@g3nomaly/g3n-skills 0.1.6 → 0.1.7

package/skills/g3n/analyze/references/commands.md

@@ -0,0 +1,54 @@
+# Commands
+
+| Command          | Does                                                   |
+| ---------------- | ------------------------------------------------------ |
+| `create_docs`    | Writes `analyze_out/index.html`, one offline HTML file |
+| `search <query>` | Finds nodes by words and by meaning                    |
+| `show <node>`    | Prints one node in full                                |
+| `refs <node>`    | Lists its edges, both ways                             |
+| `list`           | Lists nodes in display order                           |
+
+## Flags
+
+| Flag                             | Commands         | Does                                                     |
+| -------------------------------- | ---------------- | -------------------------------------------------------- |
+| `--repo <dir>`                   | all              | Repository to read. Default: the working directory       |
+| `--skills <dir>`, `--docs <dir>` | all              | Read skills or docs from this directory only. Repeatable |
+| `--exclude <glob>`               | all              | Skip matching paths. Repeatable                          |
+| `--no-embeddings`                | all              | No search by meaning                                     |
+| `--title <text>`                 | `create_docs`    | Site title                                               |
+| `--from <file>`                  | queries          | Query a built `index.html` instead of scanning           |
+| `--no-cache`                     | queries          | Scan again even when nothing changed                     |
+| `--json`                         | queries          | JSON instead of text                                     |
+| `--kind <kind>`                  | queries          | Only this kind. Repeatable                               |
+| `--section <name>`               | queries          | `skills`, `docs`, `code`, `database` or `tasks`          |
+| `-n, --limit <n>`                | `search`, `list` | Most results                                             |
+| `--by <way>`                     | `search`         | `name`, `meaning` or `both`                              |
+| `--incoming`, `--outgoing`       | `refs`           | One direction only                                       |
+| `--edge <kind>`                  | `refs`           | Only this edge kind. Repeatable                          |
+
+Each flag has an `ANALYZE_*` variable, such as `ANALYZE_REPO`. A flag wins over its variable.
+
+## Kinds
+
+- **Structure**: `folder`, `package`, `file`
+- **Code**: `namespace`, `class`, `interface`, `struct`, `enum`, `trait`, `type`, `function` (methods included)
+- **Docs and data**: `term`, `decision`, `table`, `query`
+- **Tasks**: `plan`, `phase`, `task`
+- **Members**, returned as their owner: `operation`, `definition`, `parameter`, `field`
+
+The JSON of a node has its `kind` and its `type`, the finer sort, such as `method` or `api`.
+
+## Edge kinds
+
+| Edge                | From → to                                              |
+| ------------------- | ------------------------------------------------------ |
+| `type`              | parameter or field → its type                          |
+| `returns`, `throws` | function → type it returns or throws                   |
+| `extends`           | type → type it extends or implements                   |
+| `mentions`          | page or description → node it links to                 |
+| `uses`              | text → glossary term                                   |
+| `affects`           | decision → node it is about                            |
+| `references`        | table → table of its foreign key                       |
+| `reads`, `writes`   | query → table                                          |
+| `names`, `depends`  | plan, phase or task → node it names, task it waits for |

package/skills/g3n/analyze/references/repository.md

@@ -0,0 +1,13 @@
+# What analyze reads
+
+| Shows as      | Write                                                                                                                                                                                                      |
+| ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Skill**     | A `SKILL.md` inside an AI directory: `.claude`, `.codex`, `.cursor`, `.gemini`, `.agents`, `.windsurf`, `.opencode`. Elsewhere it is a doc                                                                 |
+| **Package**   | A directory with a manifest: `package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod`, `pom.xml`, `build.gradle`, `composer.json`, `.csproj`, `.gemspec`, `Gemfile`. A declared executable makes it an app |
+| **Glossary**  | A `glossary.md`. Each term is a node, and its first use in any text links to it                                                                                                                            |
+| **Decisions** | A `decisions.md`. Each decision is a node; a link or inline code in it that names a node becomes an `affects` edge                                                                                         |
+| **Code docs** | Doc comments. `@param`, `@returns`, `@throws` and `@property` attach to the parameter, return value, error and field                                                                                       |
+| **Database**  | `.sql` files. One with `CREATE TABLE` is a schema, any other a query                                                                                                                                       |
+| **Tasks**     | The task-manager tree in `docs/task-manager`, or the directory `.g3n.config.json` names                                                                                                                    |
+
+Inline code that names a type or function, such as `` `choose_route` ``, links to it from any text.

package/skills/g3n/g3n-mods/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: g3n-mods
+description: Use when installing, updating or removing a Claude Code mod, registering a repository or folder of mods as a source, setting up the mods viewer, or when an installed mod looks missing or outdated.
+disable-model-invocation: false
+---
+
+Mods are installed with `@g3nomaly/mods`, never by copying mod folders by hand. In the g3n monorepo, run `bun packages/mods/dist/cli/index.js` in place of `bunx @g3nomaly/mods`, so the local build is used.
+
+## Steps
+
+1. **Pick the scope**: with `--user`, mods go to `~/.claude/` for every project; without it, to the project's `.claude/`, run from its git root. Check which `mods.json` lists the mod and pass `--user` to every command when it is the one in `~/.claude/`. Done when you know the scope.
+2. **Set up**, once per scope: `init` creates `mods.json`, and once per machine sets up the relay and the VS Code viewer. If another tool already set a process wrapper, `init --replace-wrapper` takes it over, and only when the user agrees. Done when `mods.json` exists. Sessions started before `init` need a restart to show in the viewer.
+3. **Look**: `ls` lists what the sources offer, `ls --installed` what is installed. Done when you know the mod's name.
+4. **Install**: `add <mod>`, `add <source>` for every mod of a source, or `add --all` for every mod of every source. When two sources offer a name, write `<mod>@<source>`. Done when the command reports each mod installed.
+5. **Update**: `update --dry-run`, then `update` for all or `update <mod>` for one. `add --all` also installs mods a source added since. Done when the dry run shows nothing left to change.
+6. **Resolve conflicts**: a conflict is an installed file that differs from what `mods.json` recorded. Pass `-f` only when the installed copy holds no change of the user's; otherwise stop and ask whether to restore, fork or skip. Done when no conflict is left.
+7. **Remove**: `remove <mod>`. Done when its folder and `mods.json` entry are gone.
+
+`add`, `update` and `remove` reload the mods in every running session. After the viewer itself was updated, the user runs **Developer: Reload Window**. A project-scope mod loads only once the workspace is trusted: run `claude` once in a terminal there, accept, then `/reload-plugins`.
+
+## Register a source
+
+The built-in source `g3n-mods` needs no registering and cannot be removed. Register any other source with `source add`:
+
+| Source               | Command                                                     |
+| -------------------- | ----------------------------------------------------------- |
+| GitHub repository    | `source add owner/repo`                                     |
+| Other git repository | `source add <URL>`, with `--ref <branch or tag>` to pin one |
+| npm package          | `source add npm:<package>`                                  |
+| Local folder         | `source add ./my-mods --name mine`                          |
+
+`source ls` lists the sources and `source remove <name>` drops one. `source add -f` points a registered name somewhere else, and its installed mods then update from there. A source lists its mods in `.claude-plugin/marketplace.json`; without one, it is read as one mod or as a folder of mods under `mods/`. A mod is a plugin folder with `.claude-plugin/plugin.json` and `hooks/hooks.json`, named like its plugin. Mods are TypeScript only: a mod with any `.js`, `.mjs`, `.cjs` or `.jsx` file is refused.

package/skills/g3n/g3n-mods/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "G3n Mods"
+  short_description: "Install, update and remove Claude Code mods with @g3nomaly/mods"
+policy:
+  allow_implicit_invocation: true

package/skills/g3n/g3n-skills/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: g3n-skills
+description: Use when installing, updating or removing a skill, registering a repository or folder of skills as a source, or when an installed skill looks missing or outdated.
+disable-model-invocation: false
+---
+
+Skills are installed with `@g3nomaly/skills`, never by copying or editing skill folders by hand. Run every command from the project's git root. In the g3n monorepo, run `bun packages/skills/dist/cli/index.js` in place of `bunx @g3nomaly/skills`, so the local build is used.
+
+## Steps
+
+1. **Set up**, once per project: `bunx @g3nomaly/skills init` picks Claude Code, Codex or both; `--targets claude,codex` skips the prompt. Without it, skills go to Claude Code only. Done when `.g3n.config.json` exists, or the project only needs Claude Code.
+2. **Look**: `ls` lists what the sources offer, `ls --installed` what is installed, `ls --source <name>` one source. Done when you know each name and whether it is a skill or a group.
+3. **Install**: `add <name>` installs a skill or a whole group, with every skill it depends on. When two sources offer a name, write `<name>@<source>`. Done when the command reports each skill installed.
+4. **Update**: `update --dry-run`, then `update` for all or `update <skill>` for one. A skill that gained a dependency is reported; install it with `add`. Done when the dry run shows nothing left to change.
+5. **Resolve conflicts**: a conflict is an installed file that differs from what `skills.json` recorded. Diff it against the source. Pass `-f` only when the installed copy holds no change of the user's; otherwise stop and ask whether to restore, fork or skip. Done when no conflict is left.
+6. **Remove**: `remove <skill>`. It offers to remove the skills that depend on it. Done when the folder and its `skills.json` entry are gone.
+7. **Stage** the skill folders and `skills.json`. Done when `git status` shows them staged.
+
+`-t claude` or `-t codex` limits `add`, `update`, `remove` and `source` to one target.
+
+## Register a source
+
+The built-in source `g3n-skills` needs no registering and cannot be removed. Register any other source with `source add`:
+
+| Source               | Command                                                                                   |
+| -------------------- | ----------------------------------------------------------------------------------------- |
+| GitHub repository    | `source add owner/repo`                                                                   |
+| Other git repository | `source add <https, ssh, git, file or git@ URL>`, with `--ref <branch or tag>` to pin one |
+| npm package          | `source add npm:<package>[@range]` or `source add @scope/package`                         |
+| Local folder         | `source add ./my-skills --name mine`; a path starting with `.`, `/`, `~` or `local:`      |
+
+`source ls` lists the sources and `source remove <name>` drops one. A source is accepted only when it offers at least one skill. It needs a `.claude-plugin/marketplace.json` that lists its plugins, or a root `.claude-plugin/plugin.json` that makes it one plugin. A plugin's skills are the folders its `plugin.json` lists in `skills`, or every folder with a `SKILL.md` under its `skills/` folder. A skill names the skills it needs in `registryDependencies` in its frontmatter, as `<skill>` or `<skill>@<source>`.

package/skills/g3n/g3n-skills/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "G3n Skills"
+  short_description: "Install, update and remove skills with @g3nomaly/skills"
+policy:
+  allow_implicit_invocation: true

package/skills/grilling/.claude-plugin/plugin.json

@@ -1,7 +1,12 @@
 {
   "name": "grilling",
   "description": "Relentless interviews that stress-test a plan, plus the domain model they feed.",
-  "version": "0.1.0",
+  "version": "0.1.7",
   "license": "UNLICENSED",
-  "skills": ["./grilling", "./grill-me", "./grill-with-docs", "./domain-modeling"]
+  "skills": [
+    "./grilling",
+    "./grill-me",
+    "./grill-with-docs",
+    "./domain-modeling"
+  ]
 }

package/skills/grilling/domain-modeling/ADR-FORMAT.md

@@ -12,7 +12,7 @@ Create the `docs/adr/` directory lazily — only when the first ADR is needed.
 {1-3 sentences: what's the context, what did we decide, and why.}
 ```
 
-That's it. An ADR can be a single paragraph. The value is in recording *that* a decision was made and *why* — not in filling out sections.
+That's it. An ADR can be a single paragraph. The value is in recording _that_ a decision was made and _why_ — not in filling out sections.
 
 ## Optional sections
 

package/skills/grilling/domain-modeling/SKILL.md

@@ -6,7 +6,7 @@ disable-model-invocation: false
 
 # Domain Modeling
 
-Actively build and sharpen the project's domain model as you design. This is the *active* discipline — challenging terms, inventing edge-case scenarios, and writing the glossary and decisions down the moment they crystallise. (Merely *reading* `CONTEXT.md` for vocabulary is not this skill — that's a one-line habit any skill can do. This skill is for when you're changing the model, not just consuming it.)
+Actively build and sharpen the project's domain model as you design. This is the _active_ discipline — challenging terms, inventing edge-case scenarios, and writing the glossary and decisions down the moment they crystallise. (Merely _reading_ `CONTEXT.md` for vocabulary is not this skill — that's a one-line habit any skill can do. This skill is for when you're changing the model, not just consuming it.)
 
 ## File structure
 

package/skills/grilling/grilling/SKILL.md

@@ -8,6 +8,6 @@ Interview me relentlessly about every aspect of this until we reach a shared und
 
 Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.
 
-If a *fact* can be found by exploring the environment (filesystem, tools, etc.), look it up rather than asking me. The *decisions*, though, are mine — put each one to me and wait for my answer.
+If a _fact_ can be found by exploring the environment (filesystem, tools, etc.), look it up rather than asking me. The _decisions_, though, are mine — put each one to me and wait for my answer.
 
 Do not act on it until I confirm we have reached a shared understanding.

package/skills/speech/.claude-plugin/plugin.json

@@ -1,8 +1,13 @@
 {
   "name": "speech",
   "description": "Conventions for how an agent writes — emphasis markup, cutting AI tells, and plain language.",
-  "version": "0.1.0",
+  "version": "0.1.7",
   "license": "UNLICENSED",
   "hooks": "./hooks.json",
-  "skills": ["./emphasise", "./unslop", "./plain-language", "./no-questions"]
+  "skills": [
+    "./emphasise",
+    "./unslop",
+    "./plain-language",
+    "./no-questions"
+  ]
 }

package/skills/speech/emphasise/SKILL.md

@@ -12,14 +12,14 @@ Three markers, three jobs: `_italics_` highlights _core concepts and themes_, **
 
 This is your primary tool for helping a reader (human or AI) skim a paragraph and instantly grasp its subject without reading every word. It does not mean the word is a strict variable; it means the word is the thematic core of the sentence.
 
-1. _Concept / Keyword_ — highlights architectural ideas, patterns, or focal points (e.g., _minimum viable product_, _god classes_, _domain segregation_). This draws the eye to the "what are we talking about" of the sentence. 
+1. _Concept / Keyword_ — highlights architectural ideas, patterns, or focal points (e.g., _minimum viable product_, _god classes_, _domain segregation_). This draws the eye to the "what are we talking about" of the sentence.
 2. _Stress_ — the pivot the meaning turns on: "the same _way_ on every run, not the same output".
 3. _Mention_ — a word or phrase named rather than used: a coined term (_tight_), or prompt text quoted as an example (_be thorough_).
 4. _Label_ — a short tag classifying the block it opens: `_Failure mode._` Mark the tag text and nothing else.
 
 ## `**bold**` — the structural pointer
 
-Bold carries heavy weight. It is reserved for strict, defined entities, specific UI/document locations, and operative actions. 
+Bold carries heavy weight. It is reserved for strict, defined entities, specific UI/document locations, and operative actions.
 
 1. **Entity / Location** — a defined concept with an authoritative definition, or a specific destination like a file, document, or section (e.g., an extension gets reported in **Findings**).
 2. **Action / Point** — the operative clause of a bullet or step, front-loaded so the list can be skimmed by its first few words. **One trigger per branch.** Bold the instruction; leave the explanation after it plain.
@@ -30,20 +30,20 @@ Backticks are not emphasis. They mean "reproduce this exactly": paths, filenames
 
 ## Choosing
 
-| Test | Marker |
-|---|---|
+| Test                                                                            | Marker                |
+| ------------------------------------------------------------------------------- | --------------------- |
 | Is it a key concept, pattern, or keyword I want the eye to catch when skimming? | `_italics_` (concept) |
-| Is it a defined strict entity, document name, or UI element? | `**bold**` (entity) |
-| Is it the operative point of a bullet? | `**bold**` (action) |
-| Would the sentence be misread without it? | `_italics_` (stress) |
-| Is it a word or quoted phrase being named rather than used? | `_italics_` (mention) |
-| Would you type it verbatim into a terminal or a file? | `` `backticks` `` |
-| None of the above | plain text |
+| Is it a defined strict entity, document name, or UI element?                    | `**bold**` (entity)   |
+| Is it the operative point of a bullet?                                          | `**bold**` (action)   |
+| Would the sentence be misread without it?                                       | `_italics_` (stress)  |
+| Is it a word or quoted phrase being named rather than used?                     | `_italics_` (mention) |
+| Would you type it verbatim into a terminal or a file?                           | `` `backticks` ``     |
+| None of the above                                                               | plain text            |
 
 ## Failure modes
 
 - _Emphasis inflation._ So much is marked that nothing reads as marked. The fix is subtraction: cut until what remains is exactly enough to allow a reader to skim and understand the paragraph.
 - _Marker collision._ The same word bolded in one passage and italicised in another. Decide whether the word is a hard entity (**bold**) or a thematic concept (_italics_) and stick to it.
 - _Double marking._ `**_both at once_**` spends two signals on one job and looks messy. Pick one.
-- _Runaway italics._ Italics past a few words — a whole paragraph or a long quotation. Concepts are punchy; if you italicise a whole sentence, you destroy the scannability. 
-- _Bold as outline._ Bolded lead-ins carrying a hierarchy across paragraphs, where a heading (`##`) or list is the real answer.
+- _Runaway italics._ Italics past a few words — a whole paragraph or a long quotation. Concepts are punchy; if you italicise a whole sentence, you destroy the scannability.
+- _Bold as outline._ Bolded lead-ins carrying a hierarchy across paragraphs, where a heading (`##`) or list is the real answer.

package/skills/task-manager/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "task-manager",
   "description": "Query and drive a tree of plans, phases and tasks through hooks, with the plan's decisions kept beside them.",
-  "version": "0.1.0",
+  "version": "0.1.7",
   "license": "UNLICENSED",
   "hooks": "./hooks.json",
   "skills": [

package/skills/task-manager/decisions/SKILL.md

@@ -11,11 +11,11 @@ Its hooks are scripts in its own `hooks/` folder, run as `bun <decisions-dir>/ho
 
 **Reach decisions through the hooks only.** They sit inside the tree, in `<plan>/decisions/<id>.md`, so `guard-tree` denies a direct read.
 
-| Hook | Does | Use it when |
-|---|---|---|
-| `list-decisions` | Returns a plan's decisions in numbered order, metadata only | starting a phase, or checking whether a question is already closed |
-| `get-decision` | Returns one decision in full | the title is not enough |
-| `add-decision` | Numbers, dates and writes a new decision from stdin. **Writes.** | a choice passed the three tests below |
+| Hook             | Does                                                             | Use it when                                                        |
+| ---------------- | ---------------------------------------------------------------- | ------------------------------------------------------------------ |
+| `list-decisions` | Returns a plan's decisions in numbered order, metadata only      | starting a phase, or checking whether a question is already closed |
+| `get-decision`   | Returns one decision in full                                     | the title is not enough                                            |
+| `add-decision`   | Numbers, dates and writes a new decision from stdin. **Writes.** | a choice passed the three tests below                              |
 
 Copy each invocation from [`references/usage.md`](references/usage.md). `add-decision` takes the decision text on stdin, as shown there.
 

package/skills/task-manager/task-manager/SKILL.md

@@ -17,14 +17,14 @@ The task-manager keeps plans, phases and tasks as Markdown files in a tree, reac
 
 ## Hooks
 
-| Hook | Does |
-|---|---|
-| `next-entry [--in <name>] [--include-blocked]` | The first entry not `completed` (nor `blocked`, unless included), in full |
-| `get-entry --id <name> [--meta-only]` | One plan, phase or task, in full, or only its metadata |
-| `list-entries [--in <name>] [--status <status>]` | A folder's entries in order, metadata only |
-| `set-state --id <name> --to <status>` | Changes the status and rebuilds the index |
-| `cleanup [--blocked] [--dry-run]` | Deletes `completed` entries, and `blocked` ones with `--blocked`. Confirm with the user first |
-| `sync-tree` | Creates what is missing and rebuilds every index |
+| Hook                                             | Does                                                                                          |
+| ------------------------------------------------ | --------------------------------------------------------------------------------------------- |
+| `next-entry [--in <name>] [--include-blocked]`   | The first entry not `completed` (nor `blocked`, unless included), in full                     |
+| `get-entry --id <name> [--meta-only]`            | One plan, phase or task, in full, or only its metadata                                        |
+| `list-entries [--in <name>] [--status <status>]` | A folder's entries in order, metadata only                                                    |
+| `set-state --id <name> --to <status>`            | Changes the status and rebuilds the index                                                     |
+| `cleanup [--blocked] [--dry-run]`                | Deletes `completed` entries, and `blocked` ones with `--blocked`. Confirm with the user first |
+| `sync-tree`                                      | Creates what is missing and rebuilds every index                                              |
 
 Flags, outputs and errors: [`references/hooks.md`](references/hooks.md).
 

package/skills/task-manager/task-manager/references/hooks.md

@@ -2,13 +2,13 @@
 
 ## Shared flags
 
-| Flag | Meaning |
-|---|---|
-| `--project <dir>` | Folder holding `.g3n.config.json`; default the working directory |
-| `--root <dir>` | The tree folder itself, skipping the config |
-| `--id <name>` | A plan or phase name, or a task id. Searched across the whole tree |
-| `--in <name>` | Whose entries; omit for the plans at the root |
-| `--pretty` | Indented JSON |
+| Flag              | Meaning                                                            |
+| ----------------- | ------------------------------------------------------------------ |
+| `--project <dir>` | Folder holding `.g3n.config.json`; default the working directory   |
+| `--root <dir>`    | The tree folder itself, skipping the config                        |
+| `--id <name>`     | A plan or phase name, or a task id. Searched across the whole tree |
+| `--in <name>`     | Whose entries; omit for the plans at the root                      |
+| `--pretty`        | Indented JSON                                                      |
 
 ## Output
 
@@ -21,9 +21,9 @@ JSON on stdout, messages on stderr.
 
 ## Fired by the plugin
 
-| Hook | Event | Does |
-|---|---|---|
-| `sync-tree` | `SessionStart` | Rebuilds every index |
+| Hook         | Event                              | Does                          |
+| ------------ | ---------------------------------- | ----------------------------- |
+| `sync-tree`  | `SessionStart`                     | Rebuilds every index          |
 | `guard-tree` | `PreToolUse` on `Read\|Grep\|Glob` | Denies a path inside the tree |
 
 ## Errors

package/skills/task-manager/task-manager/references/task-file.md

@@ -8,18 +8,18 @@
 
 The hooks check it against `TaskSchema` and reject any other key.
 
-| Key | Rule |
-|---|---|
-| `id` | A prefix, a hyphen, then digits, e.g. `TASK-012`. Unique across the tree: continue from the highest in use, shown per phase by `bun <task-manager-dir>/hooks/list-entries.ts --in <phase>` |
-| `title` | A few words naming the deliverable |
-| `package` | The package the work lands in |
-| `priority` | `critical`, `high`, `medium` or `low` |
-| `depends_on` | Ids of tasks that must be handed over first; `[]` when none |
-| `summary` | One sentence: what is different once the task is done |
-| `complexity` | `1` to `5`. Optional |
-| `worktree` | Always `true` |
-| `worktree_type` | `feature`, `fix`, `refactor`, `chore`, `docs`, `snapshot`, `demo` or `experiment`. Becomes the branch prefix |
-| `status` | `open` at creation |
+| Key             | Rule                                                                                                                                                                                       |
+| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `id`            | A prefix, a hyphen, then digits, e.g. `TASK-012`. Unique across the tree: continue from the highest in use, shown per phase by `bun <task-manager-dir>/hooks/list-entries.ts --in <phase>` |
+| `title`         | A few words naming the deliverable                                                                                                                                                         |
+| `package`       | The package the work lands in                                                                                                                                                              |
+| `priority`      | `critical`, `high`, `medium` or `low`                                                                                                                                                      |
+| `depends_on`    | Ids of tasks that must be handed over first; `[]` when none                                                                                                                                |
+| `summary`       | One sentence: what is different once the task is done                                                                                                                                      |
+| `complexity`    | `1` to `5`. Optional                                                                                                                                                                       |
+| `worktree`      | Always `true`                                                                                                                                                                              |
+| `worktree_type` | `feature`, `fix`, `refactor`, `chore`, `docs`, `snapshot`, `demo` or `experiment`. Becomes the branch prefix                                                                               |
+| `status`        | `open` at creation                                                                                                                                                                         |
 
 ## Status
 

package/skills/teach/.claude-plugin/plugin.json

@@ -1,7 +1,15 @@
 {
   "name": "teach",
   "description": "Teach through real work: build, explain, dive deep, decide architecture, debug and review while the user learns the reasoning.",
-  "version": "0.1.0",
+  "version": "0.1.7",
   "license": "UNLICENSED",
-  "skills": ["./teaching", "./learn-by-building", "./explain", "./deep-dive", "./architecture", "./guided-debugging", "./guided-review"]
+  "skills": [
+    "./teaching",
+    "./learn-by-building",
+    "./explain",
+    "./deep-dive",
+    "./architecture",
+    "./guided-debugging",
+    "./guided-review"
+  ]
 }

package/skills/teach/guided-debugging/references/debugging-loop.md

@@ -2,16 +2,16 @@
 
 Keep this record when an investigation has several plausible hypotheses or spans several experiments.
 
-| Field | Record |
-| --- | --- |
-| Exact symptom | Error, wrong result, timing and reproduction boundary |
-| Producer and stage | Component that produced the evidence, and where it failed |
-| Relevant state | Configuration, inputs, dependencies and environment |
-| Hypothesis | A testable causal explanation |
-| Prediction | The result expected if the hypothesis is right |
-| Experiment | A small, safe action that tells the likely explanations apart |
-| Observation | The result of the experiment, uninterpreted |
-| Interpretation | Hypotheses strengthened, weakened or eliminated |
+| Field              | Record                                                        |
+| ------------------ | ------------------------------------------------------------- |
+| Exact symptom      | Error, wrong result, timing and reproduction boundary         |
+| Producer and stage | Component that produced the evidence, and where it failed     |
+| Relevant state     | Configuration, inputs, dependencies and environment           |
+| Hypothesis         | A testable causal explanation                                 |
+| Prediction         | The result expected if the hypothesis is right                |
+| Experiment         | A small, safe action that tells the likely explanations apart |
+| Observation        | The result of the experiment, uninterpreted                   |
+| Interpretation     | Hypotheses strengthened, weakened or eliminated               |
 
 Update the hypothesis set after each experiment instead of piling up unrelated fixes.
 

package/skills/teach/teaching/references/learning-model.md

@@ -2,12 +2,12 @@
 
 Track understanding per concept, never as one level for the whole person. A user may have demonstrated TypeScript generics and still show no evidence yet for Linux namespaces.
 
-| State | Evidence | Guidance |
-| --- | --- | --- |
-| Unknown | None yet. Unobserved, not incapable | Explain directly, and demonstrate before expecting independent use |
-| Partial | Part of the model, with a gap or misconception | Keep what is right and repair only the missing connection |
-| Understood | Explains or reasons correctly with some support | Stop re-explaining; let the user reason through the next decision worth practicing |
-| Demonstrated | Applies it alone in real work and reads the result correctly | Step back; step in only for risk, new constraints or contradicting evidence |
+| State        | Evidence                                                     | Guidance                                                                           |
+| ------------ | ------------------------------------------------------------ | ---------------------------------------------------------------------------------- |
+| Unknown      | None yet. Unobserved, not incapable                          | Explain directly, and demonstrate before expecting independent use                 |
+| Partial      | Part of the model, with a gap or misconception               | Keep what is right and repair only the missing connection                          |
+| Understood   | Explains or reasons correctly with some support              | Stop re-explaining; let the user reason through the next decision worth practicing |
+| Demonstrated | Applies it alone in real work and reads the result correctly | Step back; step in only for risk, new constraints or contradicting evidence        |
 
 ## Evidence
 

package/skills/using-hooks/.claude-plugin/plugin.json

@@ -1,7 +1,12 @@
 {
   "name": "using-hooks",
   "description": "How to write each Claude Code lifecycle hook.",
-  "version": "0.1.0",
+  "version": "0.1.7",
   "license": "UNLICENSED",
-  "skills": ["./hook-pre-tool-use", "./hook-post-tool-use", "./hook-stop", "./hook-user-prompt-submit"]
+  "skills": [
+    "./hook-pre-tool-use",
+    "./hook-post-tool-use",
+    "./hook-stop",
+    "./hook-user-prompt-submit"
+  ]
 }

package/skills/using-hooks/hook-post-tool-use/SKILL.md

@@ -20,8 +20,15 @@ The four common fields, the call, and what came back:
   "cwd": "/home/you/project",
   "hook_event_name": "PostToolUse",
   "tool_name": "Edit",
-  "tool_input": { "file_path": "/home/you/project/src/index.ts", "old_string": "…", "new_string": "…" },
-  "tool_response": { "filePath": "/home/you/project/src/index.ts", "success": true }
+  "tool_input": {
+    "file_path": "/home/you/project/src/index.ts",
+    "old_string": "…",
+    "new_string": "…"
+  },
+  "tool_response": {
+    "filePath": "/home/you/project/src/index.ts",
+    "success": true
+  }
 }
 ```
 
@@ -34,7 +41,12 @@ Same tool-name regex as [`hook-pre-tool-use`](../hook-pre-tool-use/SKILL.md), an
 ```json
 {
   "matcher": "Edit|MultiEdit|Write",
-  "hooks": [{ "type": "command", "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/format-edited-file.ts" }]
+  "hooks": [
+    {
+      "type": "command",
+      "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/format-edited-file.ts"
+    }
+  ]
 }
 ```
 

package/skills/using-hooks/hook-pre-tool-use/SKILL.md

@@ -20,7 +20,10 @@ The four common fields, plus the call about to be made:
   "cwd": "/home/you/project",
   "hook_event_name": "PreToolUse",
   "tool_name": "Write",
-  "tool_input": { "file_path": "/home/you/project/src/index.ts", "content": "…" }
+  "tool_input": {
+    "file_path": "/home/you/project/src/index.ts",
+    "content": "…"
+  }
 }
 ```
 
@@ -33,7 +36,12 @@ This event selects by tool name, as a regex:
 ```json
 {
   "matcher": "Edit|MultiEdit|Write",
-  "hooks": [{ "type": "command", "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-protected-paths.ts" }]
+  "hooks": [
+    {
+      "type": "command",
+      "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-protected-paths.ts"
+    }
+  ]
 }
 ```
 

package/skills/workflow/.claude-plugin/plugin.json

@@ -1,10 +1,14 @@
 {
   "name": "workflow",
   "description": "Work a phase of a plan through plan, execute, review and sync, one agent per step, with hooks deciding when a step is finished.",
-  "version": "0.1.0",
+  "version": "0.1.7",
   "license": "UNLICENSED",
-  "dependencies": ["task-manager@g3n"],
-  "agents": ["./review/agents/reviewer.md"],
+  "dependencies": [
+    "task-manager@g3n"
+  ],
+  "agents": [
+    "./review/agents/reviewer.md"
+  ],
   "skills": [
     "./run",
     "./plan",

package/skills/workflow/orchestrator/SKILL.md

@@ -11,12 +11,12 @@ Hooks are scripts in a skill's `hooks/` folder, run with `bun`. `<task-manager-d
 
 `bun <orchestrator-dir>/hooks/ready-phases.ts --plan <plan>` sorts the plan's phases by gate:
 
-| Field | Holds |
-|---|---|
-| `ready` | phases whose gate is open, in queue order, each in full |
-| `waiting` | phases behind a closed gate, with the phases they are `waiting_on` |
-| `blocked` | phases set to `blocked` |
-| `completed` | finished phases |
+| Field       | Holds                                                              |
+| ----------- | ------------------------------------------------------------------ |
+| `ready`     | phases whose gate is open, in queue order, each in full            |
+| `waiting`   | phases behind a closed gate, with the phases they are `waiting_on` |
+| `blocked`   | phases set to `blocked`                                            |
+| `completed` | finished phases                                                    |
 
 1. **Claim the plan** with `bun <task-manager-dir>/hooks/set-state.ts --id <plan> --to in-progress`, unless it already is.
 2. **Read the gates** with `ready-phases`.

package/skills/workflow/plan/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: plan
 description: Use as the plan step of the workflow, when a phase has no tasks yet, or when the user wants a phase broken down.
-registryDependencies: [task-manager, writing-great-tasks, vocabulary, decisions, grilling, run]
+registryDependencies:
+  [task-manager, writing-great-tasks, vocabulary, decisions, grilling, run]
 disable-model-invocation: false
 ---
 

package/skills/workflow/review/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: review
 description: Use as the review step of the workflow, when every remaining task of a phase is in-review, or when the user wants a phase's work checked before it is merged.
-registryDependencies: [task-manager, writing-great-tasks, vocabulary, decisions, run]
+registryDependencies:
+  [task-manager, writing-great-tasks, vocabulary, decisions, run]
 disable-model-invocation: false
 ---