tdd: drop the refactor stage — red → green, not red → green → refactor

Refactoring belongs to the review stage, not the implementation loop.
Remove the refactor rule and the now-orphaned refactoring.md (its home is
the review skill), and point the loop's rule at the review skill so it
isn't re-added.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.changeset/review-smell-baseline.md

@@ -1,5 +0,0 @@
----
-"mattpocock-skills": patch
----
-
-Give the in-progress **`review`** skill an always-on Fowler smell baseline on its Standards axis. A curated ~12 high-signal "Bad Smells in Code" (Mysterious Name, Duplicated Code, Feature Envy, Data Clumps, Primitive Obsession, Repeated Switches, Shotgun Surgery, Divergent Change, Speculative Generality, Message Chains, Middle Man, Refused Bequest) are inlined into `SKILL.md` as a fixed baseline alongside whatever the repo documents — not a new third axis. Two binding rules keep it safe: a documented repo standard overrides the baseline, and every smell is reported as a judgement call, never a hard violation.

.changeset/tdd-reference-only-seams.md

@@ -0,0 +1,7 @@
+---
+"mattpocock-skills": patch
+---
+
+Reshape the `tdd` skill into reference-only. The red → green → refactor loop is anchored by leading words the model already holds, so the step-by-step Workflow was largely restating the loop and duplicating the horizontal-slicing anti-pattern. Dropped the Workflow and per-cycle checklist; folded their one durable idea — vertical slices / tracer bullets — into the Anti-patterns section and a short Rules-of-the-loop list. Introduced **seam** as the leading word for where tests go, collapsing the old Philosophy "public interfaces" prose and the Planning "confirm interface / behaviors" handshake into one rule: test only at pre-agreed seams, confirmed with the user before any test is written.
+
+Also dropped the refactor stage — TDD is now red → green, not red → green → refactor. Refactoring belongs to the review stage, not the implementation loop, so the refactor rule and `refactoring.md` were removed (its home is the `review` skill).

CLAUDE.md

@@ -14,5 +14,3 @@ Each skill entry in the top-level `README.md` must link the skill name to its `S
 Each bucket folder has a `README.md` that lists every skill in the bucket with a one-line description, with the skill name linked to its `SKILL.md`. Bucket `README.md`s and the top-level `README.md` group entries into **User-invoked** and **Model-invoked**.
 
 Every `SKILL.md` is either user-invoked (`disable-model-invocation: true`, reachable only by the human) or model-invoked (model- or user-reachable). For the full definitions, description conventions, and why a user-invoked skill can invoke model-invoked skills but never another user-invoked one, see [docs/invocation.md](./docs/invocation.md).
-
-To (re)link every skill into the local harness skill directories (`~/.claude/skills`, `~/.agents/skills`), run `scripts/link-skills.sh`. Each entry is a symlink into this repo, so a `git pull` keeps installed skills current; re-run the script after adding, removing, or renaming a skill.

scripts/link-skills.sh

@@ -1,10 +1,6 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-# NOTE: This is a dev-only script, intended for use by maintainers of this repo.
-# It is not a supported installer. Modifications to it — or requests for
-# modifications — will not be approved.
-#
 # Links all skills in the repository into the local skill directories used by
 # each agent harness:
 #   - ~/.claude/skills  — Claude Code

skills/engineering/tdd/SKILL.md

@@ -5,107 +5,32 @@ description: Test-driven development. Use when the user wants to build features
 
 # Test-Driven Development
 
-## Philosophy
+TDD is the red → green loop. This skill is the reference that makes that loop produce tests worth keeping: what a good test is, where tests go, the anti-patterns, and the rules of the loop. Every section applies on every cycle — consult them before and during the loop, not after.
 
-**Core principle**: Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't.
+When exploring the codebase, read `CONTEXT.md` (if it exists) so test names and interface vocabulary match the project's domain language, and respect ADRs in the area you're touching.
 
-**Good tests** are integration-style: they exercise real code paths through public APIs. They describe _what_ the system does, not _how_ it does it. A good test reads like a specification - "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about internal structure.
+## What a good test is
 
-**Bad tests** are coupled to implementation. They mock internal collaborators, test private methods, or verify through external means (like querying a database directly instead of using the interface). The warning sign: your test breaks when you refactor, but behavior hasn't changed. If you rename an internal function and tests fail, those tests were testing implementation, not behavior.
+Tests verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't. A good test reads like a specification — "user can checkout with valid cart" tells you exactly what capability exists — and survives refactors because it doesn't care about internal structure.
-
-**Tautological tests** restate the implementation inside the assertion, so they pass by construction and give zero confidence. When the expected value is computed the way the code computes it — `expect(add(a, b)).toBe(a + b)`, snapshotting a figure you derived by hand the same way the code does, asserting a constant equals itself — the test can never disagree with the code: break the code wrong and the assertion breaks wrong with it. The expected value must come from an independent source of truth — a known-good literal, a worked example, the spec.
 
 See [tests.md](tests.md) for examples and [mocking.md](mocking.md) for mocking guidelines.
 
-## Anti-Pattern: Horizontal Slices
+## Seams — where tests go
 
-**DO NOT write all tests first, then all implementation.** This is "horizontal slicing" - treating RED as "write all tests" and GREEN as "write all code."
+A **seam** is the public boundary you test at: the interface where you observe behavior without reaching inside. Tests live at seams, never against internals.
 
-This produces **crap tests**:
+**Test only at pre-agreed seams.** Before writing any test, write down the seams under test and confirm them with the user. No test is written at an unconfirmed seam. You can't test everything — agreeing the seams up front is how testing effort lands on the critical paths and complex logic instead of every edge case.
 
-- Tests written in bulk test _imagined_ behavior, not _actual_ behavior
+Ask: "What's the public interface, and which seams should we test?"
-- You end up testing the _shape_ of things (data structures, function signatures) rather than user-facing behavior
-- Tests become insensitive to real changes - they pass when behavior breaks, fail when behavior is fine
-- You outrun your headlights, committing to test structure before understanding the implementation
 
-**Correct approach**: Vertical slices via tracer bullets. One test → one implementation → repeat. Each test responds to what you learned from the previous cycle. Because you just wrote the code, you know exactly what behavior matters and how to verify it.
+## Anti-patterns
 
-```
+- **Implementation-coupled** — mocks internal collaborators, tests private methods, or verifies through a side channel (querying the database instead of using the interface). The tell: the test breaks when you refactor but behavior hasn't changed.
-WRONG (horizontal):
+- **Tautological** — the assertion recomputes the expected value the way the code does (`expect(add(a, b)).toBe(a + b)`, a snapshot derived by hand the same way, a constant asserted equal to itself), so it passes by construction and can never disagree with the code. Expected values must come from an independent source of truth — a known-good literal, a worked example, the spec.
-  RED:   test1, test2, test3, test4, test5
+- **Horizontal slicing** — writing all tests first, then all implementation. Bulk tests verify _imagined_ behavior: you test the _shape_ of things rather than user-facing behavior, the tests go insensitive to real changes, and you commit to test structure before understanding the implementation. Work in **vertical slices** instead — one test → one implementation → repeat, each test a **tracer bullet** that responds to what the last cycle taught you.
-  GREEN: impl1, impl2, impl3, impl4, impl5
 
-RIGHT (vertical):
+## Rules of the loop
-  RED→GREEN: test1→impl1
-  RED→GREEN: test2→impl2
-  RED→GREEN: test3→impl3
-  ...
-```
 
-## Workflow
+- **Red before green.** Write the failing test first, then only enough code to pass it. Don't anticipate future tests or add speculative features.
-
+- **One slice at a time.** One seam, one test, one minimal implementation per cycle.
-### 1. Planning
+- **Refactoring is not part of the loop.** It belongs to the review stage (see the `review` skill), not the red → green implementation cycle.
-
-When exploring the codebase, read `CONTEXT.md` (if it exists) so that test names and interface vocabulary match the project's domain language, and respect ADRs in the area you're touching.
-
-Before writing any code:
-
-- [ ] Confirm with user what interface changes are needed
-- [ ] Confirm with user which behaviors to test (prioritize)
-- [ ] Identify opportunities for deep modules (small interface, deep implementation) — run the `/codebase-design` skill for the vocabulary and the testability checks
-- [ ] List the behaviors to test (not implementation steps)
-- [ ] Get user approval on the plan
-
-Ask: "What should the public interface look like? Which behaviors are most important to test?"
-
-**You can't test everything.** Confirm with the user exactly which behaviors matter most. Focus testing effort on critical paths and complex logic, not every possible edge case.
-
-### 2. Tracer Bullet
-
-Write ONE test that confirms ONE thing about the system:
-
-```
-RED:   Write test for first behavior → test fails
-GREEN: Write minimal code to pass → test passes
-```
-
-This is your tracer bullet - proves the path works end-to-end.
-
-### 3. Incremental Loop
-
-For each remaining behavior:
-
-```
-RED:   Write next test → fails
-GREEN: Minimal code to pass → passes
-```
-
-Rules:
-
-- One test at a time
-- Only enough code to pass current test
-- Don't anticipate future tests
-- Keep tests focused on observable behavior
-
-### 4. Refactor
-
-After all tests pass, look for [refactor candidates](refactoring.md):
-
-- [ ] Extract duplication
-- [ ] Deepen modules (move complexity behind simple interfaces)
-- [ ] Apply SOLID principles where natural
-- [ ] Consider what new code reveals about existing code
-- [ ] Run tests after each refactor step
-
-**Never refactor while RED.** Get to GREEN first.
-
-## Checklist Per Cycle
-
-```
-[ ] Test describes behavior, not implementation
-[ ] Test uses public interface only
-[ ] Test would survive internal refactor
-[ ] Expected values are independent literals, not recomputed from the code
-[ ] Code is minimal for this test
-[ ] No speculative features added
-```

skills/engineering/tdd/refactoring.md

@@ -1,10 +0,0 @@
-# Refactor Candidates
-
-After TDD cycle, look for:
-
-- **Duplication** → Extract function/class
-- **Long methods** → Break into private helpers (keep tests on public interface)
-- **Shallow modules** → Combine or deepen
-- **Feature envy** → Move logic to where data lives
-- **Primitive obsession** → Introduce value objects
-- **Existing code** the new code reveals as problematic

skills/in-progress/decision-mapping/SKILL.md

@@ -4,7 +4,7 @@ description: Turn a loose idea into a sequenced map of investigation tickets, th
 disable-model-invocation: true
 ---
 
-This skill is invoked when a loose idea requires more than one agent session to turn into a plan. It creates a stateful decision map in a markdown file, and drives the user through a sequence of tickets to resolve the open questions - which may require either prototyping, research or grilling. The map is domain-agnostic: it plans engineering work, course content, or anything else that fits the same shape.
+This skill is invoked when a loose idea requires more than one agent session to turn into a plan. It creates a stateful decision map in a markdown file, and drives the user through a sequence of tickets to resolve the open questions - which may require either prototyping, research or grilling.
 
 ## The Decision Map
 
@@ -47,11 +47,9 @@ Each ticket must be sized to one 100K token agent session.
 There are three types of tickets:
 
 - **Research**: Reading documentation, third-party API's, or local resources like knowledge bases. Creates a markdown summary as an asset. Use this when knowledge outside the current working directory is required.
-- **Prototype**: Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the /prototype skill. Creates the prototype as an asset. Use this when "how should it look" or "how should it behave" is the key question.
+- **Prototype**: Writing UI or logic code to test a hypothesis, or to explore a design space. Uses the /prototype skill. Creates a prototype as an asset. Use this when "how should it look" or "how should it behave" is the key question.
 - **Grilling**: Conversation with the agent. Uses the /grilling and /domain-modeling skills. Asks one question at a time. The default case.
 
-Validation isn't a fourth type — it's the thread running through all three.
-
 ## Fog of war
 
 The map is _deliberately_ incomplete beyond the frontier. Your job is to investigate the frontier, and to resolve tickets in order to push the frontier forward. Push back the fog of war, one node at a time — until the path to the finish line is clear and no tickets remain.
@@ -74,7 +72,7 @@ User invokes with a path to an existing map. A ticket slug is **optional** — w
 
 1. Load the **whole map** as context.
 2. Choose the ticket. If the user named one, use it. Otherwise pick the first `open` ticket in document order that is [unblocked](#structure). [Claim it](#structure): set `Status: in-progress` and save before any work.
-3. Resolve it, invoking skills as needed — including any the `## Notes` block names. If in doubt, use `/grilling` and `/domain-modeling`.
+3. Resolve it, invoking skills as needed. If in doubt, use `/grilling` and `/domain-modeling`.
 4. Record the answer in the ticket's body and set `Status: resolved`.
 5. Add newly-discovered tickets with correct `Blocked by` edges. If the decisions made invalidate other parts of the map, update or delete those nodes.
 6. Handoff.
@@ -103,7 +101,3 @@ End every session by clearing the context and opening one or more fresh sessions
 > ```
 
 **No open tickets remain.** The fog is pushed back far enough that the path to the finish line is clear — the map is done. (The initial grilling may also surface no fog at all, in which case there was never a map to build.) Recommend implementing directly, or using `/to-prd` to schedule a multi-session implementation.
-
-## Notes
-
-An optional block declaring the **domain**, any skills every session should `consult`, and freeform standing preferences the planning surfaces.

skills/in-progress/review/SKILL.md

@@ -35,26 +35,6 @@ Look for the originating spec, in this order:
 
 Anything in the repo that documents how code should be written, such as `CODING_STANDARDS.md` or `CONTRIBUTING.md`.
 
-On top of whatever the repo documents, the Standards axis always carries the **smell baseline** below — a fixed set of Fowler code smells (_Refactoring_, ch.3) that applies even when a repo documents nothing. Two rules bind it:
-
-- **The repo overrides.** A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell.
-- **Always a judgement call.** Each smell is a labelled heuristic ("possible Feature Envy"), never a hard violation — and, like any standard here, skip anything tooling already enforces.
-
-Each smell reads *what it is* → *how to fix*; match it against the diff:
-
-- **Mysterious Name** — a function, variable, or type whose name doesn't reveal what it does or holds. → rename it; if no honest name comes, the design's murky.
-- **Duplicated Code** — the same logic shape appears in more than one hunk or file in the change. → extract the shared shape, call it from both.
-- **Feature Envy** — a method that reaches into another object's data more than its own. → move the method onto the data it envies.
-- **Data Clumps** — the same few fields or params keep travelling together (a type wanting to be born). → bundle them into one type, pass that.
-- **Primitive Obsession** — a primitive or string standing in for a domain concept that deserves its own type. → give the concept its own small type.
-- **Repeated Switches** — the same `switch`/`if`-cascade on the same type recurs across the change. → replace with polymorphism, or one map both sites share.
-- **Shotgun Surgery** — one logical change forces scattered edits across many files in the diff. → gather what changes together into one module.
-- **Divergent Change** — one file or module is edited for several unrelated reasons. → split so each module changes for one reason.
-- **Speculative Generality** — abstraction, parameters, or hooks added for needs the spec doesn't have. → delete it; inline back until a real need shows.
-- **Message Chains** — long `a.b().c().d()` navigation the caller shouldn't depend on. → hide the walk behind one method on the first object.
-- **Middle Man** — a class or function that mostly just delegates onward. → cut it, call the real target direct.
-- **Refused Bequest** — a subclass or implementer that ignores or overrides most of what it inherits. → drop the inheritance, use composition.
-
 ### 4. Spawn both sub-agents in parallel
 
 Send a single message with two `Agent` tool calls. Use the `general-purpose` subagent for both.
@@ -62,8 +42,8 @@ Send a single message with two `Agent` tool calls. Use the `general-purpose` sub
 **Standards sub-agent prompt** — include:
 
 - The full diff command and commit list.
-- The list of standards-source files you found in step 3, **plus the smell baseline from step 3** pasted in full — the sub-agent has no other access to it.
+- The list of standards-source files you found in step 3.
-- The brief: "Report — per file/hunk where relevant — (a) every place the diff violates a documented standard: cite the standard (file + the rule); and (b) any baseline smell you spot: name it and quote the hunk. Distinguish hard violations from judgement calls — documented-standard breaches can be hard, but baseline smells are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words."
+- The brief: "Report — per file/hunk where relevant — every place the diff violates a documented standard. Cite the standard (file + the rule). Distinguish hard violations from judgement calls. Skip anything tooling enforces. Under 400 words."
 
 **Spec sub-agent prompt** — include: