@elevasis/sdk 0.5.3 → 0.5.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -23,7 +23,7 @@ The generated `CLAUDE.md` contains these sections:
23
23
  - **Navigation** -- A table mapping concepts to file paths with load conditions (when to load each file). Includes SDK reference docs, credential model, error history, `docs/project-map.mdx`, and `docs/priorities.mdx`.
24
24
  - **Rules** -- Points to auto-loaded rule files in `.claude/rules/`. SDK patterns load automatically; project-specific patterns live in `workspace-patterns.md`. Includes error handling protocol.
25
25
  - **Interaction Guidance** -- Per-dimension behavior rules derived from `memory/profile/skills.md`. Covers vocabulary, code completeness, explanation depth, and growth logging.
26
- - **Commands** -- Table of the 4 slash commands with one-line purpose descriptions.
26
+ - **Commands** -- Table of the 4 slash commands (`/meta`, `/docs`, `/work`, `/tutorial`) with one-line purpose descriptions.
27
27
  - **Skills** -- Auto-trigger conditions for the `creds` skill.
28
28
  - **Maintaining Memory** -- Hierarchical structure, pruning rules, and what belongs in memory vs. `docs/` vs. `.claude/rules/`.
29
29
 
@@ -42,11 +42,12 @@ At the start of every session the agent runs these steps silently before respond
42
42
 
43
43
  Slash commands are short Markdown instruction files in `.claude/commands/`. When you type `/command-name` in a Claude Code session, the agent reads the corresponding file and follows its instructions.
44
44
 
45
- Three commands and one skill are scaffolded by `elevasis init` and committed to version control so collaborators get the same experience:
45
+ Four commands and one skill are scaffolded by `elevasis init` and committed to version control so collaborators get the same experience:
46
46
 
47
47
  | Command | File | Purpose |
48
48
  | --- | --- | --- |
49
49
  | `/meta` | `meta.md` | Project lifecycle -- init, status, fix (incl. docs verification), deploy, health |
50
+ | `/docs` | `docs.md` | Browse, create, and verify permanent documentation |
50
51
  | `/work` | `work.md` | Task tracking -- list, create, save, resume, complete |
51
52
  | `/tutorial` | `tutorial.md` | Progressive learning path -- 3 tracks, menu-driven |
52
53
 
@@ -62,6 +63,14 @@ The `/meta` command namespace manages the full project lifecycle. It has five op
62
63
  - **`/meta deploy`** -- Full 9-step deploy pipeline: validate, type-check, verify docs, commit, deploy (auto-regenerates `docs/project-map.mdx`), verify platform, update deployment state, and optionally push.
63
64
  - **`/meta health`** -- Execution debugging and resource status; shows recent executions, analyzes failures, and checks environment connectivity.
64
65
 
66
+ ### `/docs` Command
67
+
68
+ The `/docs` command manages the permanent `docs/` tree -- everything except `docs/in-progress/` (owned by `/work`) and auto-generated files (`project-map.mdx`, `resource-map.mdx`). Three operations:
69
+
70
+ - **`/docs`** (no arguments) -- Browse. Scans `docs/` recursively and displays a numbered list of user-maintained docs with auto-generated files shown separately as read-only. Pick a number to read and discuss, or say "create" or "verify."
71
+ - **`/docs create [description]`** -- Interview-driven reference doc creation. If the doc is about a specific resource, the agent scans `src/` and pre-populates from code (config, schemas, step names, platform tools). Scaffolds sections appropriate to the doc type (resource guide, integration guide, architecture notes, process doc, or general reference).
72
+ - **`/docs verify [file?]`** -- Interactive standalone version of `/meta fix` step 5. Cross-references resource IDs, schema fields, and platform tools in docs against `src/`. Shows a summary, then guides fixes interactively. Can be scoped to a single file.
73
+
65
74
  ### `/work` Command
66
75
 
67
76
  The `/work` command manages in-progress task tracking across sessions. It uses `docs/in-progress/` for task documents with standardized frontmatter (`status: planned | in-progress | complete`). Operations:
@@ -17,6 +17,7 @@ Running `elevasis init my-project` produces the following agent infrastructure a
17
17
  ├── settings.json # autoCompact: false
18
18
  ├── commands/
19
19
  │ ├── meta.md # Project lifecycle (init, fix, deploy, health)
20
+ │ ├── docs.md # Browse, create, and verify permanent docs
20
21
  │ ├── tutorial.md # Progressive learning path (3 tracks)
21
22
  │ └── work.md # Task tracking
22
23
  ├── hooks/
@@ -52,7 +53,7 @@ The agent reads `memory/index.md` at session start and drills into `memory/profi
52
53
 
53
54
  The `CLAUDE.md` file drives all agent behavior. It contains the session initialization instructions, adaptive guidance tiers, memory maintenance rules, and slash command definitions. No hooks, no code enforcement -- everything is instruction-driven so non-technical users never need to configure anything.
54
55
 
55
- The `/meta` command manages the project lifecycle: `/meta init` for guided setup, `/meta fix` for SDK upgrades, drift repair, and documentation verification, `/meta deploy` for deployments, `/meta health` for debugging executions. `/work` tracks tasks across sessions, and `/tutorial` guides new developers through a menu-driven multi-track learning path. A `creds` skill auto-triggers when credential setup is needed.
56
+ The `/meta` command manages the project lifecycle: `/meta init` for guided setup, `/meta fix` for SDK upgrades, drift repair, and documentation verification, `/meta deploy` for deployments, `/meta health` for debugging executions. `/docs` browses, creates, and verifies permanent documentation in `docs/`. `/work` tracks tasks across sessions, and `/tutorial` guides new developers through a menu-driven multi-track learning path. A `creds` skill auto-triggers when credential setup is needed.
56
57
 
57
58
  See [Agent System](agent.mdx) for CLAUDE.md sections, slash command reference, developer profile, and adaptive guidance tiers.
58
59
 
@@ -229,7 +229,7 @@ This directory is gitignored -- it is personal to you and not shared with collab
229
229
 
230
230
  ## Slash Commands
231
231
 
232
- The `.claude/commands/` directory contains three commands covering the core development loop. Invoke them in Claude Code with `/meta`, `/work`, and `/tutorial`.
232
+ The `.claude/commands/` directory contains four commands covering the core development loop. Invoke them in Claude Code with `/meta`, `/docs`, `/work`, and `/tutorial`.
233
233
 
234
234
  ### `/meta` -- Project Lifecycle
235
235
 
@@ -241,6 +241,14 @@ Manages the full lifecycle of your workspace. Five operations:
241
241
  - **`deploy`** -- Full 9-step deploy pipeline: validate, type-check, verify docs, commit, deploy (auto-regenerates `docs/project-map.mdx`), verify platform, update deployment state, and optionally push.
242
242
  - **`health`** -- Execution debugging and resource status; shows recent executions, analyzes failures, and checks environment connectivity.
243
243
 
244
+ ### `/docs` -- Documentation
245
+
246
+ Manages the permanent `docs/` tree. Three operations:
247
+
248
+ - **No arguments** -- Browse. Lists user-maintained docs with auto-generated files (`project-map.mdx`, `resource-map.mdx`) shown as read-only. Pick a number to read and discuss.
249
+ - **`create [description]`** -- Interview-driven reference doc creation. If the doc is about a specific resource, the agent reads `src/` and pre-populates from code. Scaffolds sections by doc type (resource guide, integration guide, architecture notes, process doc, general reference).
250
+ - **`verify [file?]`** -- Interactive standalone docs verification. Cross-references resource IDs, schema fields, and platform tools in docs against `src/`. Guides fixes interactively.
251
+
244
252
  ### `/work` -- Task Tracking
245
253
 
246
254
  Manages in-progress task tracking across sessions using `docs/in-progress/` task documents. Five operations:
@@ -261,7 +269,7 @@ A 7-lesson guided learning path adapted to the user's skill profile. Lessons cov
261
269
 
262
270
  Not all scaffolded files participate in template updates. Files fall into two categories:
263
271
 
264
- **SCAFFOLD_FILES total: 29**
272
+ **SCAFFOLD_FILES total: 30**
265
273
 
266
274
  **INIT_ONLY** (15 files) -- Written once during `elevasis init`, never updated by `elevasis update`:
267
275
  - `package.json`, `pnpm-workspace.yaml`, `tsconfig.json`
@@ -270,10 +278,10 @@ Not all scaffolded files participate in template updates. Files fall into two ca
270
278
  - `docs/index.mdx`, `docs/in-progress/.gitkeep`
271
279
  - `.claude/rules/workspace-patterns.md`
272
280
 
273
- **MANAGED** (14 files) -- Written during `elevasis init` and checked/updatable by `elevasis update`:
281
+ **MANAGED** (15 files) -- Written during `elevasis init` and checked/updatable by `elevasis update`:
274
282
  - `elevasis.config.ts`, `.gitignore`, `CLAUDE.md`, `.claude/settings.json`
275
283
  - One hook: `.claude/hooks/enforce-sdk-boundary.mjs`
276
- - Three command files: `.claude/commands/meta.md`, `.claude/commands/tutorial.md`, `.claude/commands/work.md`
284
+ - Four command files: `.claude/commands/meta.md`, `.claude/commands/docs.md`, `.claude/commands/tutorial.md`, `.claude/commands/work.md`
277
285
  - One skill: `.claude/skills/creds/SKILL.md`
278
286
  - Five rule files: `.claude/rules/sdk-patterns.md`, `.claude/rules/docs-authoring.md`, `.claude/rules/memory-conventions.md`, `.claude/rules/project-map.md`, `.claude/rules/task-tracking.md`
279
287