@orderful/droid 0.25.2 → 0.27.0

package/src/tools/tech-design/skills/tech-design/references/thought-doc-template.md

@@ -0,0 +1,72 @@
+# Thought Doc Template
+
+Used when creating thought doc via `/brain plan tech-design-{project}`.
+
+```markdown
+# [Tech Design] {Project Name}
+
+**Type:** plan
+**Status:** exploring
+**Created:** {YYYY-MM-DD}
+**PRD:** [[codex:projects/{project}/PRD]]
+**Research:** [[tech-design-{project}-research]]
+
+Tech design for {project}.
+
+## Background
+
+{Why we're doing this - 2-3 paragraphs from PRD}
+
+{What problem we're solving, who it's for, why it matters}
+
+See research doc for codebase context and discovered patterns.
+
+## Proposal
+
+{What we're building - to be drafted}
+
+## Open Questions
+
+{What we don't know yet - to be explored}
+```
+
+## Variable Substitutions
+
+| Variable         | Example                 | Notes                       |
+| ---------------- | ----------------------- | --------------------------- |
+| `{Project Name}` | "Transaction Templates" | Human-readable project name |
+| `{YYYY-MM-DD}`   | "2026-01-10"            | Current date                |
+| `{project}`      | "transaction-templates" | Codex project slug          |
+
+## Philosophy
+
+**Start minimal:** 3 sections (Background, Proposal, Open Questions)
+
+**Gaps surface more:** Use `/tech-design gaps` to discover what sections to add (Data Model, API Surface, Rollout Plan, etc.)
+
+**Research doc separation:** The thought doc references the research doc but doesn't duplicate codebase discoveries. Keep the thought doc focused on architectural decisions.
+
+## Sections That Can Be Added
+
+Via `/tech-design draft {section}` or `/tech-design gaps`:
+
+- **Scope** - What's in/out explicitly
+- **Data Model** - Tables, schemas, types
+- **API Surface** - Endpoints, methods, interfaces
+- **Implementation Plan** - Step-by-step approach
+- **Key Decisions** - Options considered, what we chose and why
+- **Trade-off Analysis** - Pros/cons of approach
+- **Risks & Mitigations** - What could go wrong, how to handle it
+- **Metrics** - What we'll measure
+- **Rollout Plan** - Phased deployment, feature flags, rollback
+- **Security Considerations** - Auth, validation, audit logging
+
+## Template Evolution
+
+The template starts with 3 sections, but the thought doc grows based on:
+
+1. **User adds via `/draft {section}`** - AI generates section from research
+2. **User explores via `/think {topic}`** - May add sections organically
+3. **User identifies via `/gaps`** - Shows what's missing, suggests adding
+
+The minimal start reduces cognitive load. Sections appear when needed.

package/dist/tools/code-review/skills/droid-code-review/SKILL.md

@@ -1,55 +0,0 @@
----
-name: droid-code-review
-description: "Comprehensive code review using specialized agents. Use when reviewing PRs, checking staged changes, or analysing code quality. User prompts like 'review this PR', 'check my changes', 'review before I commit'."
-globs:
-  - "**/*"
-alwaysApply: false
-allowed-tools: Read, Grep, Glob, Bash, Task
----
-
-# Code Review Skill
-
-Run comprehensive code reviews using specialized agents, each focused on a specific concern.
-
-## How It Works
-
-The `/code-review` command orchestrates multiple specialized agents in parallel:
-
-1. **edi-standards-reviewer** - EDI patterns, partnership handling, billing concerns
-2. **test-coverage-analyzer** - Test completeness and edge cases
-3. **error-handling-reviewer** - Silent failures, missing error handling
-4. **type-reviewer** - TypeScript type design, interface contracts
-
-Each agent returns issues with confidence scores (0-100). Issues below 80% confidence are filtered out to reduce noise.
-
-## Usage
-
-```bash
-/code-review #123           # Review PR #123
-/code-review staged         # Review staged changes
-/code-review branch         # Review current branch vs main
-/code-review path/to/file   # Review specific file
-```
-
-## Output Format
-
-Reviews are presented in prioritized categories:
-
-🔴 **Critical** - Security, data loss, billing errors
-🟠 **Important** - Bugs, missing tests, type issues
-🟡 **Suggestions** - Style, readability improvements
-
-## Post-Review Actions
-
-After presenting findings, you can:
-- Post the review as a PR comment
-- Get suggested fixes for specific issues
-- Check out the branch and fix critical issues
-
-## Domain-Aware Reviews
-
-The EDI Standards Reviewer discovers project conventions by reading:
-- `.claude/CLAUDE.md` or `CLAUDE.md` for team conventions
-- `AGENTS.md` or `docs/` for architecture guidance
-
-This lets it apply your project's specific patterns rather than generic rules.

package/dist/tools/codex/skills/droid-codex/scripts/git-finish-write.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"git-finish-write.d.ts","sourceRoot":"","sources":["../../../../../../src/tools/codex/skills/droid-codex/scripts/git-finish-write.ts"],"names":[],"mappings":";AACA;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG"}

package/dist/tools/codex/skills/droid-codex/scripts/git-preamble.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"git-preamble.d.ts","sourceRoot":"","sources":["../../../../../../src/tools/codex/skills/droid-codex/scripts/git-preamble.ts"],"names":[],"mappings":";AACA;;;;;;;;;;;;;;;;GAgBG"}

package/dist/tools/codex/skills/droid-codex/scripts/git-start-write.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"git-start-write.d.ts","sourceRoot":"","sources":["../../../../../../src/tools/codex/skills/droid-codex/scripts/git-start-write.ts"],"names":[],"mappings":";AACA;;;;;;;;;;;;;;;;;;;GAmBG"}

package/src/tools/code-review/skills/droid-code-review/SKILL.md

@@ -1,55 +0,0 @@
----
-name: droid-code-review
-description: "Comprehensive code review using specialized agents. Use when reviewing PRs, checking staged changes, or analysing code quality. User prompts like 'review this PR', 'check my changes', 'review before I commit'."
-globs:
-  - "**/*"
-alwaysApply: false
-allowed-tools: Read, Grep, Glob, Bash, Task
----
-
-# Code Review Skill
-
-Run comprehensive code reviews using specialized agents, each focused on a specific concern.
-
-## How It Works
-
-The `/code-review` command orchestrates multiple specialized agents in parallel:
-
-1. **edi-standards-reviewer** - EDI patterns, partnership handling, billing concerns
-2. **test-coverage-analyzer** - Test completeness and edge cases
-3. **error-handling-reviewer** - Silent failures, missing error handling
-4. **type-reviewer** - TypeScript type design, interface contracts
-
-Each agent returns issues with confidence scores (0-100). Issues below 80% confidence are filtered out to reduce noise.
-
-## Usage
-
-```bash
-/code-review #123           # Review PR #123
-/code-review staged         # Review staged changes
-/code-review branch         # Review current branch vs main
-/code-review path/to/file   # Review specific file
-```
-
-## Output Format
-
-Reviews are presented in prioritized categories:
-
-🔴 **Critical** - Security, data loss, billing errors
-🟠 **Important** - Bugs, missing tests, type issues
-🟡 **Suggestions** - Style, readability improvements
-
-## Post-Review Actions
-
-After presenting findings, you can:
-- Post the review as a PR comment
-- Get suggested fixes for specific issues
-- Check out the branch and fix critical issues
-
-## Domain-Aware Reviews
-
-The EDI Standards Reviewer discovers project conventions by reading:
-- `.claude/CLAUDE.md` or `CLAUDE.md` for team conventions
-- `AGENTS.md` or `docs/` for architecture guidance
-
-This lets it apply your project's specific patterns rather than generic rules.