@@ -73,6 +73,7 @@ Always present. Situate the skill in the system in a sentence or two:
 
 - Explain the **why**, not the process. The page orients and situates the skill; it never reproduces the `SKILL.md` steps or template dumps — a human choosing a tool does not need the runbook.
 - Use the skill's **leading words** (_seam_, _deep module_, _tracer bullet_) so the page and the skill speak one language.
+- **Use the [AI Coding Dictionary](https://www.aihero.dev/ai-coding-dictionary)'s term where one exists, and link its first use on the page.** The dictionary is the house vocabulary for AI coding — _context window_, _subagent_, _harness_, _primary source_, _agent mode_. Prefer its word over a synonym you invent. Link the first occurrence of each term to `https://www.aihero.dev/ai-coding-dictionary/<slug>` (the slug is the term lowercased with non-alphanumerics as hyphens: _context window_ → `context-window`), and leave every later occurrence unlinked. Link only where the word carries the dictionary's sense — a domain *model*, background *context* or an auth *token* is a different word that happens to match. Never link inside a heading, a code span, or an existing link, and never link a word that names a skill in this repo rather than the concept. For the full term list, read `~/repos/ai/ai-coding-dictionary/dictionary/` if it exists on this machine — one file per term, the filename *is* the term — and otherwise [mattpocock/dictionary-of-ai-coding](https://github.com/mattpocock/dictionary-of-ai-coding), which is the source of truth either way.
 - **Branches go in a table or a list, never in a paragraph.** Where the page presents a choice — two artifacts the skill can produce, four situations that trigger it, five options at a boundary — the reader is scanning for the one row that matches their situation. A paragraph makes them read all of it to find out. A short markdown table (condition in the left column, what to do in the right) or a bulleted list gives it back in one glance. This applies wherever the branch appears, most often in `## When to reach for it` and the free-form middle.
 - Keep the page itself low-load. It is documentation *about* low-cognitive-load skills; furniture (spare headings, restated links) is the thing it is arguing against.
 
@@ -85,6 +86,7 @@ Always present. Situate the skill in the system in a sentence or two:
 - `## Where it fits` names the role and links to `ask-matt`.
 - A prerequisite (workspace, prior setup, tooling) is stated where one exists, and the section is absent where none does.
 - The middle surfaces the leading word.
+- Every AI Coding Dictionary term the page uses is spelt the dictionary's way, and its first use — and only its first use — links to the dictionary entry.
 - Every multi-way branch is a table or a list, not a paragraph the reader has to read in full.
 - The hunt for real questions ran — the wiki, the issues, the changelog — and `## Common questions` is sized to what it found, not padded to match a richer skill's page.
 - Every `## It's working if` bullet is checkable without opening `SKILL.md`.
 
@@ -1,8 +1,8 @@
 ## What it does
 
-`ask-matt` is the router over the skills in this repo. You describe the situation you are in — an idea you cannot start, a pile of incoming bug reports, a session that has run long — and it names the skill or the sequence of skills that fits, plus where the human decisions in that sequence sit.
+`ask-matt` is the router over the skills in this repo. You describe the situation you are in — an idea you cannot start, a pile of incoming bug reports, a [session](https://www.aihero.dev/ai-coding-dictionary/session) that has run long — and it names the skill or the sequence of skills that fits, plus where the human decisions in that sequence sit.
 
-It recommends and stops. It does not grill, write a spec, open a file or fire the skill it just named; what you get back is the next thing to type, and you type it. It is also a hand-written map of the skills in this repo rather than a scan of what you have installed, so it will not route you over your own skills or another author's.
+It recommends and stops. It does not grill, write a [spec](https://www.aihero.dev/ai-coding-dictionary/spec), open a file or fire the skill it just named; what you get back is the next thing to type, and you type it. It is also a hand-written map of the skills in this repo rather than a scan of what you have installed, so it will not route you over your own skills or another author's.
 
 ## When to reach for it
 
@@ -11,9 +11,9 @@ You invoke this by typing `/ask-matt` — the agent won't reach for it on its ow
 | Your situation | What the router gives back |
 | --- | --- |
 | An idea, and no idea where to start | The head of the main flow, and whether the build is small enough to skip the spec |
-| Bugs and requests arriving from other people | The [triage](https://aihero.dev/skills-triage) on-ramp, and why tickets you generated yourself don't belong on it |
+| Bugs and requests arriving from other people | The [triage](https://aihero.dev/skills-triage) on-ramp, and why [tickets](https://www.aihero.dev/ai-coding-dictionary/ticket) you generated yourself don't belong on it |
 | Two skills that look interchangeable | The line between them, and it is usually one concrete test rather than a matter of taste. [grill-me](https://aihero.dev/skills-grill-me) or [grill-with-docs](https://aihero.dev/skills-grill-with-docs) turns on whether you are in a working directory; [grill-with-docs](https://aihero.dev/skills-grill-with-docs) or [wayfinder](https://aihero.dev/skills-wayfinder) turns on whether the effort fits one session |
-| A long session and a decision about the context | The ordered tree over the five options at a phase boundary |
+| A long session and a decision about the [context](https://www.aihero.dev/ai-coding-dictionary/context) | The ordered tree over the five options at a phase boundary |
 | A skill you have already picked | Nothing useful. Invoke that skill directly. |
 
 ## Prerequisites
@@ -33,14 +33,14 @@ The word the skill gives you to think with is **flow**: a path *through* the ski
 
 ## The phase boundary
 
-The other idea it hands you is the **phase boundary**. A phase is a chunk of work inside a session — the grilling, the implementation, the QA — and the boundary between two of them is the only place the question "what do I do with this context?" belongs. Mid-phase there is nothing to decide: continue, or split what is left into subagents.
+The other idea it hands you is the **phase boundary**. A phase is a chunk of work inside a session — the [grilling](https://www.aihero.dev/ai-coding-dictionary/grilling), the implementation, the QA — and the boundary between two of them is the only place the question "what do I do with this context?" belongs. Mid-phase there is nothing to decide: continue, or split what is left into [subagents](https://www.aihero.dev/ai-coding-dictionary/subagent).
 
 | Option | Take it when |
 | --- | --- |
-| **Continue** | The next phase wants this one verbatim, or you have smart zone left. It is the only move that keeps the session as a primary source, so rule it out first |
+| **Continue** | The next phase wants this one verbatim, or you have [smart zone](https://www.aihero.dev/ai-coding-dictionary/smart-zone) left. It is the only move that keeps the session as a [primary source](https://www.aihero.dev/ai-coding-dictionary/primary-source), so rule it out first |
 | **`/clear`** | Everything behind you is disposable. Cheapest move on the board, and one-way if you were wrong |
-| **[handoff](https://aihero.dev/skills-handoff)** | Something has to travel: a new harness, a new directory, a colleague, a side task forked mid-phase |
-| **Subagent** | The task is scoped tightly enough to run with you away from the keyboard |
+| **[handoff](https://aihero.dev/skills-handoff)** | Something has to travel: a new [harness](https://www.aihero.dev/ai-coding-dictionary/harness), a new directory, a colleague, a side task forked mid-phase |
+| **Subagent** | The task is scoped tightly enough to run with you [away from the keyboard](https://www.aihero.dev/ai-coding-dictionary/afk) |
 | **`/compact`** | None of the above. The default, and it lands here often |
 
 Two of those are routinely got wrong, which is why the router carries the order rather than the list. `/handoff` reads like the general bridge between windows and is not: portability is the whole of what it buys. `/compact` is the bottom of the tree rather than the first reach, because the four questions above it are each cheaper or more precise.
@@ -57,7 +57,7 @@ A known bug, unfixed. Most of the skills the router routes you through set `disa
 
 **It described a skill's behaviour, and the skill doesn't do that.**
 
-Also real, also unfixed. The router answers from its own one-line summary of each skill rather than from the skill. One detailed report tracked three instances in a single session, including a recommendation to skip [to-spec](https://aihero.dev/skills-to-spec) on the strength of the gloss "turn the thread into a spec" — `to-spec/SKILL.md` was never opened. In every case it verified only after the user pushed back, and never on its own initiative. Skipping `to-spec` there cost a real seam check, and the tickets that came out undercounted the work. When the router asserts something load-bearing about another skill, ask it to open that `SKILL.md` first. The same applies to questions the map does not cover at all, such as whether to use plan mode: that answer is the model's inference, not something written down here.
+Also real, also unfixed. The router answers from its own one-line summary of each skill rather than from the skill. One detailed report tracked three instances in a single session, including a recommendation to skip [to-spec](https://aihero.dev/skills-to-spec) on the strength of the gloss "turn the thread into a spec" — `to-spec/SKILL.md` was never opened. In every case it verified only after the user pushed back, and never on its own initiative. Skipping `to-spec` there cost a real seam check, and the tickets that came out undercounted the work. When the router asserts something load-bearing about another skill, ask it to open that `SKILL.md` first. The same applies to questions the map does not cover at all, such as whether to use [plan mode](https://www.aihero.dev/ai-coding-dictionary/agent-mode): that answer is the [model](https://www.aihero.dev/ai-coding-dictionary/model)'s inference, not something written down here.
 
 **Why is it prose instead of a numbered checklist?**
 
@@ -87,4 +87,4 @@ Check the changelog for a rename before assuming it is gone. `writing-great-skil
 
 `ask-matt` is a **standalone router** that sits over the whole set. It is never a step in a chain; it points into every chain, and it is the node the other docs pages link back to so none of them has to redraw the graph. From here you most often land on [grill-with-docs](https://aihero.dev/skills-grill-with-docs), the head of the main flow, or [triage](https://aihero.dev/skills-triage), the on-ramp for work that arrived rather than work you started.
 
-It is a secondary source over the skills it describes. Where the router and a `SKILL.md` disagree, the `SKILL.md` is right.
+It is a [secondary source](https://www.aihero.dev/ai-coding-dictionary/secondary-source) over the skills it describes. Where the router and a `SKILL.md` disagree, the `SKILL.md` is right.
@@ -1,8 +1,8 @@
 ## What it does
 
-`code-review` reviews the diff between `HEAD` and a fixed point you name — a commit, a branch, a tag, `main`, `HEAD~5` — along two axes. **Standards** asks whether the code follows how this repo writes code. **Spec** asks whether the code does what the originating issue or spec asked for. Each axis runs in its own sub-agent so neither sees the other's reasoning.
+`code-review` reviews the diff between `HEAD` and a fixed point you name — a commit, a branch, a tag, `main`, `HEAD~5` — along two axes. **Standards** asks whether the code follows how this repo writes code. **Spec** asks whether the code does what the originating issue or [spec](https://www.aihero.dev/ai-coding-dictionary/spec) asked for. Each axis runs in its own [sub-agent](https://www.aihero.dev/ai-coding-dictionary/subagent) so neither sees the other's reasoning.
 
-The two axes are never merged and never re-ranked. The report ends with a worst issue *per axis* and refuses to name a single winner across them, because a change can pass one axis and fail the other: code that follows every convention while implementing the wrong thing passes Standards and fails Spec; code that does exactly what the ticket asked while breaking the repo's conventions does the reverse. A blended verdict lets the passing axis hide the failing one.
+The two axes are never merged and never re-ranked. The report ends with a worst issue *per axis* and refuses to name a single winner across them, because a change can pass one axis and fail the other: code that follows every convention while implementing the wrong thing passes Standards and fails Spec; code that does exactly what the [ticket](https://www.aihero.dev/ai-coding-dictionary/ticket) asked while breaking the repo's conventions does the reverse. A blended verdict lets the passing axis hide the failing one.
 
 ## When to reach for it
 
@@ -41,21 +41,21 @@ Step 1 depends on `docs/agents/issue-tracker.md`, which [setup-matt-pocock-skill
 | Reports | Documented breaches (can be hard), and smells (always judgement calls) | Missing or partial requirements, scope creep, requirements implemented wrongly |
 | Every finding cites | The standards file and the rule, or the named smell plus the hunk | The line of the spec |
 
-A generic review skill that does not know your standards is the thing this design is trying to avoid — it flags what is deliberate in your codebase and misses the invariants your codebase actually depends on. So the repo's own documentation is the primary source on the Standards axis, and **the repo always overrides**.
+A generic review skill that does not know your standards is the thing this design is trying to avoid — it flags what is deliberate in your codebase and misses the invariants your codebase actually depends on. So the repo's own documentation is the [primary source](https://www.aihero.dev/ai-coding-dictionary/primary-source) on the Standards axis, and **the repo always overrides**.
 
 The **smell baseline** is the floor underneath it: twelve Fowler code smells from _Refactoring_ ch.3 — Mysterious Name, Duplicated Code, Feature Envy, Data Clumps, Primitive Obsession, Repeated Switches, Shotgun Surgery, Divergent Change, Speculative Generality, Message Chains, Middle Man, Refused Bequest. Each is a labelled heuristic ("possible Feature Envy"), never a hard violation, and each is stated as *what it is* → *how to fix*, so a finding arrives with a move attached rather than a complaint. Anything your linter already enforces is skipped by both axes.
 
 ## Common questions
 
 **It collides with Claude Code's own `/code-review`. What do I do?**
 
-This is the most reported problem with the skill, and it is not fixed. Claude Code ships its own `/code-review`, which does something different — it hunts bugs in the diff, where this one checks spec compliance and repo standards. Installing this library means one of them wins, and which one wins depends on how you installed. Via the plugin marketplace, everything is aliased under a `mattpocock-skills:` prefix and the built-in becomes hard to reach at the unqualified name; via a plain skills install, the local file wins and this skill shadows the built-in. Matt's own answer is that he removes Claude Code's built-in skills entirely — "Huge context saving and means I don't need to worry about this. I consider the shadowing issue a CC harness bug, I should be free to name my skills whatever." His advice to anyone hitting it has been to rename his copy locally. Editing the frontmatter or renaming the directory gets undone by `npx skills update`; the durable workaround reported by users is to fork the skill to a new name and drop `code-review` from the managed set, keeping a note of the commit you forked from so you can re-sync by hand.
+This is the most reported problem with the skill, and it is not fixed. Claude Code ships its own `/code-review`, which does something different — it hunts bugs in the diff, where this one checks spec compliance and repo standards. Installing this library means one of them wins, and which one wins depends on how you installed. Via the plugin marketplace, everything is aliased under a `mattpocock-skills:` prefix and the built-in becomes hard to reach at the unqualified name; via a plain skills install, the local file wins and this skill shadows the built-in. Matt's own answer is that he removes Claude Code's built-in skills entirely — "Huge [context](https://www.aihero.dev/ai-coding-dictionary/context) saving and means I don't need to worry about this. I consider the shadowing issue a CC [harness](https://www.aihero.dev/ai-coding-dictionary/harness) bug, I should be free to name my skills whatever." His advice to anyone hitting it has been to rename his copy locally. Editing the frontmatter or renaming the directory gets undone by `npx skills update`; the durable workaround reported by users is to fork the skill to a new name and drop `code-review` from the managed set, keeping a note of the commit you forked from so you can re-sync by hand.
 
 **Its sub-agents keep invoking `/code-review` again and spawn more agents.**
 
 Known open bug, reproduced by several people and in more than one harness. The Standards and Spec prompts do not forbid delegation, so a sub-agent can rediscover the skill and fan out again — one report reached 50-plus agents. The fix people have applied on forks is one line appended to both sub-agent briefs: "Do not invoke `/code-review` or spawn additional agents — perform this review directly." Some prefer to handle it at the harness level so every skill inherits the guard. Neither is in the shipped skill yet. If you run this unattended, watch the agent count.
 
-**Should I run it in the same session that wrote the code?**
+**Should I run it in the same [session](https://www.aihero.dev/ai-coding-dictionary/session) that wrote the code?**
 
 Prefer a fresh one. As one reader put it: "Same context reviewing itself isn't review, it's confirmation bias with a slash command." The reviewing agent in the authoring session holds every assumption that shaped the code, which is exactly the context an independent reviewer would not have. This is also why people ask for [implement](https://aihero.dev/skills-implement) without its built-in review step — it runs the review inside the session that just wrote the diff. Invoking `/code-review` yourself from a clean session is the honest version.