@ck123pm/harness-kit 0.1.3 → 0.1.4

package/.claude/scheduled_tasks.lock

@@ -0,0 +1 @@
+{"sessionId":"3f555614-8398-44a9-8eaf-c6392cea7744","pid":24940,"acquiredAt":1779795641460}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ck123pm/harness-kit",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "description": "CLI for installing and managing Claude Code harness capabilities",
   "type": "module",
   "bin": {

package/skills/harness-init/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-init
-description: Initialize a project's .harness/ directory by deriving high-value project knowledge from the real codebase, splitting content into the expected index/rules/domain/decisions/guides/memory/human-docs structure, and avoiding facts that can be re-derived from source.
+description: Initialize a project's .harness/ directory by exploring the real codebase and generating structured project knowledge docs. Use when starting harness for a new project or rebuilding stale .harness/ content.
 ---
 
 # Harness Init
@@ -15,16 +15,16 @@ Use this skill when the user wants to initialize a project's `.harness/` directo
 4. Put human-oriented docs in `human-docs/` as Markdown first, convert them to HTML with `md-to-html-doc`, then remove the Markdown source if the workflow requires generated HTML only.
 5. Never fabricate content that is not supported by the actual repository state.
 
-## Target Directory Structure
+## Directory Structure and Content Routing
 
-Create this structure under `.harness/`:
+The `.harness/` directory uses a category-based layout. The reference files below are **starting points** — create only files with real content, add new files when needed, and skip empty placeholders.
 
 ```text
 .harness/
-├── README.md
+├── README.md           # always create: explain injection routing via index/routing.md and priority via index/priority.md
 ├── index/
-│   ├── routing.md
-│   ├── priority.md
+│   ├── routing.md      # always create
+│   ├── priority.md     # always create
 │   ├── module-map.md
 │   └── project-profile.md
 ├── rules/
@@ -48,30 +48,26 @@ Create this structure under `.harness/`:
 │   ├── patterns.md
 │   └── lessons.md
 └── human-docs/
-    ├── onboarding.html
-    ├── architecture-intro.html
-    └── operation-manual.html
+    └── ...             # onboarding.html, architecture-intro.html, operation-manual.html
 ```
 
-## Content Routing
-
-| Information type | Destination |
+| Information type | Reference file |
 | --- | --- |
-| Project identity, tech stack, module structure, key constants | `index/project-profile.md` |
+| Project identity, tech stack, module structure | `index/project-profile.md` |
 | Task-to-context routing | `index/routing.md` |
 | Injection priority and intensity | `index/priority.md` |
 | Module-to-spec mapping | `index/module-map.md` |
-| Architecture constraints, module boundaries, ownership, high-risk chains | `rules/architecture.md` |
-| Coding standards, serialization, locking, conventions | `rules/coding.md` |
-| Test framework, file layout, strategy, fast commands | `rules/testing.md` |
+| Architecture constraints, boundaries, ownership | `rules/architecture.md` |
+| Coding standards, conventions | `rules/coding.md` |
+| Test framework, strategy, commands | `rules/testing.md` |
 | Security constraints | `rules/security.md` |
 | Domain terminology | `domain/glossary.md` |
 | Stable business rules | `domain/business-rules.md` |
-| Runtime semantics, state transitions, magic values | `domain/runtime-semantics.md` |
-| External-system runtime semantics, message flow, integration behavior | `guides/backend.md` |
-| Build, startup, logs, config, monitoring, troubleshooting | `guides/ops.md` |
-| ADRs and tradeoffs | `decisions/` |
-| Historical pitfalls, regressions, reusable patterns, lessons | `memory/` |
+| Runtime semantics, state transitions | `domain/runtime-semantics.md` |
+| External integrations, message flow | `guides/backend.md` |
+| Build, config, monitoring, troubleshooting | `guides/ops.md` |
+| ADRs, design tradeoffs | `decisions/` |
+| Pitfalls, regressions, patterns, lessons | `memory/` |
 
 ## Exploration Strategy
 
@@ -90,11 +86,3 @@ Before generating any content, determine the output language:
 1. Read the project's `CLAUDE.md` (or `.claude/CLAUDE.md`) if it exists. If it declares a language preference (e.g. `language: zh-CN`, "使用中文", "write in English"), follow that.
 2. If no language preference is found, match the language of the current conversation.
 3. All generated files in `.harness/` must use the same language consistently.
-
-## Execution
-
-1. Explore the repository thoroughly and base all outputs on the current branch state.
-2. Create the full `.harness/` tree, even if some files are initially brief.
-3. Keep generated content concise and high-signal.
-4. If `human-docs/` content is needed, write Markdown first, then use `md-to-html-doc` to produce HTML.
-5. Verify the final `.harness/` tree is complete.

package/skills/harness-update-spec/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-update-spec
-description: Analyze an existing project's .harness/ specs against the current codebase, identify incremental updates or missing specs, and propose focused changes without regenerating everything from scratch.
+description: Analyze and incrementally update an existing project's .harness/ specs against the current codebase. Use when the codebase has changed and .harness/ content may be stale, or when the user wants to check spec freshness.
 ---
 
 # Harness Update Spec
@@ -41,7 +41,7 @@ Prefer CodeGraph when it is available.
 
 ### 3. Derive a diff matrix
 
-Map detected changes to spec targets:
+Map detected changes to spec targets. These are reference mappings — create new files when the change doesn't fit an existing one.
 
 | Change type | Likely spec target |
 | --- | --- |
@@ -73,16 +73,6 @@ When updating:
 3. Keep internal references inside `.harness/` consistent after edits.
 4. Re-run a quick file list check to ensure the directory remains coherent.
 
-## Content Routing
-
-Reuse the same content-routing rules as `harness-init`:
-
-- Project identity goes to `index/project-profile.md`.
-- Data flow and external runtime semantics go to `guides/backend.md`.
-- High-risk chains and boundaries go to `rules/architecture.md`.
-- Decisions and tradeoffs go to `decisions/`.
-- Historical pitfalls, regressions, and patterns go to `memory/`.
-
 ## Language
 
 Before generating or updating any content, determine the output language using the same rules as `harness-init`: