](./frontend-design/SKILL.md)** — Build distinctive, production-grade frontend UI that avoids generic "AI slop" aesthetics.

skills/misc/README.md

@@ -2,7 +2,11 @@
 
 Tools I keep around but rarely use.
 
-- **[git-guardrails-claude-code](./git-guardrails-claude-code/SKILL.md)** — Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, etc.) before they execute.
-- **[migrate-to-shoehorn](./migrate-to-shoehorn/SKILL.md)** — Migrate test files from `as` type assertions to @total-typescript/shoehorn.
-- **[scaffold-exercises](./scaffold-exercises/SKILL.md)** — Create exercise directory structures with sections, problems, solutions, and explainers.
-- **[setup-pre-commit](./setup-pre-commit/SKILL.md)** — Set up Husky pre-commit hooks with lint-staged, Prettier, type checking, and tests.
+## Model-invoked
+
+Model- or user-reachable (rich trigger phrasing so the model can reach for them).
+
+- **[codex-debugging](./codex-debugging/SKILL.md)** — Investigate Codex CLI/app-server behavior, config parsing, tool behavior, prompts, and MCP wiring bugs.
+- **[git-guardrails-claude-code](./git-guardrails-claude-code/SKILL.md)** — Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
+- **[github-deep-review](./github-deep-review/SKILL.md)** — Evidence-first review of a bug or PR: read the code, find the real cause, decide the best fix, and say "not proven" when the trail is weak.
+- **[github-project-triage](./github-project-triage/SKILL.md)** — Triage a GitHub project's issues/PRs into maintainer-facing item cards: what it's about, risk, proof/test state, blockers, next action.

skills/productivity/README.md

@@ -0,0 +1,16 @@
+# Productivity
+
+Daily non-code workflow tools.
+
+## User-invoked
+
+Reachable only when you type them (`disable-model-invocation: true`).
+
+- **[grill-me](./grill-me/SKILL.md)** — Relentless interview to sharpen a plan or design, for non-code uses.
+- **[handoff](./handoff/SKILL.md)** — Compact the current conversation into a handoff document so another agent can continue the work.
+
+## Model-invoked
+
+Model- or user-reachable (rich trigger phrasing so the model can reach for them).
+
+- **[grilling](./grilling/SKILL.md)** — Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved. The reusable loop behind `grill-me`.