@mrciphersmith/keryx 0.2.97 → 0.2.98

package/src/gdskills/bundled/skills/orchestration/task-implementer/SKILL.opencode.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.3.1"
-  category: "implementation"
+  category: "orchestration"
   agent_worthy: true
   compatible_harnesses: "claude,cursor,codex,zed,opencode"
 license: "MIT"
@@ -222,8 +222,6 @@ Based on what you're implementing, load and follow the relevant project rules.
 
 Rules live at `.metaproject/rules/core/<rule>.mdc` on every harness — that is the
 one tree `keryx init` installs and the one every build of this skill reads.
-Cursor additionally mirrors them under `.cursor/rules/core/<rule>.mdc`; when both
-are present they are copies of the same file, so read either.
 
 **Output of Phase 2:** Mental model of the implementation:
 ```
@@ -317,15 +315,21 @@ Execute the change plan. Write production-quality code.
 
 **4.5 Commit after implementation:**
 
-When auto-commit is enabled, create a conventional commit with the changes. Include the `refs #<issue_number>` line below only when a positive real issue number was supplied; otherwise omit that entire line:
+When auto-commit is enabled, create a conventional commit with the changes. Stage explicit paths only — never `-A`/`--all`/`.` — and run every git command as `git -C "<codebase_path>"` (`rules/core/git-concurrency.mdc`). Include the `refs #<issue_number>` line below only when a positive real issue number was supplied; otherwise omit that entire line:
 ```bash
-git add <modified files>
-git commit -m "<type>(<scope>): <description>
+git -C "<codebase_path>" add <modified files, explicit paths>
+git -C "<codebase_path>" commit -m "<type>(<scope>): <description>
 
 refs #<issue_number>
 task: <task_id>"
 ```
 
+When auto-commit is disabled, do not commit. Report the exact list of files you
+changed — nothing inferred — in the Phase 6 STATUS response and the result
+file's `files_modified`/`files_created`/`files_deleted`; the orchestrator stages
+and commits those exact paths at the task boundary (`rules/core/git-concurrency.mdc`,
+"Reporting Back").
+
 Commit type mapping:
 | Task Type | Commit Type |
 |-----------|-------------|
@@ -396,20 +400,25 @@ identical outputs cost the whole budget to learn what the second one already
 said. Report the block instead, naming what repeated.
 
 
-**ROLLBACK POLICY**: If implementation fatally fails (tests still failing after 3 attempts, or unresolvable compilation errors), restore ONLY the files this task changed — `git checkout -- <your files>` for tracked ones, delete the untracked ones you created — then report the failure in Phase 6.
+**ROLLBACK POLICY**: If implementation fatally fails (tests still failing after 3 attempts, or unresolvable compilation errors), restore ONLY the files this task changed — `git -C "<codebase_path>" checkout -- <your files>` for tracked ones, delete the untracked ones you created — then report the failure in Phase 6.
 
 **Never run `git reset --hard`, `git clean`, or any unscoped revert.** You do not own the worktree. `job-orchestrator` dispatches implementers in PARALLEL WAVES sharing a single worktree, so an unscoped reset destroys a wave-mate's uncommitted work — work that is not yours, cannot be recovered, and whose loss is invisible to you because the other agent's failure surfaces somewhere else entirely. If you cannot identify which files are yours, leave the tree exactly as it is and say so in the report: a dirty tree is recoverable, a destroyed one is not.
 
+**Same reasoning bans `git stash` and unscoped `git add`.** Never `git stash` — the stash stack is shared by every worktree, so even a scoped `push -- <file>` can be popped by another lane. Stage only the files this task changed (`git -C "<codebase_path>" add <path> <path>`), never `-A`/`--all`/`.`. Every git command runs as `git -C <this worktree's absolute path>`. See `rules/core/git-concurrency.mdc`.
+
 **5.5 Re-commit fixes if any:**
-When auto-commit is enabled, use the template below. Include `refs #<issue_number>` only for a supplied positive real issue number; otherwise omit that entire line.
+When auto-commit is enabled, use the template below — explicit paths only, `git -C "<codebase_path>"` for every command (`rules/core/git-concurrency.mdc`). Include `refs #<issue_number>` only for a supplied positive real issue number; otherwise omit that entire line.
 ```bash
-git add <fixed files>
-git commit -m "fix(<scope>): resolve lint/type/test issues
+git -C "<codebase_path>" add <fixed files, explicit paths>
+git -C "<codebase_path>" commit -m "fix(<scope>): resolve lint/type/test issues
 
 refs #<issue_number>
 task: <task_id>"
 ```
 
+When auto-commit is disabled, do not commit; report the exact fixed-file list in
+Phase 6 as in 4.5 — the orchestrator commits it at the task boundary.
+
 ### Phase 6: REPORT
 
 Write the full result to a file, then emit a compact STATUS response to the orchestrator.

package/src/gdskills/bundled/skills/orchestration/task-implementer/SKILL.zed.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.3.1"
-  category: "implementation"
+  category: "orchestration"
   agent_worthy: true
   compatible_harnesses: "claude,cursor,codex,zed,opencode"
 license: "MIT"
@@ -222,8 +222,6 @@ Based on what you're implementing, load and follow the relevant project rules.
 
 Rules live at `.metaproject/rules/core/<rule>.mdc` on every harness — that is the
 one tree `keryx init` installs and the one every build of this skill reads.
-Cursor additionally mirrors them under `.cursor/rules/core/<rule>.mdc`; when both
-are present they are copies of the same file, so read either.
 
 **Output of Phase 2:** Mental model of the implementation:
 ```
@@ -317,15 +315,21 @@ Execute the change plan. Write production-quality code.
 
 **4.5 Commit after implementation:**
 
-When auto-commit is enabled, create a conventional commit with the changes. Include the `refs #<issue_number>` line below only when a positive real issue number was supplied; otherwise omit that entire line:
+When auto-commit is enabled, create a conventional commit with the changes. Stage explicit paths only — never `-A`/`--all`/`.` — and run every git command as `git -C "<codebase_path>"` (`rules/core/git-concurrency.mdc`). Include the `refs #<issue_number>` line below only when a positive real issue number was supplied; otherwise omit that entire line:
 ```bash
-git add <modified files>
-git commit -m "<type>(<scope>): <description>
+git -C "<codebase_path>" add <modified files, explicit paths>
+git -C "<codebase_path>" commit -m "<type>(<scope>): <description>
 
 refs #<issue_number>
 task: <task_id>"
 ```
 
+When auto-commit is disabled, do not commit. Report the exact list of files you
+changed — nothing inferred — in the Phase 6 STATUS response and the result
+file's `files_modified`/`files_created`/`files_deleted`; the orchestrator stages
+and commits those exact paths at the task boundary (`rules/core/git-concurrency.mdc`,
+"Reporting Back").
+
 Commit type mapping:
 | Task Type | Commit Type |
 |-----------|-------------|
@@ -396,20 +400,25 @@ identical outputs cost the whole budget to learn what the second one already
 said. Report the block instead, naming what repeated.
 
 
-**ROLLBACK POLICY**: If implementation fatally fails (tests still failing after 3 attempts, or unresolvable compilation errors), restore ONLY the files this task changed — `git checkout -- <your files>` for tracked ones, delete the untracked ones you created — then report the failure in Phase 6.
+**ROLLBACK POLICY**: If implementation fatally fails (tests still failing after 3 attempts, or unresolvable compilation errors), restore ONLY the files this task changed — `git -C "<codebase_path>" checkout -- <your files>` for tracked ones, delete the untracked ones you created — then report the failure in Phase 6.
 
 **Never run `git reset --hard`, `git clean`, or any unscoped revert.** You do not own the worktree. `job-orchestrator` dispatches implementers in PARALLEL WAVES sharing a single worktree, so an unscoped reset destroys a wave-mate's uncommitted work — work that is not yours, cannot be recovered, and whose loss is invisible to you because the other agent's failure surfaces somewhere else entirely. If you cannot identify which files are yours, leave the tree exactly as it is and say so in the report: a dirty tree is recoverable, a destroyed one is not.
 
+**Same reasoning bans `git stash` and unscoped `git add`.** Never `git stash` — the stash stack is shared by every worktree, so even a scoped `push -- <file>` can be popped by another lane. Stage only the files this task changed (`git -C "<codebase_path>" add <path> <path>`), never `-A`/`--all`/`.`. Every git command runs as `git -C <this worktree's absolute path>`. See `rules/core/git-concurrency.mdc`.
+
 **5.5 Re-commit fixes if any:**
-When auto-commit is enabled, use the template below. Include `refs #<issue_number>` only for a supplied positive real issue number; otherwise omit that entire line.
+When auto-commit is enabled, use the template below — explicit paths only, `git -C "<codebase_path>"` for every command (`rules/core/git-concurrency.mdc`). Include `refs #<issue_number>` only for a supplied positive real issue number; otherwise omit that entire line.
 ```bash
-git add <fixed files>
-git commit -m "fix(<scope>): resolve lint/type/test issues
+git -C "<codebase_path>" add <fixed files, explicit paths>
+git -C "<codebase_path>" commit -m "fix(<scope>): resolve lint/type/test issues
 
 refs #<issue_number>
 task: <task_id>"
 ```
 
+When auto-commit is disabled, do not commit; report the exact fixed-file list in
+Phase 6 as in 4.5 — the orchestrator commits it at the task boundary.
+
 ### Phase 6: REPORT
 
 Write the full result to a file, then emit a compact STATUS response to the orchestrator.

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.codex.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "ideation"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.cursor.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "ideation"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "ideation"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/interview/SKILL.codex.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "analysis"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/interview/SKILL.cursor.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "analysis"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/interview/SKILL.md

@@ -11,7 +11,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "analysis"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/interviewer/SKILL.codex.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "meta"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/interviewer/SKILL.cursor.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "meta"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/interviewer/SKILL.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "meta"
+  category: "planning"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.codex.md

@@ -11,7 +11,7 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
-  compatible_harnesses: "cursor,codex,zed,opencode"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
 
@@ -93,6 +93,8 @@ When generating the final PRD, follow this exact structure:
 ```markdown
 # PRD: {Feature Name}
 
+Version: 0.1.0
+
 ## 1. Overview
 Brief summary of the feature.
 
@@ -145,13 +147,11 @@ Then
 ## 6. Output Location & Format
 
 **Direct Mode:**
-- You MUST follow `rules/core/documentation-management.mdc` for the `requirements` category.
+- You MUST follow `rules/core/requirements-package-standard.mdc` (via `rules/core/documentation-management.mdc` for the `requirements` category).
 - Before saving, ASK the user to confirm the feature name (`<name>`) or to suggest a custom path.
-- The default target path is: `<current_project_root>/docs/requirements/<name>-<YYYY-MM-DD>/`
-- You MUST generate 3 synchronized language variants:
-  - `ru/<name>.md` (Russian for humans)
-  - `en/<name>.md` (English for humans)
-  - `ai/<name>.md` (AI-readable format, heavily using Gherkin)
+- The default target path is: `<current_project_root>/docs/requirements/<name>/prd.md` — no date-stamped folder.
+- If the requirements package (`README.md`, `prd.md`, `specification.md`) does not exist yet, create it; otherwise update `prd.md` in place and bump its `Version` field rather than creating a parallel copy.
+- Default to a single document in the project's documentation language (`en` unless the project states otherwise). Generate additional language variants only when the user explicitly asks for them, and keep any variants you create synchronized.
 - You MUST NOT create a single file in the generic `docs/` root.
 
 **Orchestrated Mode:**

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.cursor.md

@@ -11,7 +11,7 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
-  compatible_harnesses: "cursor,codex,zed,opencode"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
 
@@ -93,6 +93,8 @@ When generating the final PRD, follow this exact structure:
 ```markdown
 # PRD: {Feature Name}
 
+Version: 0.1.0
+
 ## 1. Overview
 Brief summary of the feature.
 
@@ -145,13 +147,11 @@ Then
 ## 6. Output Location & Format
 
 **Direct Mode:**
-- You MUST follow `rules/core/documentation-management.mdc` for the `requirements` category.
+- You MUST follow `rules/core/requirements-package-standard.mdc` (via `rules/core/documentation-management.mdc` for the `requirements` category).
 - Before saving, ASK the user to confirm the feature name (`<name>`) or to suggest a custom path.
-- The default target path is: `<current_project_root>/docs/requirements/<name>-<YYYY-MM-DD>/`
-- You MUST generate 3 synchronized language variants:
-  - `ru/<name>.md` (Russian for humans)
-  - `en/<name>.md` (English for humans)
-  - `ai/<name>.md` (AI-readable format, heavily using Gherkin)
+- The default target path is: `<current_project_root>/docs/requirements/<name>/prd.md` — no date-stamped folder.
+- If the requirements package (`README.md`, `prd.md`, `specification.md`) does not exist yet, create it; otherwise update `prd.md` in place and bump its `Version` field rather than creating a parallel copy.
+- Default to a single document in the project's documentation language (`en` unless the project states otherwise). Generate additional language variants only when the user explicitly asks for them, and keep any variants you create synchronized.
 - You MUST NOT create a single file in the generic `docs/` root.
 
 **Orchestrated Mode:**

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.md

@@ -11,7 +11,7 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
-  compatible_harnesses: "cursor,codex,zed,opencode"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
 
@@ -93,6 +93,8 @@ When generating the final PRD, follow this exact structure:
 ```markdown
 # PRD: {Feature Name}
 
+Version: 0.1.0
+
 ## 1. Overview
 Brief summary of the feature.
 
@@ -145,13 +147,11 @@ Then
 ## 6. Output Location & Format
 
 **Direct Mode:**
-- You MUST follow `rules/core/documentation-management.mdc` for the `requirements` category.
+- You MUST follow `rules/core/requirements-package-standard.mdc` (via `rules/core/documentation-management.mdc` for the `requirements` category).
 - Before saving, ASK the user to confirm the feature name (`<name>`) or to suggest a custom path.
-- The default target path is: `<current_project_root>/docs/requirements/<name>-<YYYY-MM-DD>/`
-- You MUST generate 3 synchronized language variants:
-  - `ru/<name>.md` (Russian for humans)
-  - `en/<name>.md` (English for humans)
-  - `ai/<name>.md` (AI-readable format, heavily using Gherkin)
+- The default target path is: `<current_project_root>/docs/requirements/<name>/prd.md` — no date-stamped folder.
+- If the requirements package (`README.md`, `prd.md`, `specification.md`) does not exist yet, create it; otherwise update `prd.md` in place and bump its `Version` field rather than creating a parallel copy.
+- Default to a single document in the project's documentation language (`en` unless the project states otherwise). Generate additional language variants only when the user explicitly asks for them, and keep any variants you create synchronized.
 - You MUST NOT create a single file in the generic `docs/` root.
 
 **Orchestrated Mode:**

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.opencode.md

@@ -11,7 +11,7 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
-  compatible_harnesses: "cursor,codex,zed,opencode"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
 
@@ -93,6 +93,8 @@ When generating the final PRD, follow this exact structure:
 ```markdown
 # PRD: {Feature Name}
 
+Version: 0.1.0
+
 ## 1. Overview
 Brief summary of the feature.
 
@@ -145,13 +147,11 @@ Then
 ## 6. Output Location & Format
 
 **Direct Mode:**
-- You MUST follow `rules/core/documentation-management.mdc` for the `requirements` category.
+- You MUST follow `rules/core/requirements-package-standard.mdc` (via `rules/core/documentation-management.mdc` for the `requirements` category).
 - Before saving, ASK the user to confirm the feature name (`<name>`) or to suggest a custom path.
-- The default target path is: `<current_project_root>/docs/requirements/<name>-<YYYY-MM-DD>/`
-- You MUST generate 3 synchronized language variants:
-  - `ru/<name>.md` (Russian for humans)
-  - `en/<name>.md` (English for humans)
-  - `ai/<name>.md` (AI-readable format, heavily using Gherkin)
+- The default target path is: `<current_project_root>/docs/requirements/<name>/prd.md` — no date-stamped folder.
+- If the requirements package (`README.md`, `prd.md`, `specification.md`) does not exist yet, create it; otherwise update `prd.md` in place and bump its `Version` field rather than creating a parallel copy.
+- Default to a single document in the project's documentation language (`en` unless the project states otherwise). Generate additional language variants only when the user explicitly asks for them, and keep any variants you create synchronized.
 - You MUST NOT create a single file in the generic `docs/` root.
 
 **Orchestrated Mode:**

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.zed.md

@@ -11,7 +11,7 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
-  compatible_harnesses: "cursor,codex,zed,opencode"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
 
@@ -93,6 +93,8 @@ When generating the final PRD, follow this exact structure:
 ```markdown
 # PRD: {Feature Name}
 
+Version: 0.1.0
+
 ## 1. Overview
 Brief summary of the feature.
 
@@ -145,13 +147,11 @@ Then
 ## 6. Output Location & Format
 
 **Direct Mode:**
-- You MUST follow `rules/core/documentation-management.mdc` for the `requirements` category.
+- You MUST follow `rules/core/requirements-package-standard.mdc` (via `rules/core/documentation-management.mdc` for the `requirements` category).
 - Before saving, ASK the user to confirm the feature name (`<name>`) or to suggest a custom path.
-- The default target path is: `<current_project_root>/docs/requirements/<name>-<YYYY-MM-DD>/`
-- You MUST generate 3 synchronized language variants:
-  - `ru/<name>.md` (Russian for humans)
-  - `en/<name>.md` (English for humans)
-  - `ai/<name>.md` (AI-readable format, heavily using Gherkin)
+- The default target path is: `<current_project_root>/docs/requirements/<name>/prd.md` — no date-stamped folder.
+- If the requirements package (`README.md`, `prd.md`, `specification.md`) does not exist yet, create it; otherwise update `prd.md` in place and bump its `Version` field rather than creating a parallel copy.
+- Default to a single document in the project's documentation language (`en` unless the project states otherwise). Generate additional language variants only when the user explicitly asks for them, and keep any variants you create synchronized.
 - You MUST NOT create a single file in the generic `docs/` root.
 
 **Orchestrated Mode:**

package/src/gdskills/bundled/skills/platform/claude-md-management/SKILL.codex.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "configuration"
+  category: "platform"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/platform/claude-md-management/SKILL.cursor.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "configuration"
+  category: "platform"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/platform/claude-md-management/SKILL.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "configuration"
+  category: "platform"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/platform/hookify/SKILL.codex.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "configuration"
+  category: "platform"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/platform/hookify/SKILL.cursor.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "configuration"
+  category: "platform"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/platform/hookify/SKILL.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "configuration"
+  category: "platform"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/changelog/SKILL.codex.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "workflow"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/changelog/SKILL.cursor.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "workflow"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/changelog/SKILL.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "workflow"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/commit/SKILL.codex.md

@@ -9,7 +9,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "workflow"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
@@ -29,7 +29,7 @@ Create well-structured git commits from current changes.
 If nothing is staged, intelligently stage relevant files:
 - Stage modified and new files that are part of the logical change
 - **NEVER** stage `.env`, credentials, secrets, or large binary files
-- Prefer `git add <specific files>` over `git add -A`
+- Stage explicit pathspecs (`git add <specific files>`); **NEVER** `git add -A`, `--all`, or `.`
 - Ask the user before staging untracked files that look unrelated to recent work
 
 ### Phase 3: Generate Commit Message

package/src/gdskills/bundled/skills/quality/commit/SKILL.cursor.md

@@ -9,7 +9,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "workflow"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
@@ -29,7 +29,7 @@ Create well-structured git commits from current changes.
 If nothing is staged, intelligently stage relevant files:
 - Stage modified and new files that are part of the logical change
 - **NEVER** stage `.env`, credentials, secrets, or large binary files
-- Prefer `git add <specific files>` over `git add -A`
+- Stage explicit pathspecs (`git add <specific files>`); **NEVER** `git add -A`, `--all`, or `.`
 - Ask the user before staging untracked files that look unrelated to recent work
 
 ### Phase 3: Generate Commit Message

package/src/gdskills/bundled/skills/quality/commit/SKILL.md

@@ -9,7 +9,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "workflow"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---
@@ -29,7 +29,7 @@ Create well-structured git commits from current changes.
 If nothing is staged, intelligently stage relevant files:
 - Stage modified and new files that are part of the logical change
 - **NEVER** stage `.env`, credentials, secrets, or large binary files
-- Prefer `git add <specific files>` over `git add -A`
+- Stage explicit pathspecs (`git add <specific files>`); **NEVER** `git add -A`, `--all`, or `.`
 - Ask the user before staging untracked files that look unrelated to recent work
 
 ### Phase 3: Generate Commit Message

package/src/gdskills/bundled/skills/quality/db-migrate/SKILL.codex.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "database"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/db-migrate/SKILL.cursor.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "database"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/db-migrate/SKILL.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "database"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/dependency-update/SKILL.codex.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "maintenance"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/dependency-update/SKILL.cursor.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "maintenance"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---

package/src/gdskills/bundled/skills/quality/dependency-update/SKILL.md

@@ -10,7 +10,7 @@ triggers:
 metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
-  category: "maintenance"
+  category: "quality"
   compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
 ---