claudecode-omc 5.4.0 → 5.5.0

package/bundled/upstream/oh-my-claudecode/skills/self-improve/templates/harness.md

@@ -0,0 +1,18 @@
+# Harness Rules
+
+## H001 — One Hypothesis Per Plan
+Each plan must test exactly ONE hypothesis. Plans with zero or multiple hypotheses are rejected by the critic.
+
+## H002 — No Approach Family Streak
+The same `approach_family` must not appear as the winner for 3 or more consecutive iterations. This prevents the system from getting stuck in a local exploration loop.
+
+## H003 — Intra-Round Diversity
+Within a single round, no two plans may share the same `approach_family`. The critic rejects the later plan if a duplicate family is detected.
+
+## Custom Rules
+<!-- Add project-specific rules here -->
+
+## Custom Approach Families
+<!-- Add custom approach families here (one per line, prefixed with - or *) -->
+<!-- Example: -->
+<!-- - `prompt_engineering` -->

package/bundled/upstream/oh-my-claudecode/skills/self-improve/templates/idea.md

@@ -0,0 +1,5 @@
+# Experiment Ideas
+
+<!-- Add your experiment ideas here. These will be given highest priority by the planners. -->
+<!-- Format: one idea per section with a title and description. -->
+<!-- Ideas are consumed once per iteration and cleared after planners read them. -->

package/bundled/upstream/oh-my-claudecode/skills/self-improve/templates/settings.json

@@ -0,0 +1,23 @@
+{
+  "si_claude_setting": false,
+  "number_of_agents": 3,
+  "number_of_max_critics": 3,
+  "current_repo_url": "",
+  "fork_url": "",
+  "upstream_url": "",
+  "topic_slug": "default",
+  "target_branch": "main",
+  "benchmark_command": "",
+  "benchmark_format": "json",
+  "benchmark_direction": "higher_is_better",
+  "max_iterations": 50,
+  "plateau_threshold": 0.01,
+  "plateau_window": 3,
+  "target_value": null,
+  "primary_metric": "primary",
+  "sealed_files": [],
+  "regression_threshold": 0.05,
+  "circuit_breaker_threshold": 3,
+  "auto_push": false,
+  "auto_pr": false
+}

package/bundled/upstream/oh-my-claudecode/skills/skill/SKILL.md

@@ -2,6 +2,7 @@
 name: skill
 description: Manage local skills - list, add, remove, search, edit, setup wizard
 argument-hint: "<command> [args]"
+level: 2
 ---
 
 # Skill Management CLI
@@ -12,18 +13,23 @@ Meta-skill for managing oh-my-claudecode skills via CLI-like commands.
 
 ### /skill list
 
-Show all local skills organized by scope.
+Show all available skills organized by scope.
 
 **Behavior:**
-1. Scan user skills at `~/.omc/skills/` (preferred)
-2. Scan legacy user skills at `~/.claude/skills/omc-learned/` (compatibility)
+1. Scan bundled built-in skills in the plugin `skills/` directory (read-only)
+2. Scan user skills at `${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/`
 3. Scan project skills at `.omc/skills/`
-4. Scan builtin plugin skills at `~/.claude/plugins/oh-my-claudecode/skills/`
-5. Parse YAML frontmatter for metadata
-6. Display in organized table format:
+4. Parse YAML frontmatter for metadata
+5. Display in organized table format:
 
 ```
-USER SKILLS (~/.omc/skills + ~/.claude/skills/omc-learned):
+BUILT-IN SKILLS (bundled with oh-my-claudecode):
+| Name              | Description                    | Scope    |
+|-------------------|--------------------------------|----------|
+| visual-verdict    | Structured visual QA verdicts  | built-in |
+| ralph             | Persistence loop               | built-in |
+
+USER SKILLS (~/.claude/skills/omc-learned/):
 | Name              | Triggers           | Quality | Usage | Scope |
 |-------------------|--------------------|---------|-------|-------|
 | error-handler     | fix, error         | 95%     | 42    | user  |
@@ -33,16 +39,12 @@ PROJECT SKILLS (.omc/skills/):
 | Name              | Triggers           | Quality | Usage | Scope   |
 |-------------------|--------------------|---------|-------|---------|
 | test-runner       | test, run          | 92%     | 15    | project |
-
-BUILTIN SKILLS (~/.claude/plugins/oh-my-claudecode/skills):
-| Name              | Source  | Scope   |
-|-------------------|---------|---------|
-| omc-setup         | plugin  | builtin |
-| code-review       | plugin  | builtin |
 ```
 
 **Fallback:** If quality/usage stats not available, show "N/A"
 
+**Built-in skill note:** Built-in skills are bundled with oh-my-claudecode and are discoverable/readable, but not removed or edited through `/skill remove` or `/skill edit`.
+
 ---
 
 ### /skill add [name]
@@ -59,8 +61,8 @@ Interactive wizard for creating a new skill.
 4. **Ask for argument hint** (optional)
    - Example: "<file> [options]"
 5. **Ask for scope:**
-   - `user` → `~/.omc/skills/<name>.md` (fallback: `~/.claude/skills/omc-learned/<name>.md`)
-   - `project` → `.omc/skills/<name>.md`
+   - `user` → `${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<name>/SKILL.md`
+   - `project` → `.omc/skills/<name>/SKILL.md`
 6. **Create skill file** with template:
 
 ```yaml
@@ -113,7 +115,7 @@ Triggers (comma-separated): log, logger, logging
 Argument hint (optional): <level> [message]
 Scope (user/project): user
 
-✓ Created skill at ~/.omc/skills/custom-logger.md
+✓ Created skill at ~/.claude/skills/omc-learned/custom-logger/SKILL.md
 → Edit with: /skill edit custom-logger
 ```
 
@@ -125,13 +127,13 @@ Remove a skill by name.
 
 **Behavior:**
 1. **Search for skill** in both scopes:
-   - `~/.omc/skills/<name>.md` and `~/.claude/skills/omc-learned/<name>.md`
-   - `.omc/skills/<name>.md`
+   - `${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<name>/SKILL.md`
+   - `.omc/skills/<name>/SKILL.md`
 2. **If found:**
    - Display skill info (name, description, scope)
    - **Ask for confirmation:** "Delete '<name>' skill from <scope>? (yes/no)"
 3. **If confirmed:**
-   - Delete the matching skill file (e.g., `~/.omc/skills/<name>.md`)
+   - Delete entire skill directory (e.g., `${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<name>/`)
    - Report: "✓ Removed skill '<name>' from <scope>"
 4. **If not found:**
    - Report: "✗ Skill '<name>' not found in user or project scope"
@@ -143,7 +145,7 @@ Remove a skill by name.
 User: /skill remove old-logger
 Assistant: Found skill 'old-logger' in user scope:
   Description: Legacy logging utility
-  Scope: user (~/.omc/skills/)
+  Scope: user (~/.claude/skills/omc-learned/)
 
 Delete 'old-logger' skill? (yes/no)
 
@@ -259,13 +261,13 @@ Show detailed information about a skill.
 
 ```
 Skill: custom-logger
-Scope: user (~/.omc/skills/custom-logger.md)
+Scope: user (~/.claude/skills/omc-learned/custom-logger/)
 Description: Enhanced logging with structured output
 Triggers: log, logger, logging
 Argument Hint: <level> [message]
 Quality: 95% (if available)
 Usage Count: 42 times (if available)
-File Path: /home/user/.omc/skills/custom-logger.md
+File Path: /home/user/.claude/skills/omc-learned/custom-logger/SKILL.md
 
 --- FULL CONTENT ---
 [entire markdown content]
@@ -280,7 +282,7 @@ Assistant: Skill: custom-logger
 Scope: user
 Description: Enhanced logging with structured output
 Triggers: log, logger, logging
-File: ~/.omc/skills/custom-logger.md
+File: ~/.claude/skills/omc-learned/custom-logger/SKILL.md
 
 --- CONTENT ---
 # Custom Logger Skill
@@ -298,7 +300,7 @@ Sync skills between user and project scopes.
 
 **Behavior:**
 1. **Scan both scopes:**
-   - User skills: `~/.omc/skills/` and `~/.claude/skills/omc-learned/`
+   - User skills: `${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/`
    - Project skills: `.omc/skills/`
 2. **Compare and categorize:**
    - User-only skills (not in project)
@@ -367,9 +369,8 @@ Interactive wizard for setting up and managing local skills (formerly local-skil
 First, check if skill directories exist and create them if needed:
 
 ```bash
-# Check and create user-level skills directories (preferred + legacy)
-USER_SKILLS_DIR="$HOME/.omc/skills"
-LEGACY_USER_SKILLS_DIR="$HOME/.claude/skills/omc-learned"
+# Check and create user-level skills directory
+USER_SKILLS_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned"
 if [ -d "$USER_SKILLS_DIR" ]; then
   echo "User skills directory exists: $USER_SKILLS_DIR"
 else
@@ -377,13 +378,6 @@ else
   echo "Created user skills directory: $USER_SKILLS_DIR"
 fi
 
-if [ -d "$LEGACY_USER_SKILLS_DIR" ]; then
-  echo "Legacy user skills directory exists: $LEGACY_USER_SKILLS_DIR"
-else
-  mkdir -p "$LEGACY_USER_SKILLS_DIR"
-  echo "Created legacy user skills directory: $LEGACY_USER_SKILLS_DIR"
-fi
-
 # Check and create project-level skills directory
 PROJECT_SKILLS_DIR=".omc/skills"
 if [ -d "$PROJECT_SKILLS_DIR" ]; then
@@ -399,34 +393,28 @@ fi
 Scan both directories and show a comprehensive inventory:
 
 ```bash
-# Scan user-level skills (preferred + legacy)
-echo "=== USER-LEVEL SKILLS (~/.omc/skills + ~/.claude/skills/omc-learned/) ==="
-USER_COUNT=0
-for USER_DIR in "$HOME/.omc/skills" "$HOME/.claude/skills/omc-learned"; do
-  if [ -d "$USER_DIR" ]; then
-    USER_COUNT=$((USER_COUNT + $(find "$USER_DIR" -name "*.md" 2>/dev/null | wc -l)))
-  fi
-done
-echo "Total skills: $USER_COUNT"
-
-if [ $USER_COUNT -gt 0 ]; then
-  echo ""
-  echo "Skills found:"
-  for USER_DIR in "$HOME/.omc/skills" "$HOME/.claude/skills/omc-learned"; do
-    [ -d "$USER_DIR" ] || continue
-    find "$USER_DIR" -name "*.md" -type f -exec sh -c '
+# Scan user-level skills
+echo "=== USER-LEVEL SKILLS (~/.claude/skills/omc-learned/) ==="
+if [ -d "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned" ]; then
+  USER_COUNT=$(find "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned" -name "*.md" 2>/dev/null | wc -l)
+  echo "Total skills: $USER_COUNT"
+
+  if [ $USER_COUNT -gt 0 ]; then
+    echo ""
+    echo "Skills found:"
+    find "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned" -name "*.md" -type f -exec sh -c '
       FILE="$1"
       NAME=$(grep -m1 "^name:" "$FILE" 2>/dev/null | sed "s/name: //")
       DESC=$(grep -m1 "^description:" "$FILE" 2>/dev/null | sed "s/description: //")
       MODIFIED=$(stat -c "%y" "$FILE" 2>/dev/null || stat -f "%Sm" "$FILE" 2>/dev/null)
-      [ -z "$NAME" ] && NAME=$(basename "$FILE" .md)
       echo "  - $NAME"
       [ -n "$DESC" ] && echo "    Description: $DESC"
-      echo "    File: $FILE"
       echo "    Modified: $MODIFIED"
       echo ""
     ' sh {} \;
-  done
+  fi
+else
+  echo "Directory not found"
 fi
 
 echo ""
@@ -453,19 +441,8 @@ else
   echo "Directory not found"
 fi
 
-# Scan builtin plugin skills (read-only)
-echo ""
-echo "=== BUILTIN SKILLS (~/.claude/plugins/oh-my-claudecode/skills/) ==="
-if [ -d "$HOME/.claude/plugins/oh-my-claudecode/skills" ]; then
-  BUILTIN_COUNT=$(find "$HOME/.claude/plugins/oh-my-claudecode/skills" -name "SKILL.md" 2>/dev/null | wc -l)
-  echo "Total skills: $BUILTIN_COUNT"
-else
-  BUILTIN_COUNT=0
-  echo "Directory not found (plugin may not be installed yet)"
-fi
-
 # Summary
-TOTAL=$((USER_COUNT + PROJECT_COUNT + BUILTIN_COUNT))
+TOTAL=$((USER_COUNT + PROJECT_COUNT))
 echo "=== SUMMARY ==="
 echo "Total skills across all directories: $TOTAL"
 ```
@@ -500,9 +477,8 @@ Ask user to provide either:
 - **Paste content**: Paste skill markdown content directly
 
 Then ask for scope:
-- **User-level** (~/.omc/skills/ preferred, ~/.claude/skills/omc-learned/ legacy) - Available across all projects
+- **User-level** (~/.claude/skills/omc-learned/) - Available across all projects
 - **Project-level** (.omc/skills/) - Only for this project
-- **Builtin** (~/.claude/plugins/oh-my-claudecode/skills/) - Plugin-provided, read-only
 
 Validate the skill format and save to the chosen location.
 
@@ -795,8 +771,7 @@ Good skills are:
 > /oh-my-claudecode:skill list
 
 Checking skill directories...
-✓ User skills directory exists: ~/.omc/skills/
-✓ Legacy user skills directory exists: ~/.claude/skills/omc-learned/
+✓ User skills directory exists: ~/.claude/skills/omc-learned/
 ✓ Project skills directory exists: .omc/skills/
 
 Scanning for skills...
@@ -821,14 +796,8 @@ Total skills: 5
     Description: When to clear TypeScript build cache to fix phantom errors
     Modified: 2026-01-21 11:28:37
 
-=== BUILTIN SKILLS ===
-Total skills: 37
-  - omc-setup
-  - code-review
-  - ultrawork
-
 === SUMMARY ===
-Total skills: 45
+Total skills: 8
 
 What would you like to do?
 1. Add new skill
@@ -845,7 +814,7 @@ What would you like to do?
 - Run `/oh-my-claudecode:skill list` periodically to review your skill library
 - After solving a tricky bug, immediately run learner to capture it
 - Use project-level skills for codebase-specific knowledge
-- Use user-level skills (`~/.omc/skills/`) for general patterns that apply everywhere
+- Use user-level skills for general patterns that apply everywhere
 - Review and refine triggers over time to improve matching accuracy
 
 ---

package/bundled/upstream/oh-my-claudecode/skills/skillify/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: skillify
+description: Turn a repeatable workflow from the current session into a reusable OMC skill draft
+---
+
+# Skillify
+
+Use this skill when the current session uncovered a repeatable workflow that should become a reusable OMC skill.
+
+## Goal
+Capture a successful multi-step workflow as a concrete skill draft instead of rediscovering it later.
+
+## Workflow
+1. Identify the repeatable task the session accomplished.
+2. Extract:
+   - inputs
+   - ordered steps
+   - success criteria
+   - constraints / pitfalls
+   - best target location for the skill
+3. Decide whether the workflow belongs as:
+   - a repo built-in skill
+   - a user/project learned skill
+   - documentation only
+4. When drafting a learned skill file, output a complete skill file that starts with YAML frontmatter.
+   - Never emit plain markdown-only skill files.
+   - Minimum frontmatter:
+     ```yaml
+     ---
+     name: <skill-name>
+     description: <one-line description>
+     triggers:
+       - <trigger-1>
+       - <trigger-2>
+     ---
+     ```
+   - Write learned/user/project skills to:
+     - `${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<skill-name>.md`
+     - `.omc/skills/<skill-name>.md`
+5. Draft the rest of the skill file with clear triggers, steps, and success criteria.
+6. Point out anything still too fuzzy to encode safely.
+
+## Rules
+- Only capture workflows that are actually repeatable.
+- Keep the skill practical and scoped.
+- Prefer explicit success criteria over vague prose.
+- If the workflow still has unresolved branching decisions, note them before drafting.
+
+## Output
+- Proposed skill name
+- Target location
+- Draft workflow structure
+- Open questions, if any

package/bundled/upstream/oh-my-claudecode/skills/team/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: team
 description: N coordinated agents on shared task list using Claude Code native teams
+argument-hint: "[N:agent-type] [ralph] <task description>"
 aliases: []
 level: 4
 ---
@@ -799,7 +800,7 @@ See Cancellation section below for details.
 
 If the lead crashes mid-run, the team skill should detect existing state and resume:
 
-1. Check `~/.claude/teams/` for teams matching the task slug
+1. Check `${CLAUDE_CONFIG_DIR:-~/.claude}/teams/` for teams matching the task slug
 2. If found, read `config.json` to discover active members
 3. Resume monitor mode instead of creating a duplicate team
 4. Call `TaskList` to determine current progress
@@ -871,26 +872,97 @@ When `OMC_TEAM_SCALING_ENABLED=1` is set, the team supports mid-session scaling:
 
 ## Configuration
 
-Optional settings via `.omc-config.json`:
+Optional settings live in `.claude/omc.jsonc` (project) or `~/.config/claude-omc/config.jsonc` (user). Project values override user values; `OMC_TEAM_ROLE_OVERRIDES` (env JSON) supersedes both.
 
-```json
+```jsonc
 {
   "team": {
-    "maxAgents": 20,
-    "defaultAgentType": "executor",
-    "monitorIntervalMs": 30000,
-    "shutdownTimeoutMs": 15000
+    "ops": {
+      "maxAgents": 20,
+      "defaultAgentType": "claude",
+      "monitorIntervalMs": 30000,
+      "shutdownTimeoutMs": 15000
+    }
   }
 }
 ```
 
-- **maxAgents** - Maximum teammates (default: 20)
-- **defaultAgentType** - Agent type when not specified (default: `executor`)
-- **monitorIntervalMs** - How often to poll `TaskList` (default: 30s)
-- **shutdownTimeoutMs** - How long to wait for shutdown responses (default: 15s)
+- **ops.maxAgents** - Maximum teammates (default: 20)
+- **ops.defaultAgentType** - CLI provider when a `/team` invocation does not specify one (`claude` | `codex` | `gemini`, default: `claude`)
+- **ops.monitorIntervalMs** - How often to poll `TaskList` (default: 30s)
+- **ops.shutdownTimeoutMs** - How long to wait for shutdown responses (default: 15s)
 
 > **Note:** Team members do not have a hardcoded model default. Each teammate is a separate Claude Code session that inherits the user's configured model. Since teammates can spawn their own subagents, the session model acts as the orchestration layer while subagents can use any model tier.
 
+## Per-Role Provider & Model Routing
+
+> **Scope:** Applies to `/team` only. Task-based delegation uses `delegationRouting` (see separate docs). The two systems coexist by design.
+
+Declare which provider (`claude`, `codex`, `gemini`) and which model tier should back each canonical role. Routing is resolved **once** at team creation and persisted in `TeamConfig.resolved_routing` — spawn, scale-up, and restart all read from the snapshot, so a role's worker CLI and model are stable for the lifetime of the team.
+
+### Example — user target mapping
+
+```jsonc
+// .claude/omc.jsonc
+{
+  "team": {
+    "roleRouting": {
+      "orchestrator":  { "model": "inherit" },
+      "planner":       { "provider": "claude", "model": "HIGH" },
+      "analyst":       { "provider": "claude", "model": "HIGH" },
+      "executor":      { "provider": "claude", "model": "MEDIUM" },
+      "critic":        { "provider": "codex" },
+      "code-reviewer": { "provider": "gemini" },
+      "test-engineer": { "provider": "gemini", "model": "MEDIUM" }
+    }
+  }
+}
+```
+
+| Role | Provider | Model |
+|---|---|---|
+| `orchestrator` | claude (pinned) | inherits invoking session |
+| `planner` | claude | `HIGH` (opus) |
+| `analyst` | claude | `HIGH` (opus) |
+| `executor` | claude | `MEDIUM` (sonnet) |
+| `critic` | codex | codex default |
+| `code-reviewer` | gemini | gemini default |
+| `test-engineer` | gemini | `MEDIUM` (sonnet) |
+
+### Canonical roles
+
+`orchestrator`, `planner`, `analyst`, `architect`, `executor`, `debugger`, `critic`, `code-reviewer`, `security-reviewer`, `test-engineer`, `designer`, `writer`, `code-simplifier`, `explore`, `document-specialist`.
+
+User-friendly aliases normalize via `normalizeDelegationRole()` — e.g. `reviewer` → `code-reviewer`, `quality-reviewer` → `code-reviewer`, `harsh-critic` → `critic`, `build-fixer` → `debugger`. Accepted alias keys are honored during resolved snapshot creation and later stage routing, not just validation. Unknown roles fail validation at parse time.
+
+### Spec fields (`TeamRoleAssignmentSpec`)
+
+- **provider** — `"claude" | "codex" | "gemini"`. Omitted → defaults to `claude`.
+- **model** — tier name (`"HIGH" | "MEDIUM" | "LOW"`) or an explicit model ID. Tiers resolve through `routing.tierModels`.
+- **agent** — optional Claude agent name (e.g. `"critic"`, `"executor"`). Only honored when the resolved provider is `claude`.
+
+`orchestrator` is pinned to `claude`; only `model` is user-configurable. Any other key on `orchestrator` is rejected by the validator.
+
+### Env override
+
+```bash
+OMC_TEAM_ROLE_OVERRIDES='{"critic":{"provider":"codex"},"code-reviewer":{"provider":"gemini"}}'
+```
+
+Precedence: `OMC_TEAM_ROLE_OVERRIDES` > `.claude/omc.jsonc` (project) > `~/.config/claude-omc/config.jsonc` (user) > built-in defaults. Invalid JSON logs a warning and is ignored — env overrides are best-effort and never abort the run.
+
+### Fallback when a CLI is missing
+
+If the CLI for a configured provider is absent from `PATH` at spawn time, `buildLaunchArgs()` throws, the team lead emits a visible `SendMessage` warning, and the runtime falls back to a deterministic Claude assignment pre-computed by `buildResolvedRoutingSnapshot` (same tier + same agent, `provider: "claude"`). Fallback is loud by design — silent fallback is a test failure. Probe provider availability with `omc doctor --team-routing`.
+
+### Stickiness — resolved once, reused everywhere
+
+Resolved routing is immutable per team. Editing config mid-team-lifetime does not affect running teams; a new `/team` invocation picks up the new mapping. This guarantees that spawn, scale-up, and worker-restart all see identical routing, including across worktree detaches (the snapshot travels with `TeamConfig`).
+
+### Zero-config behavior
+
+An empty `team.roleRouting` preserves pre-patch behavior: every worker is Claude, model tiers follow `routing.tierModels`, and `/team 3:executor ...` still spawns three Claude Sonnet executors.
+
 ## State Cleanup
 
 On successful completion:

package/bundled/upstream/oh-my-claudecode/skills/trace/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: trace
 description: Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
+argument-hint: "<observation to trace>"
 agent: tracer
 level: 2
 ---

package/bundled/upstream/oh-my-claudecode/skills/ultraqa/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: ultraqa
 description: QA cycling workflow - test, verify, fix, repeat until goal met
+argument-hint: "[--tests|--build|--lint|--typecheck|--custom <pattern>] [--interactive]"
 level: 3
 ---
 

package/bundled/upstream/oh-my-claudecode/skills/ultrawork/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: ultrawork
 description: Parallel execution engine for high-throughput task completion
+argument-hint: "<task description with parallel work items>"
 level: 4
 ---
 

package/bundled/upstream/oh-my-claudecode/skills/verify/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: verify
+description: Verify that a change really works before you claim completion
+---
+
+# Verify
+
+Use this skill when the user wants confidence that a feature, fix, or refactor actually works.
+
+## Goal
+Turn vague “it should work” claims into concrete evidence.
+
+## Workflow
+1. Identify the exact behavior that must be proven.
+2. Prefer existing tests first.
+3. If coverage is missing, run the narrowest direct verification commands available.
+4. If direct automation is not enough, describe the manual validation steps and gather concrete observable evidence.
+5. Report only what was actually verified.
+
+## Verification order
+1. Existing tests
+2. Typecheck / build
+3. Narrow direct command checks
+4. Manual or interactive validation
+
+## Rules
+- Do not say a change is complete without evidence.
+- If a check fails, include the failure clearly.
+- If no realistic verification path exists, say that explicitly instead of bluffing.
+- Prefer concise evidence summaries over noisy logs.
+
+## Output
+- What was verified
+- Which commands/tests were run
+- What passed
+- What failed or remains unverified
+

package/bundled/upstream/oh-my-claudecode/skills/wiki/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: wiki
+description: LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
+triggers: ["wiki", "wiki this", "wiki add", "wiki lint", "wiki query"]
+---
+
+# Wiki
+
+Persistent, self-maintained markdown knowledge base for project and session knowledge. Inspired by Karpathy's LLM Wiki concept.
+
+## Operations
+
+### Ingest
+Process knowledge into wiki pages. A single ingest can touch multiple pages.
+
+```
+wiki_ingest({ title: "Auth Architecture", content: "...", tags: ["auth", "architecture"], category: "architecture" })
+```
+
+### Query
+Search across all wiki pages by keywords and tags. Returns matching pages with snippets — YOU (the LLM) synthesize answers with citations from the results.
+
+```
+wiki_query({ query: "authentication", tags: ["auth"], category: "architecture" })
+```
+
+### Lint
+Run health checks on the wiki. Detects orphan pages, stale content, broken cross-references, oversized pages, and structural contradictions.
+
+```
+wiki_lint()
+```
+
+### Quick Add
+Add a single page quickly (simpler than ingest).
+
+```
+wiki_add({ title: "Page Title", content: "...", tags: ["tag1"], category: "decision" })
+```
+
+### List / Read / Delete
+```
+wiki_list()           # Show all pages (reads index.md)
+wiki_read({ page: "auth-architecture" })  # Read specific page
+wiki_delete({ page: "outdated-page" })    # Delete a page
+```
+
+### Log
+View wiki operation history by reading `.omc/wiki/log.md`.
+
+## Categories
+Pages are organized by category: `architecture`, `decision`, `pattern`, `debugging`, `environment`, `session-log`
+
+## Storage
+- Pages: `.omc/wiki/*.md` (markdown with YAML frontmatter)
+- Index: `.omc/wiki/index.md` (auto-maintained catalog)
+- Log: `.omc/wiki/log.md` (append-only operation chronicle)
+
+## Cross-References
+Use `[[page-name]]` wiki-link syntax to create cross-references between pages.
+
+## Auto-Capture
+At session end, significant discoveries are automatically captured as session-log pages. Configure via `wiki.autoCapture` in `.omc-config.json` (default: enabled).
+
+## Hard Constraints
+- NO vector embeddings — query uses keyword + tag matching only
+- Wiki pages are git-ignored by default (`.omc/wiki/` is project-local)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudecode-omc",
-  "version": "5.4.0",
+  "version": "5.5.0",
   "description": "Claude Code harness — best-practice skills, agents, hooks, and configs from multiple sources",
   "bin": {
     "omc-manage": "bin/omc-manage.js"
@@ -17,6 +17,8 @@
   "scripts": {
     "setup": "node bin/omc-manage.js setup",
     "doctor": "node bin/omc-manage.js doctor",
+    "guidelines:optimize": "node bin/omc-manage.js guidelines optimize",
+    "guidelines:apply": "node bin/omc-manage.js guidelines apply",
     "source:list": "node bin/omc-manage.js source list",
     "source:sync": "node bin/omc-manage.js source sync",
     "source:status": "node bin/omc-manage.js source status",