@amsterdamdatalabs/enact-extensions 0.1.37 → 0.1.47

package/extensions/enact-repo/skills/backend-remove-deadcode/SKILL.md

@@ -0,0 +1,96 @@
+---
+name: backend-remove-deadcode
+description: Remove explicitly enumerated dead Rust symbols from backend/crates only after repository-specific false-positive guards, fresh graph evidence, zero-reference proof, and focused tests pass. Use for an approved dead-code cleanup plan, not broad refactoring.
+disable-model-invocation: false
+---
+
+# Backend dead-code removal
+
+Delete only candidates named by an active plan. Candidate inventories, current
+line numbers, dispositions, blockers, and test run IDs belong in that plan,
+never in this skill.
+
+## Use When
+
+- An approved dead-code cleanup plan names specific Rust symbols in `backend/crates`, and each one needs false-positive guards, fresh graph evidence, and zero-reference proof before deletion.
+
+## Do Not Use When
+
+- No active, approved plan names the candidate symbols — a graph or scanner count alone is not authorization to delete.
+- The work is broad refactoring, feature revival, or touches code outside `backend/crates` (non-Rust code, donors).
+
+## Preconditions
+
+1. Run git status and preserve unrelated work.
+2. Run crg status. Use graph evidence only when its branch and commit match the
+   current checkout.
+3. Read the active plan and enumerate the exact symbols and files in the
+   current cluster.
+4. Search every symbol with:
+
+       rg -n "<Symbol>" backend/crates --no-ignore -g '*.rs' -g '!target/**'
+
+5. Read the definition, all hits, crate exports, entry points, and relevant
+   tests before deciding.
+
+A graph dead-code result is a candidate generator, never deletion proof.
+
+## False-positive guards
+
+Reject or escalate a candidate when it is:
+
+- a serde, wire, database, configuration, plugin, or manifest type reachable
+  through data rather than a Rust call edge;
+- test-only support behind tests, cfg(test), or a test-support feature;
+- SQL DDL under schema/postgres/ or schema/migrations/postgres/;
+- a same-named symbol whose text hits cannot distinguish paths;
+- a trait, trait method, impl, macro input, derive target, or public re-export;
+- reachable through route registration, dependency injection, factory
+  dispatch, command tables, inventory/linker registration, or feature-gated
+  binaries;
+- referenced by build.rs, examples, benches, generated code, scripts, or
+  external protocol names;
+- owned for revival or wiring by another active plan.
+
+Fog of war is a keep decision. Do not turn plausible deadness into deletion.
+
+## Per-symbol proof
+
+A symbol may be deleted only when all are true:
+
+- the fresh graph has no live caller or construction edge relevant to the
+  symbol kind;
+- rg finds no live use outside the definition and deletion-owned code;
+- entry-point and re-export review finds no dynamic reachability;
+- serialization/configuration/protocol review finds no name-based reachability;
+- no active plan or specification owns future wiring;
+- the deletion leaves no dead imports, match arms, modules, or public exports.
+
+Record the commands, disposition, and exact source revision in the active plan.
+
+## Cluster execution
+
+Keep each cluster narrow enough to verify independently:
+
+1. remove the proven symbols and deletion-owned residue;
+2. format only affected Rust files;
+3. run the smallest affected crate batch through the repository guard:
+
+       cd backend && just test-batch -p <affected-crate>...
+
+4. read .enact/test-batch/<run-id>/summary.json;
+5. run the owning repository phase selected by the changed files;
+6. update the active plan with deleted, retained, reclassified, and blocked
+   counts plus command evidence.
+
+A red batch means the cluster is not complete. Diagnose it; do not weaken tests,
+hide the failure, or claim a partial deletion green.
+
+## Hygiene boundaries
+
+- Do not bulk-delete from a scanner count.
+- Do not delete tested code to improve coverage.
+- Do not combine deletion with refactoring or feature revival.
+- Do not store cleanup status under .agents/skill-catalog/.
+- Do not touch donors.
+- Do not commit or push without explicit authorization.

package/extensions/enact-repo/skills/cmux-leader/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: cmux-leader
+description: Coordinate parallel cmux follower sessions across independent repository scopes.
+disable-model-invocation: true
+---
+
+# Cmux Leader
+
+## Purpose
+
+Lead parallel follower sessions from a neutral directory. The leader shards, briefs, polls, verifies, and closes work; followers perform the assigned work.
+
+## Use When
+
+- Independent work can run in separate repositories or sibling worktrees.
+- A leader must coordinate up to five cmux follower sessions.
+
+## Do Not Use When
+
+- Two workers must change the same checkout; split the work or create sibling worktrees first.
+- Only one message needs delivery; use `cmux-send`.
+
+## Workflow
+
+1. Lead from the common parent directory; inspect follower repositories with `git -C <path>`, not a persistent `cd`.
+2. Shard only independent work. Give each shared-repository worker a sibling worktree, never a nested worktree.
+3. Create a follower on demand, then verify its cwd before launching its agent:
+   ```bash
+   cmux new-split right --focus false
+   cmux send --surface surface:N "cd /abs/repo && pwd\n"
+   cmux read-screen --surface surface:N --lines 5
+   ```
+4. Brief each follower with scope, exit criteria, and `cmux-send` reply envelope.
+5. Poll topology and screens, unblock parked followers, compact high-context sessions, and close completed followers.
+6. Verify tests, builds, and PR state yourself before accepting a follower result.
+
+## Output
+
+Keep a concise shard map: follower, repository/worktree, scope, status, evidence, and next action.
+
+## State Contract
+
+Creates and closes cmux surfaces; may create sibling worktrees. Does not implement follower work or record board assignments.
+
+## Boundaries
+
+### In scope
+
+Independent sharding, rooted follower launch, briefing, polling, unblocking, and evidence-based coordination.
+
+### Out of scope
+
+Message mechanics belong to `cmux-send`; detached board assignments belong to `handoff`; implementation belongs to the follower.
+
+### Fog of war
+
+Stop and clarify overlapping ownership. Treat a parked or silent follower as blocked when the send protocol does not clear it.
+
+## Completion
+
+Verify every completed follower with `node -e "process.exit(0)"` only after its `cmux read-screen --surface surface:N --lines 20` output and repository gate are attached.

package/extensions/enact-repo/skills/cmux-send/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: cmux-send
+description: Send and verify a message between cmux leader and follower surfaces.
+disable-model-invocation: false
+---
+
+# Cmux Send
+
+## Purpose
+
+Deliver one complete, attributable line to a cmux surface and prove it left the compose box.
+
+## Use When
+
+- A leader or follower must send a status, question, or briefing through cmux.
+- A parked message must be submitted and verified.
+
+## Do Not Use When
+
+- Choosing message content, scheduling followers, or verifying implementation; use `cmux-leader`.
+- The target surface label cannot be resolved.
+
+## Workflow
+
+1. Resolve labels with `cmux list-pane-surfaces [--pane pane:N]`.
+2. Send one line with `[<from>] to [<to>] ` prefix and the required reply prefix at the end.
+3. Submit two Enter keys, then `ctrl+b`, then inspect the compose box:
+   ```bash
+   cmux send --surface surface:N "[FROM] to [TO] <message>. Respond back once done using prefix \"[TO] to [FROM] \"\n"
+   cmux send-key --surface surface:N enter
+   cmux send-key --surface surface:N enter
+   cmux send-key --surface surface:N ctrl+b
+   cmux read-screen --surface surface:N --lines 6
+   ```
+4. Retry the Enter pair once if text remains. Report the surface as stuck if it still remains.
+
+## Output
+
+Report target surface, envelope, whether the compose box was empty, and any retry.
+
+## State Contract
+
+Writes keystrokes to one cmux surface and reads its screen. Does not decide workflow or interpret the reply.
+
+## Boundaries
+
+### In scope
+
+One-line message envelope, two-Enter submission, `ctrl+b` flush, and empty-compose-box verification.
+
+### Out of scope
+
+Follower orchestration and content decisions belong to `cmux-leader`.
+
+### Fog of war
+
+Re-discover panes when a human label is absent; do not guess a surface number.
+
+## Completion
+
+Run `node -e "process.exit(0)"` only after `cmux read-screen --surface surface:N --lines 6` shows an empty compose box.

package/extensions/enact-repo/skills/code-review/SKILL.md

@@ -0,0 +1,100 @@
+---
+name: code-review
+description: Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
+disable-model-invocation: false
+---
+
+# Code Review
+Two-axis review of the diff between `HEAD` and a fixed point the user supplies:
+
+- **Standards** — does the code conform to this repo's documented coding standards?
+- **Spec** — does the code faithfully implement the originating issue / PRD / spec?
+
+Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings.
+
+## Use When
+
+- The user wants to review a branch, a PR, or work-in-progress changes against a fixed point.
+- The user asks to "review since X" (a commit, branch, tag, or merge-base).
+
+## Do Not Use When
+
+- There is no fixed point to diff against and the user won't supply one (pin one first, see Process step 1), or the work isn't implemented yet so there's no diff to review — use `implement` first.
+
+The issue tracker should have been provided to you — run `/setup-matt-pocock-skills` if `docs/agents/issue-tracker.md` is missing.
+
+## Process
+
+### 1. Pin the fixed point
+
+Whatever the user said is the fixed point — a commit SHA, branch name, tag, `main`, `HEAD~5`, etc. If they didn't specify one, ask for it.
+
+Capture the diff command once: `git diff <fixed-point>...HEAD` (three-dot, so the comparison is against the merge-base). Also note the list of commits via `git log <fixed-point>..HEAD --oneline`.
+
+Before going further, confirm the fixed point resolves (`git rev-parse <fixed-point>`) and the diff is non-empty. A bad ref or empty diff should fail here — not inside two parallel sub-agents.
+
+### 2. Identify the spec source
+
+Look for the originating spec, in this order:
+
+1. Issue references in the commit messages (`#123`, `Closes #45`, GitLab `!67`, etc.) — fetch via the workflow in `docs/agents/issue-tracker.md`.
+2. A path the user passed as an argument.
+3. A PRD/spec file under `docs/`, `specs/`, or `.enact/` matching the branch name or feature.
+4. If nothing is found, ask the user where the spec is. If they say there isn't one, the **Spec** sub-agent will skip and report "no spec available".
+
+### 3. Identify the standards sources
+
+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.
+
+**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 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."
+
+**Spec sub-agent prompt** — include:
+
+- The diff command and commit list.
+- The path or fetched contents of the spec.
+- The brief: "Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line for each finding. Under 400 words."
+
+If the spec is missing, skip the Spec sub-agent and note this in the final report.
+
+### 5. Aggregate
+
+Present the two reports under `## Standards` and `## Spec` headings, verbatim or lightly cleaned. Do **not** merge or rerank findings — the two axes are deliberately separate (see _Why two axes_).
+
+End with a one-line summary: total findings per axis, and the worst issue _within each axis_ (if any). Don't pick a single winner across axes — that's the reranking the separation exists to prevent.
+
+## Why two axes
+
+A change can pass one axis and fail the other:
+
+- Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.**
+- Code that does exactly what the issue asked but breaks the project's conventions → **Spec pass, Standards fail.**
+
+Reporting them separately stops one axis from masking the other.

package/extensions/enact-repo/skills/codebase-design/SKILL.md

@@ -0,0 +1,98 @@
+---
+name: codebase-design
+description: Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
+disable-model-invocation: false
+---
+
+# Codebase Design
+
+Design **deep modules**: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface. Use this language and these principles wherever code is being designed or restructured. The aim is reach for callers, locality for maintainers, and testability for everyone.
+
+## Use When
+
+- Designing or reviewing a module's interface, deciding where a seam should go, or hunting for deepening opportunities.
+- Making code more testable or AI-navigable, or another skill needs the deep-module vocabulary (module, interface, depth, seam, adapter).
+
+## Do Not Use When
+
+- There is no interface or seam decision to make — a pure data fix, a copy change, or a config tweak with no module boundary involved.
+
+## Glossary
+
+Use these terms exactly — don't substitute "component," "service," "API," or "boundary." Consistent language is the whole point.
+
+**Module** — anything with an interface and an implementation. Deliberately scale-agnostic: a function, class, package, or tier-spanning slice. _Avoid_: unit, component, service.
+
+**Interface** — everything a caller must know to use the module correctly: the type signature, but also invariants, ordering constraints, error modes, required configuration, and performance characteristics. _Avoid_: API, signature (too narrow — they refer only to the type-level surface).
+
+**Implementation** — what's inside a module, its body of code. Distinct from **Adapter**: a thing can be a small adapter with a large implementation (a Postgres repo) or a large adapter with a small implementation (an in-memory fake). Reach for "adapter" when the seam is the topic; "implementation" otherwise.
+
+**Depth** — reach at the interface: the amount of behaviour a caller (or test) can exercise per unit of interface they have to learn. A module is **deep** when a large amount of behaviour sits behind a small interface, **shallow** when the interface is nearly as complex as the implementation.
+
+**Seam** _(Michael Feathers)_ — a place where you can alter behaviour without editing in that place; the *location* at which a module's interface lives. Where to put the seam is its own design decision, distinct from what goes behind it. _Avoid_: boundary (overloaded with DDD's bounded context).
+
+**Adapter** — a concrete thing that satisfies an interface at a seam. Describes *role* (what slot it fills), not substance (what's inside).
+
+**Reach** — what callers get from depth: more capability per unit of interface they learn. One implementation pays back across N call sites and M tests.
+
+**Locality** — what maintainers get from depth: change, bugs, knowledge, and verification concentrate in one place rather than spreading across callers. Fix once, fixed everywhere.
+
+## Deep vs shallow
+
+**Deep module** = small interface + lots of implementation:
+
+```
+┌─────────────────────┐
+│   Small Interface   │  ← Few methods, simple params
+├─────────────────────┤
+│                     │
+│  Deep Implementation│  ← Complex logic hidden
+│                     │
+└─────────────────────┘
+```
+
+**Shallow module** = large interface + little implementation (avoid):
+
+```
+┌─────────────────────────────────┐
+│       Large Interface           │  ← Many methods, complex params
+├─────────────────────────────────┤
+│  Thin Implementation            │  ← Just passes through
+└─────────────────────────────────┘
+```
+
+When designing an interface, ask:
+
+- Can I reduce the number of methods?
+- Can I simplify the parameters?
+- Can I hide more complexity inside?
+
+## Principles
+
+- **Depth is a property of the interface, not the implementation.** A deep module can be internally composed of small, mockable, swappable parts — they just aren't part of the interface. A module can have **internal seams** (private to its implementation, used by its own tests) as well as the **external seam** at its interface.
+- **The deletion test.** Imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
+- **The interface is the test surface.** Callers and tests cross the same seam. If you want to test *past* the interface, the module is probably the wrong shape.
+- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a seam unless something actually varies across it.
+
+## Designing for testability
+
+Good interfaces make testing natural: accept dependencies instead of creating them, return results instead of producing side effects, and keep the surface small. See [references/TESTABILITY.md](references/TESTABILITY.md) for the three practices with testable/hard-to-test code examples.
+
+## Relationships
+
+- A **Module** has exactly one **Interface** (the surface it presents to callers and tests).
+- **Depth** is a property of a **Module**, measured against its **Interface**.
+- A **Seam** is where a **Module**'s **Interface** lives.
+- An **Adapter** sits at a **Seam** and satisfies the **Interface**.
+- **Depth** produces **Reach** for callers and **Locality** for maintainers.
+
+## Rejected framings
+
+- **Depth as ratio of implementation-lines to interface-lines** (Ousterhout): rewards padding the implementation. We use depth-as-reach instead.
+- **"Interface" as the TypeScript `interface` keyword or a class's public methods**: too narrow — interface here includes every fact a caller must know.
+- **"Boundary"**: overloaded with DDD's bounded context. Say **seam** or **interface**.
+
+## Going deeper
+
+- **Deepening a cluster given its dependencies** — see [references/DEEPENING.md](references/DEEPENING.md): dependency categories, seam discipline, and replace-don't-layer testing.
+- **Exploring alternative interfaces** — see [references/DESIGN-IT-TWICE.md](references/DESIGN-IT-TWICE.md): spin up parallel sub-agents to design the interface several radically different ways, then compare on depth, locality, and seam placement.

package/extensions/enact-repo/skills/codebase-design/references/DEEPENING.md

@@ -0,0 +1,37 @@
+# Deepening
+
+How to deepen a cluster of shallow modules safely, given its dependencies. Assumes the vocabulary in [SKILL.md](SKILL.md) — **module**, **interface**, **seam**, **adapter**.
+
+## Dependency categories
+
+When assessing a candidate for deepening, classify its dependencies. The category determines how the deepened module is tested across its seam.
+
+### 1. In-process
+
+Pure computation, in-memory state, no I/O. Always deepenable — merge the modules and test through the new interface directly. No adapter needed.
+
+### 2. Local-substitutable
+
+Dependencies that have local test stand-ins (PGLite for Postgres, in-memory filesystem). Deepenable if the stand-in exists. The deepened module is tested with the stand-in running in the test suite. The seam is internal; no port at the module's external interface.
+
+### 3. Remote but owned (Ports & Adapters)
+
+Your own services across a network boundary (microservices, internal APIs). Define a **port** (interface) at the seam. The deep module owns the logic; the transport is injected as an **adapter**. Tests use an in-memory adapter. Production uses an HTTP/gRPC/queue adapter.
+
+Recommendation shape: *"Define a port at the seam, implement an HTTP adapter for production and an in-memory adapter for testing, so the logic sits in one deep module even though it's deployed across a network."*
+
+### 4. True external (Mock)
+
+Third-party services (Stripe, Twilio, etc.) you don't control. The deepened module takes the external dependency as an injected port; tests provide a mock adapter.
+
+## Seam discipline
+
+- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a port unless at least two adapters are justified (typically production + test). A single-adapter seam is just indirection.
+- **Internal seams vs external seams.** A deep module can have internal seams (private to its implementation, used by its own tests) as well as the external seam at its interface. Don't expose internal seams through the interface just because tests use them.
+
+## Testing strategy: replace, don't layer
+
+- Old unit tests on shallow modules become waste once tests at the deepened module's interface exist — delete them.
+- Write new tests at the deepened module's interface. The **interface is the test surface**.
+- Tests assert on observable outcomes through the interface, not internal state.
+- Tests should survive internal refactors — they describe behaviour, not implementation. If a test has to change when the implementation changes, it's testing past the interface.

package/extensions/enact-repo/skills/codebase-design/references/DESIGN-IT-TWICE.md

@@ -0,0 +1,44 @@
+# Design It Twice
+
+When the user wants to explore alternative interfaces for a chosen deepening candidate, use this parallel sub-agent pattern. Based on "Design It Twice" (Ousterhout) — your first idea is unlikely to be the best.
+
+Uses the vocabulary in [SKILL.md](SKILL.md) — **module**, **interface**, **seam**, **adapter**, **reach**.
+
+## Process
+
+### 1. Frame the problem space
+
+Before spawning sub-agents, write a user-facing explanation of the problem space for the chosen candidate:
+
+- The constraints any new interface would need to satisfy
+- The dependencies it would rely on, and which category they fall into (see [DEEPENING.md](DEEPENING.md))
+- A rough illustrative code sketch to ground the constraints — not a proposal, just a way to make the constraints concrete
+
+Show this to the user, then immediately proceed to Step 2. The user reads and thinks while the sub-agents work in parallel.
+
+### 2. Spawn sub-agents
+
+Spawn 3+ sub-agents in parallel using the Agent tool. Each must produce a **radically different** interface for the deepened module.
+
+Prompt each sub-agent with a separate technical brief (file paths, coupling details, dependency category from [DEEPENING.md](DEEPENING.md), what sits behind the seam). The brief is independent of the user-facing problem-space explanation in Step 1. Give each agent a different design constraint:
+
+- Agent 1: "Minimize the interface — aim for 1–3 entry points max. Maximise reach per entry point."
+- Agent 2: "Maximise flexibility — support many use cases and extension."
+- Agent 3: "Optimise for the most common caller — make the default case trivial."
+- Agent 4 (if applicable): "Design around ports & adapters for cross-seam dependencies."
+
+Include both [SKILL.md](SKILL.md) vocabulary and CONTEXT.md vocabulary in the brief so each sub-agent names things consistently with the architecture language and the project's domain language.
+
+Each sub-agent outputs:
+
+1. Interface (types, methods, params — plus invariants, ordering, error modes)
+2. Usage example showing how callers use it
+3. What the implementation hides behind the seam
+4. Dependency strategy and adapters (see [DEEPENING.md](DEEPENING.md))
+5. Trade-offs — where reach is high, where it's thin
+
+### 3. Present and compare
+
+Present designs sequentially so the user can absorb each one, then compare them in prose. Contrast by **depth** (reach at the interface), **locality** (where change concentrates), and **seam placement**.
+
+After comparing, give your own recommendation: which design you think is strongest and why. If elements from different designs would combine well, propose a hybrid. Be opinionated — the user wants a strong read, not a menu.

package/extensions/enact-repo/skills/codebase-design/references/TESTABILITY.md

@@ -0,0 +1,29 @@
+# Designing for Testability
+
+Good interfaces make testing natural:
+
+1. **Accept dependencies, don't create them.**
+
+   ```typescript
+   // Testable
+   function processOrder(order, paymentGateway) {}
+
+   // Hard to test
+   function processOrder(order) {
+     const gateway = new StripeGateway();
+   }
+   ```
+
+2. **Return results, don't produce side effects.**
+
+   ```typescript
+   // Testable
+   function calculateDiscount(cart): Discount {}
+
+   // Hard to test
+   function applyDiscount(cart): void {
+     cart.total -= discount;
+   }
+   ```
+
+3. **Small surface area.** Fewer methods = fewer tests needed. Fewer params = simpler test setup.

package/extensions/enact-repo/skills/computer-use/SKILL.md

@@ -0,0 +1,76 @@
+---
+name: computer-use
+description: >-
+  Use Orca's computer-use CLI to inspect and operate local desktop app windows
+  through accessibility trees, screenshots, and safe UI actions. Use for
+  desktop app interaction: list apps/windows, get app state, read visible UI,
+  click controls, type, press keys, scroll, drag, set values, or perform
+  accessibility actions. Also use for browser windows, webviews, Orca app UI,
+  or other desktop UI. Triggers include "computer use", "orca computer", "read
+  Spotify", "read Slack", "control/click/read in a desktop app", and "get app
+  state".
+disable-model-invocation: false
+---
+
+# Computer Use
+
+This file is a discovery stub, not the usage guide. The full, version-matched computer-use
+reference is served by the `orca` binary itself — kept out of this file on purpose so it can
+never drift from the binary that will actually run your commands.
+
+## Use When
+
+Inspecting or operating a local desktop app window — reading its accessibility
+tree, taking screenshots, or performing safe UI actions (click controls, type,
+press keys, scroll, drag, set values, or other accessibility actions). Also
+for browser windows, webviews, and Orca's own UI. Triggers include "computer
+use", "orca computer", "read Spotify", "read Slack", "control/click/read in a
+desktop app", and "get app state".
+
+## Do Not Use When
+
+The task touches Orca-managed state instead of desktop UI — worktrees, folder
+contexts, terminals, repos, automations, artifacts, skill sharing, worktree
+comments, or the browser embedded inside the Orca app — use `orca-cli`.
+Structured multi-agent coordination (threaded messages, task DAGs, decision
+gates, coordinator loops) — use `orchestration`.
+
+## Resolve the CLI for this session
+
+See `orca-cli`'s **Resolve the CLI for this session** section: it picks the
+executable once (`ORCA_CLI_COMMAND`, then `orca-dev`, then `orca-ide`, then
+`orca`) and defines the `ORCA` placeholder used below. Stop and report if the
+resolved executable cannot run — never fall through to a different one.
+
+## Load the full guide before running Orca commands
+
+```text
+ORCA skills get computer-use
+```
+
+That prints the complete, version-matched guide for the exact binary that will
+handle your next commands — listing apps/windows, reading UI, and driving
+clicks, typing, and other accessibility actions. Read it first, then run the
+specific command you need. This stub does not list computer-use subcommands or
+flags — they change between Orca releases, so do not guess them from memory or
+a cached copy of this file. Confirm the app is up with `ORCA status --json`
+(start it with `ORCA open --json` if needed), and prefer `--json` for
+agent-driven calls.
+
+## If an older Orca does not recognize `skills get`
+
+Use this fallback only when the selected binary explicitly reports `skills
+get` as an unknown command — another failure is not proof of an older binary;
+report it instead of guessing or changing executables. For a confirmed
+pre-guide binary, use only this bounded, read-only bootstrap to orient. Do not
+dead-end and do not invent commands:
+
+```text
+ORCA status --json
+ORCA computer capabilities --json
+ORCA computer list-apps --json
+```
+
+Then tell the user that updating Orca restores the full, version-matched guide
+via `ORCA skills get computer-use`. Beyond these commands, ask the user rather
+than guessing a command surface this older binary may not support.

package/extensions/enact-repo/skills/debug-issue/SKILL.md

@@ -0,0 +1,40 @@
+---
+name: debug-issue
+description: "Use when the user reports a bug, crash, stack trace, exception, error, or unexpected/broken behavior and wants the root cause traced through the code with graph-powered navigation. USE FOR: debug this, trace a crash, find the root cause, follow the call chain through callers and callees, trace an execution flow, investigate why something is failing, throwing, or broken, check whether a recent change caused a regression. DO NOT USE FOR: getting oriented with no known issue (use explore-codebase), reviewing a diff for merge readiness (use review-changes), or planning a fix once the cause is already known (use refactor-safely)."
+disable-model-invocation: false
+---
+
+# Debug Issue
+
+Use the knowledge graph to systematically trace and debug issues.
+
+## Use When
+
+Tracing the root cause of a reported bug or unexpected behavior through call
+chains, execution flows, and recent changes.
+
+## Do Not Use When
+
+There is no known issue to trace — use `explore-codebase` to get oriented
+instead. You are reviewing a diff for merge readiness — use `review-changes`.
+You already know the cause and are planning the fix — use `refactor-safely`.
+
+## Steps
+
+1. Use `semantic_search_nodes_tool` to find code related to the issue.
+2. Use `query_graph_tool` with `callers_of` and `callees_of` to trace call chains.
+3. Use `get_flow_tool` to see full execution paths through suspected areas.
+4. Run `detect_changes_tool` to check if recent changes caused the issue.
+5. Use `get_impact_radius_tool` on suspected files to see what else is affected.
+
+## Tips
+
+- Check both callers and callees to understand the full context.
+- Look at affected flows to find the entry point that triggers the bug.
+- Recent changes are the most common source of new issues.
+
+## Token Efficiency
+
+Trace efficiently using `explore-codebase`'s **Token Efficiency Rules** —
+start minimal, cap calls at 5 and output around 800 tokens, then verify the
+suspected cause against real source before proposing a fix.