oh-my-githubcopilot 1.8.1 → 2.0.0-alpha.1cd01f4

package/skills/ultragoal/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: ultragoal
+description: Durable goal ledger in .omp/ultragoal/ with fail-closed checkpoints
+trigger: "ultragoal:, /ultragoal, /omp:ultragoal"
+autoinvoke: false
+---
+# Skill: UltraGoal
+
+## Metadata
+
+| Field | Value |
+|-------|-------|
+| **ID** | `ultragoal` |
+| **Keywords** | `ultragoal:`, `/ultragoal` |
+| **Tier** | Planning Tool |
+| **Source** | `src/skills/ultragoal.mts` |
+
+## Description
+
+Durable goal ledger that persists goals in `.omp/ultragoal/goals.json` with fail-closed checkpoints. Goals survive session restarts and context resets. Each goal is assigned an ID, status, and creation timestamp. Supports adding new goals, listing current goals, and marking goals complete or failed.
+
+## Interface
+
+```typescript
+interface SkillInput { trigger: string; args: string[]; }
+interface SkillOutput { status: "ok" | "error"; message: string; }
+export async function activate(input: SkillInput): Promise<SkillOutput>
+export function deactivate(): void
+```
+
+## Implementation
+
+Activates the `ultragoal` mode by spawning `bin/omp.mjs ultragoal [args]`. The CLI handler creates or reads `.omp/ultragoal/goals.json`, adds new goals from args, and prints the current goal list. No persistent resources are maintained by the skill itself.

package/skills/ultraqa/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: ultraqa
+description: QA cycle loop with qa-tester agent; runs until all checks pass
+trigger: "ultraqa:, /ultraqa, /omp:ultraqa"
+autoinvoke: false
+---
+# Skill: UltraQA
+
+## Metadata
+
+| Field | Value |
+|-------|-------|
+| **ID** | `ultraqa` |
+| **Keywords** | `ultraqa:`, `/ultraqa` |
+| **Tier** | Execution Mode |
+| **Source** | `src/skills/ultraqa.mts` |
+
+## Description
+
+QA cycle loop that runs the qa-tester agent repeatedly until all acceptance criteria pass. Each iteration executes the test suite, collects failures, and routes remediation tasks back through the execution pipeline. Exits only when all checks are green or the maximum iteration count is reached.
+
+## Interface
+
+```typescript
+interface SkillInput { trigger: string; args: string[]; }
+interface SkillOutput { status: "ok" | "error"; message: string; }
+export async function activate(input: SkillInput): Promise<SkillOutput>
+export function deactivate(): void
+```
+
+## Implementation
+
+Activates the `ultraqa` orchestration mode by spawning `bin/omp.mjs ultraqa [args]`. Drives the `@qa-tester` agent in a loop with the execution pipeline until all checks pass. No persistent resources are maintained.

package/skills/verify/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: verify
+description: Evidence-based completion check via verifier agent
+trigger: "verify:, /verify, /omp:verify"
+autoinvoke: false
+---
+# Skill: Verify
+
+## Metadata
+
+| Field | Value |
+|-------|-------|
+| **ID** | `verify` |
+| **Keywords** | `verify:`, `/verify` |
+| **Tier** | Planning Tool |
+| **Source** | `src/skills/verify.mts` |
+
+## Description
+
+Evidence-based completion check that routes to the verifier agent. Inspects current work against acceptance criteria, runs any defined test suites, and produces a structured pass/fail report with citations.
+
+## Interface
+
+```typescript
+interface SkillInput { trigger: string; args: string[]; }
+interface SkillOutput { status: "ok" | "error"; message: string; }
+export async function activate(input: SkillInput): Promise<SkillOutput>
+export function deactivate(): void
+```
+
+## Implementation
+
+Activates the `verify` orchestration mode by spawning `bin/omp.mjs verify [args]`. Delegates to the verifier agent which checks completion evidence. No persistent resources are maintained.

package/skills/visual-verdict/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: visual-verdict
+description: Visual diff/screenshot comparison verdict
+trigger: "visual-verdict:, /visual-verdict, /omp:visual-verdict"
+autoinvoke: false
+---
+# Skill: Visual Verdict
+
+## Metadata
+
+| Field | Value |
+|-------|-------|
+| **ID** | `visual-verdict` |
+| **Keywords** | `visual-verdict:`, `/visual-verdict` |
+| **Tier** | QA Tool |
+| **Source** | `src/skills/visual-verdict.mts` |
+
+## Description
+
+Compares visual diffs or screenshots to render a pass/fail verdict. Accepts before/after image paths or URLs, runs a pixel-level diff, and produces a structured verdict with diff percentage, bounding boxes of changed regions, and a human-readable summary.
+
+## Interface
+
+```typescript
+interface SkillInput { trigger: string; args: string[]; }
+interface SkillOutput { status: "ok" | "error"; message: string; }
+export async function activate(input: SkillInput): Promise<SkillOutput>
+export function deactivate(): void
+```
+
+## Implementation
+
+Extension-only skill. Triggers visual diff comparison in Copilot. The CLI prints guidance directing users to the Copilot CLI slash command.
+
+> **P3 scope:** Integration with Playwright screenshot capture and CI diff reporting (as specified in SPEC-omp-2.0 §5) are deferred to P3. The current implementation accepts user-supplied image paths only.

package/skills/web-clone/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: web-clone
+description: Clone and adapt a web page/design to the codebase
+trigger: "web-clone:, /web-clone, /omp:web-clone"
+autoinvoke: false
+---
+# Skill: Web-Clone
+
+## Metadata
+
+| Field | Value |
+|-------|-------|
+| **ID** | `web-clone` |
+| **Keywords** | `web-clone:`, `/web-clone` |
+| **Tier** | Frontend Tool |
+| **Source** | `src/skills/web-clone.mts` |
+
+## Description
+
+Clones a web page or design reference and adapts it to the project's codebase. Accepts a URL or screenshot, extracts the visual structure and content, and generates framework-appropriate components that match the existing project conventions. Handles responsive layouts, typography, colour schemes, and interactive elements.
+
+## Interface
+
+```typescript
+interface SkillInput { trigger: string; args: string[]; }
+interface SkillOutput { status: "ok" | "error"; message: string; }
+export async function activate(input: SkillInput): Promise<SkillOutput>
+export function deactivate(): void
+```
+
+## Implementation
+
+Extension-only skill. Triggers web page cloning and adaptation in Copilot. The CLI prints guidance directing users to the Copilot CLI slash command.
+
+> **P3 scope:** Live browser puppeteer crawl, asset extraction, and animation cloning (as specified in SPEC-omp-2.0 §5) are deferred to P3. The current implementation accepts URL or screenshot input and generates static component output.

package/skills/writer-memory/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: writer-memory
+description: Writing style memory — stores voice/tone preferences
+trigger: "writer-memory:, /writer-memory, /omp:writer-memory"
+autoinvoke: false
+---
+# Skill: Writer Memory
+
+## Metadata
+
+| Field | Value |
+|-------|-------|
+| **ID** | `writer-memory` |
+| **Keywords** | `writer-memory:`, `/writer-memory` |
+| **Tier** | Memory Tool |
+| **Source** | `src/skills/writer-memory.mts` |
+
+## Description
+
+Stores and retrieves writing style preferences, voice, and tone guidelines in `.omp/writer-memory.md`. Use `omp writer-memory <style-note>` to append a new style note, or `omp writer-memory` (no args) to print the current style guide. These preferences persist across sessions and are available to writer and document-specialist agents.
+
+## Interface
+
+```typescript
+interface SkillInput { trigger: string; args: string[]; }
+interface SkillOutput { status: "ok" | "error"; message: string; }
+export async function activate(input: SkillInput): Promise<SkillOutput>
+export function deactivate(): void
+```
+
+## Implementation
+
+Real CLI logic: `omp writer-memory <style-note>` appends the note to `.omp/writer-memory.md`. `omp writer-memory` prints the current file content. Extension-side reads and injects the style guide into the agent context.
+
+> **Note:** Concurrent appends from multiple Copilot sessions are safe for entries ≤ 4KB (POSIX `O_APPEND` atomicity), but may interleave for larger entries. Single-session usage is fully safe.
+
+> **P3 scope:** Full character/relationship/scene/theme tracking (as specified in SPEC-omp-2.0 §3) is deferred to P3. The current implementation provides voice/tone preference storage only.

package/agents/orchestrator.agent.md

@@ -1,26 +0,0 @@
----
-name: orchestrator
-description: >
-  Top-level coordinator for OMP sessions.
-  Use when: you need full orchestration — receives requests, selects agents, delegates work, verifies outcomes.
-model: claude-opus-4-6
-tools: [readFile, search, codebase]
-agents: [executor, architect, planner, verifier, writer, reviewer, designer, researcher, tester, debugger, security-reviewer, simplifier, test-engineer, critic, tracer, scientist, code-reviewer, document-specialist, qa-tester, git-master, analyst, explorer]
-user-invocable: true
----
-
-# Orchestrator
-
-## Role
-The brain of the OMP system. Analyzes requests, selects the appropriate specialized agent, delegates work, and verifies outcomes.
-
-## Responsibilities
-- Route every request to the most appropriate agent
-- Verify agent output before surfacing to user
-- Enforce delegation rules and model tier selection
-- Track context budget and trigger HUD/eco mode as needed
-
-## Constraints
-- NEVER writes code, docs, or configs directly
-- ALWAYS delegates to a specialized agent
-- ALWAYS verifies before claiming completion

package/agents/researcher.agent.md

@@ -1,18 +0,0 @@
----
-name: researcher
-description: >
-  External knowledge researcher for SDK docs, library references, and technology comparisons.
-  Use when: looking up external docs, comparing libraries, researching APIs.
-model: claude-sonnet-4-6
-tools: [readFile, search, fetch]
-agents: []
-user-invocable: true
----
-
-# Researcher
-
-## Role
-Find and synthesize external knowledge: SDK docs, library references, API docs, dependency information, technology comparisons.
-
-## Constraints
-- READ-ONLY. Does not implement — finds and summarizes.

package/agents/reviewer.agent.md

@@ -1,23 +0,0 @@
----
-name: reviewer
-description: >
-  Code quality reviewer and style enforcer.
-  Use when: code review, style enforcement, catching bugs before merge.
-model: claude-opus-4-6
-tools: [readFile, search, codebase, usages, problems]
-agents: [explore]
-user-invocable: true
----
-
-# Reviewer
-
-## Role
-Thorough code reviews: enforce style, catch bugs, identify quality issues, and gate merges.
-
-## Responsibilities
-- Style enforcement and pattern consistency
-- Bug identification with LSP precision
-- Merge gate verdicts
-
-## NOT Responsible For
-- Implementing fixes (→ executor)

package/agents/tester.agent.md

@@ -1,20 +0,0 @@
----
-name: tester
-description: >
-  Test author and coverage analyzer.
-  Use when: writing unit tests, executing test suites, analyzing coverage, CI integration.
-model: claude-sonnet-4-6
-tools: [readFile, editFiles, runInTerminal, findTestFiles, testFailures]
-agents: [explore]
-user-invocable: true
----
-
-# Tester
-
-## Role
-Author tests, execute test suites, analyze coverage, and integrate tests into CI pipelines.
-
-## Responsibilities
-- Unit and integration test authoring
-- Coverage analysis and gap identification
-- CI pipeline integration