@codyswann/lisa 1.19.0 → 1.19.1

package/all/copy-overwrite/.claude/commands/project/debrief.md

@@ -1,11 +0,0 @@
----
-description: "Aggregates learnings from tasks and findings, uses skill-evaluator to decide where each belongs (new skill, .claude/rules/PROJECT_RULES.md, or omit)"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-debrief skill to aggregate and apply project learnings. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/document.md

@@ -1,11 +0,0 @@
----
-description: "Updates all documentation related to changes implemented in the project"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-document skill to update all project documentation. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/execute.md

@@ -1,11 +0,0 @@
----
-description: "Automated project execution from planning through debrief (requires gap-free research)"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-execute skill to run the complete project workflow. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/fix-linter-error.md

@@ -1,11 +0,0 @@
----
-description: "Fix all violations of one or more ESLint rules across the codebase"
-allowed-tools: ["Skill"]
-argument-hint: "<rule-1> [rule-2] [rule-3] ..."
-
----
-
-> **DEPRECATED**: This command is deprecated. Use `/plan:fix-linter-error` instead.
-> This command will be removed in a future release.
-
-Use the /project-fix-linter-error skill to fix ESLint rule violations. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/implement.md

@@ -1,11 +0,0 @@
----
-description: "Systematically implements all tasks in a specified project"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-implement skill to implement all planned tasks. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/local-code-review.md

@@ -1,10 +0,0 @@
----
-description: "Code review local changes on the current branch"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use `/plan:local-code-review` instead.
-> This command will be removed in a future release.
-
-Use the /project-local-code-review skill to review local changes on the current branch. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/lower-code-complexity.md

@@ -1,9 +0,0 @@
----
-description: "Reduces the code complexity of the codebase by 2 on each run"
-allowed-tools: ["Skill"]
----
-
-> **DEPRECATED**: This command is deprecated. Use `/plan:lower-code-complexity` instead.
-> This command will be removed in a future release.
-
-Use the /project-lower-code-complexity skill to reduce cognitive complexity. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/plan.md

@@ -1,11 +0,0 @@
----
-description: "Uses the research.md and brief.md file in the specified directory to create a detailed list of tasks to implement the project"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-plan skill to create implementation tasks from research and brief. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/reduce-max-lines-per-function.md

@@ -1,11 +0,0 @@
----
-description: "Reduce max lines per function threshold and fix violations"
-allowed-tools: ["Skill"]
-argument-hint: "<max-lines-per-function-value>"
-
----
-
-> **DEPRECATED**: This command is deprecated. Use `/plan:reduce-max-lines-per-function` instead.
-> This command will be removed in a future release.
-
-Use the /project-reduce-max-lines-per-function skill to reduce function line limits. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/reduce-max-lines.md

@@ -1,11 +0,0 @@
----
-description: "Reduce max file lines threshold and fix violations"
-allowed-tools: ["Skill"]
-argument-hint: "<max-lines-value>"
-
----
-
-> **DEPRECATED**: This command is deprecated. Use `/plan:reduce-max-lines` instead.
-> This command will be removed in a future release.
-
-Use the /project-reduce-max-lines skill to reduce file line limits. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/research.md

@@ -1,11 +0,0 @@
----
-description: "Conducts research of your code base and the web relevant to your project and compiles it for the planning phase"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-research skill to conduct comprehensive research for the project. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/review.md

@@ -1,11 +0,0 @@
----
-description: "Performs extensive code review and optimization on the current project"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-review skill to perform code review and optimization. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/setup.md

@@ -1,11 +0,0 @@
----
-description: "Initialize a project with full requirements analysis, planning, and structure setup"
-allowed-tools: ["Skill"]
-argument-hint: "<file-path|jira-issue|text-description>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-setup skill to initialize a new project. $ARGUMENTS

package/all/copy-overwrite/.claude/commands/project/verify.md

@@ -1,11 +0,0 @@
----
-description: "Comprehensive verification that a feature branch fully implements all project requirements with proper code quality, tests, and documentation"
-allowed-tools: ["Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This command is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This command will be removed in a future release.
-
-Use the /project-verify skill to verify the project implementation. $ARGUMENTS

package/all/copy-overwrite/.claude/skills/project-add-test-coverage/SKILL.md

@@ -1,61 +0,0 @@
----
-name: project-add-test-coverage
-description: This skill should be used when increasing test coverage to a specified threshold percentage. It runs the coverage report, identifies files with the lowest coverage, generates a brief with coverage gaps, and bootstraps a project to add the missing tests.
-allowed-tools: ["Read", "Bash", "Glob", "Grep"]
-argument-hint: "<threshold-percentage>"
-
----
-
-> **DEPRECATED**: This skill is deprecated. Use `/plan-add-test-coverage` instead, which integrates with Claude's native plan mode.
-> This skill will be removed in a future release.
-
-# Increase Test Coverage
-
-Target threshold: $ARGUMENTS%
-
-If no argument provided, prompt the user for a target.
-
-## Step 1: Gather Requirements
-
-1. **Find coverage config** (jest.config.js, vitest.config.ts, .nycrc, etc.)
-2. **Run coverage report** to get current state:
-   ```bash
-   bun run test:cov 2>&1 | head -100
-   ```
-3. **Identify the 20 files with lowest coverage**, noting:
-   - File path
-   - Current coverage % (lines, branches, functions)
-   - Which lines/branches are uncovered
-
-## Step 2: Generate Brief
-
-Compile findings into a detailed brief:
-
-```
-Increase test coverage from [current]% to $ARGUMENTS%.
-
-## Files Needing Coverage (ordered by coverage gap)
-
-1. src/services/user.ts - 23% coverage (target: $ARGUMENTS%)
-   - Uncovered: lines 45-67, 89-102
-   - Missing branch coverage: lines 34, 56
-2. src/utils/helpers.ts - 34% coverage (target: $ARGUMENTS%)
-   - Uncovered: lines 12-45
-...
-
-## Configuration
-- Config file: [path to coverage config]
-- Update thresholds to $ARGUMENTS% for: lines, branches, functions, statements
-
-## Acceptance Criteria
-- All files meet $ARGUMENTS% coverage threshold
-- `bun run test:cov` passes with no threshold violations
-
-## Verification
-Command: `bun run test:cov`
-Expected: All thresholds pass at $ARGUMENTS%
-```
-
-## Step 3: Bootstrap Project
-
-Run `/project-bootstrap` with the generated brief as a text prompt.

package/all/copy-overwrite/.claude/skills/project-archive/SKILL.md

@@ -1,14 +0,0 @@
----
-name: project-archive
-description: This skill should be used when archiving a completed project. It moves the project directory to the projects/archive folder, clears the active project marker, and commits and submits a PR with the changes.
-allowed-tools: ["Read", "Write", "Bash(git*)", "Glob", "Grep", "Task", "TaskCreate", "TaskUpdate", "TaskList"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This skill is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This skill will be removed in a future release.
-
-1. Move $ARGUMENTS to `projects/archive`
-2. Clear the active project marker: `rm -f .claude-active-project`
-3. Run /git-commit-and-submit-pr

package/all/copy-overwrite/.claude/skills/project-bootstrap/SKILL.md

@@ -1,33 +0,0 @@
----
-name: project-bootstrap
-description: This skill should be used when performing automated project setup and research with gap detection. It runs project setup, conducts research, checks for open questions, and if no gaps exist, proceeds directly to project execution.
-argument-hint: "<file-path|jira-issue|\"text description\">"
----
-
-> **DEPRECATED**: This skill is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This skill will be removed in a future release.
-
-Complete all of the following steps for $ARGUMENTS:
-
-## Step 1: Setup
-
-Run `/project-setup $ARGUMENTS`
-
-Capture the project name from the output for use in subsequent steps.
-
-## Step 2: Research
-
-Run `/project-research @projects/<project-name>`
-
-## Step 3: Gap Detection
-
-Read @projects/<project-name>/research.md.
-
-Check '## Open Questions' section. If unresolved questions exist, STOP and report to human.
-
-If no gaps, immediately run `/project-execute @projects/<project-name>`
-
-## Output to Human
-
-- If gaps exist: "Bootstrap complete but needs human review - see Open Questions in research.md"

package/all/copy-overwrite/.claude/skills/project-debrief/SKILL.md

@@ -1,48 +0,0 @@
----
-name: project-debrief
-description: This skill should be used when aggregating learnings from completed project tasks and findings. It collects learnings from task metadata and findings.md, uses the skill-evaluator to categorize each learning (new skill, project rule, or omit), and applies the decisions accordingly.
-allowed-tools: ["Read", "Write", "Edit", "Bash", "Glob", "Grep", "Task", "TaskCreate", "TaskUpdate", "TaskList", "Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This skill is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This skill will be removed in a future release.
-
-## Setup
-
-Set active project marker: `echo "$ARGUMENTS" | sed 's|.*/||' > .claude-active-project`
-
-Extract `<project-name>` from the last segment of `$ARGUMENTS`.
-
-## Create and Execute Tasks
-
-Create workflow tracking tasks with `metadata.project` set to the project name:
-
-```
-TaskCreate:
-  subject: "Aggregate project learnings"
-  description: "Collect all learnings from two sources: 1) Read $ARGUMENTS/findings.md for manual findings. 2) Read all task files in $ARGUMENTS/tasks/*.json and extract metadata.learnings arrays. Compile into a single list of distinct findings/learnings."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Evaluate each learning"
-  description: "For each learning, use Task tool with subagent_type 'skill-evaluator' to determine: CREATE SKILL (complex, reusable pattern), ADD TO RULES (simple never/always rule), or OMIT ENTIRELY (already covered or too project-specific). Collect all decisions."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Apply decisions"
-  description: "For each learning based on skill-evaluator decision: CREATE SKILL → run /skill-creator with details. ADD TO RULES → add succinctly to .claude/rules/PROJECT_RULES.md. OMIT → no action. Report summary: skills created, rules added, omitted count."
-  metadata: { project: "<project-name>" }
-```
-
-**Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until all are completed.
-
-## Important: Rules vs Skills
-
-**WARNING about PROJECT_RULES.md**: Rules in `.claude/rules/` are **always loaded** at session start for every request. Only add learnings to PROJECT_RULES.md if they:
-- Apply to **every** request in this codebase (not just specific features)
-- Are simple "never do X" or "always do Y" statements
-- Cannot be scoped to a skill that's invoked on-demand
-
-If a learning only applies to certain types of work (e.g., "when writing GraphQL resolvers..."), it should be a **skill** instead, not a rule.

package/all/copy-overwrite/.claude/skills/project-document/SKILL.md

@@ -1,55 +0,0 @@
----
-name: project-document
-description: This skill should be used when updating all documentation related to changes implemented in a project. It identifies changed files, maps them to documentation targets, and updates README, API docs, CHANGELOG, and JSDoc documentation.
-allowed-tools: ["Read", "Write", "Edit", "Bash", "Glob", "Grep", "Task", "TaskCreate", "TaskUpdate", "TaskList", "Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This skill is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This skill will be removed in a future release.
-
-The current branch is a feature branch with implementation of the project in $ARGUMENTS.
-
-Changes on this branch need corresponding documentation updates to keep README, API docs, changelogs, and JSDoc current.
-
-**IMPORTANT**: Perform each step and move to the next without stopping.
-
-## Setup
-
-Set active project marker: `echo "$ARGUMENTS" | sed 's|.*/||' > .claude-active-project`
-
-Extract `<project-name>` from the last segment of `$ARGUMENTS`.
-
-## Create and Execute Tasks
-
-Create workflow tracking tasks with `metadata.project` set to the project name:
-
-```
-TaskCreate:
-  subject: "Identify changed files and documentation targets"
-  description: "Use git to identify files changed on this branch (git diff main...HEAD --name-only). For each changed file, identify related documentation: README sections, API docs, inline JSDoc, CHANGELOG entries, architecture docs, configuration docs. Compile a mapping of: changed file → related documentation file(s). Save to $ARGUMENTS/doc-targets.json with structure: { \"file.ts\": [\"README.md#section\", \"docs/api.md\"], ... }"
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Update README and user-facing docs"
-  description: "For each documentation target in $ARGUMENTS/doc-targets.json that is a README section or user guide: Read the changed implementation file. Read the current documentation section. Update the documentation to accurately reflect the new/changed behavior, examples, or configuration. Preserve existing structure and tone."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Update API and technical documentation"
-  description: "For each documentation target that is API docs, architecture docs, or technical guides: Read the changed implementation. Read the current documentation. Update to reflect new endpoints, parameters, type signatures, behavior changes, or architectural decisions. Ensure consistency with code comments."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Update CHANGELOG"
-  description: "If CHANGELOG.md or CHANGELOG.{md,txt,rst} exists in project root: Add entry for all user-facing changes. Group by type (Added, Changed, Fixed, Deprecated). Reference relevant files or features. Follow existing CHANGELOG format and conventions."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Verify JSDoc on changed files"
-  description: "Read $ARGUMENTS/doc-targets.json. For each changed file (key), verify its JSDoc preamble and function/export documentation are current: Run /jsdoc-best-practices skill. Check that file-level preambles explain the module's purpose and when to use it. Check that exported functions/types have 'why' documentation (not just 'what'). Update any stale or missing documentation."
-  metadata: { project: "<project-name>" }
-```
-
-**Execute each task via a subagent** to preserve main context. Launch up to 5 in parallel where tasks don't have dependencies. Do not stop until all are completed.

package/all/copy-overwrite/.claude/skills/project-execute/SKILL.md

@@ -1,72 +0,0 @@
----
-name: project-execute
-description: This skill should be used when running the complete automated project execution workflow from planning through debrief. It requires gap-free research and sequentially runs planning, implementation, review, documentation, verification, debrief, and archive phases.
-allowed-tools: ["Read", "Write", "Edit", "Bash", "Glob", "Grep", "Task", "TaskCreate", "TaskUpdate", "TaskList", "TaskGet", "Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This skill is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This skill will be removed in a future release.
-
-Execute complete implementation workflow for $ARGUMENTS.
-
-## Execution Rules
-
-1. **Continuous execution**: After each step completes, immediately invoke the next
-2. **No summaries**: Do not summarize progress between steps
-3. **No waiting**: Do not wait for user confirmation between steps
-4. **Only stop when done**: Only stop when all steps are completed
-
-## Setup
-
-1. Set active project marker: `echo "$ARGUMENTS" | sed 's|.*/||' > .claude-active-project`
-2. Read `$ARGUMENTS/research.md` and check "## Open Questions" section
-   - If gaps exist: STOP with "Cannot proceed - research.md has unresolved open questions"
-3. Check if planning is already complete: `ls $ARGUMENTS/tasks/*.md 2>/dev/null | head -3`
-   - If task files exist: Skip planning, start at implementation
-
-## Create and Execute Tasks
-
-Create workflow tracking tasks with `metadata.project` set to the project name:
-
-```
-TaskCreate:
-  subject: "Planning"
-  description: "Run /project-plan $ARGUMENTS to create implementation tasks."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Implementation"
-  description: "Run /project-implement $ARGUMENTS to execute all planned tasks."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Review"
-  description: "Run /project-review $ARGUMENTS to review code changes."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Documentation"
-  description: "Run /project-document $ARGUMENTS to update documentation related to changes."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Verification"
-  description: "Run /project-verify $ARGUMENTS to verify all requirements are met."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Debrief"
-  description: "Run /project-debrief $ARGUMENTS to capture learnings."
-  metadata: { project: "<project-name>" }
-
-TaskCreate:
-  subject: "Archive"
-  description: "Run /project-archive $ARGUMENTS to archive the completed project."
-  metadata: { project: "<project-name>" }
-```
-
-**Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until all are completed.
-
-Report "Project complete and archived" when done.

package/all/copy-overwrite/.claude/skills/project-fix-linter-error/SKILL.md

@@ -1,70 +0,0 @@
----
-name: project-fix-linter-error
-description: This skill should be used when fixing all violations of one or more ESLint rules across the codebase. It runs the linter, groups violations by rule and file, generates a brief with fix strategies, and bootstraps a project to implement the fixes.
-allowed-tools: ["Read", "Bash", "Glob", "Grep"]
-argument-hint: "<rule-1> [rule-2] [rule-3] ..."
-
----
-
-> **DEPRECATED**: This skill is deprecated. Use `/plan-fix-linter-error` instead, which integrates with Claude's native plan mode.
-> This skill will be removed in a future release.
-
-# Fix Linter Errors
-
-Target rules: $ARGUMENTS
-
-If no arguments provided, prompt the user for at least one lint rule name.
-
-## Step 1: Gather Requirements
-
-1. **Parse rules** from $ARGUMENTS (space-separated)
-2. **Run linter** to collect all violations:
-   ```bash
-   bun run lint 2>&1
-   ```
-3. **Group violations** by rule, then by file, noting:
-   - File path and line numbers
-   - Violation count per file
-   - Sample error messages
-
-## Step 2: Generate Brief
-
-Compile findings into a detailed brief:
-
-```
-Fix ESLint violations for rules: $ARGUMENTS
-
-## Violations by Rule
-
-### [rule-name-1] (X total violations across Y files)
-
-1. src/services/user.ts (5 violations)
-   - Line 23: [error message]
-   - Line 45: [error message]
-   - Line 67: [error message]
-   ...
-2. src/utils/helpers.ts (3 violations)
-   - Line 12: [error message]
-   ...
-
-### [rule-name-2] (X total violations across Y files)
-...
-
-## Fix Strategies
-- **Complexity rules** (sonarjs/*): Extract functions, early returns, simplify conditions
-- **Style rules** (prettier/*, import/order): Apply formatting fixes
-- **Best practice rules** (react-hooks/*, prefer-const): Refactor to recommended pattern
-- **Type rules** (@typescript-eslint/*): Add proper types, remove `any`
-
-## Acceptance Criteria
-- `bun run lint` passes with zero violations for: $ARGUMENTS
-- Each rule's fixes committed separately: `fix(lint): resolve [rule-name] violations`
-
-## Verification
-Command: `bun run lint 2>&1 | grep -E "($ARGUMENTS)" | wc -l`
-Expected: 0
-```
-
-## Step 3: Bootstrap Project
-
-Run `/project-bootstrap` with the generated brief as a text prompt.

package/all/copy-overwrite/.claude/skills/project-implement/SKILL.md

@@ -1,43 +0,0 @@
----
-name: project-implement
-description: This skill should be used when systematically implementing all tasks in a specified project. It retrieves planned tasks, executes them via subagents in parallel, runs verification commands, and tracks completion status.
-allowed-tools: ["Read", "Write", "Edit", "Bash", "Glob", "Grep", "Task", "TaskCreate", "TaskUpdate", "TaskList", "TaskGet", "Skill"]
-argument-hint: "<project-directory>"
----
-
-> **DEPRECATED**: This skill is deprecated. Use Claude's native plan mode instead.
-> Enter plan mode with `/plan`, describe your requirements, and Claude will create a plan with tasks automatically.
-> This skill will be removed in a future release.
-
-## Setup
-
-1. Set active project marker: `echo "$ARGUMENTS" | sed 's|.*/||' > .claude-active-project`
-2. Extract `<project-name>` from the last segment of `$ARGUMENTS`
-3. Use **TaskList** to verify tasks exist for this project (check metadata.project)
-4. If no tasks found, error: "No tasks found. Run /project-plan first"
-
-## Implementation
-
-Use **TaskList** to get current task status.
-
-**Always execute tasks via subagents** to keep the main context window clean. Launch up to 6 subagents in parallel for unblocked tasks.
-
-For each pending, unblocked task (filter by `metadata.project` = `<project-name>`):
-
-1. Use **TaskUpdate** to mark it `in_progress`
-2. Use **TaskGet** to retrieve full task details
-3. Complete the task following the instructions in its description
-4. Run the verification command and confirm expected output
-5. If verification passes, use **TaskUpdate** to mark it `completed`
-6. If verification fails, keep task `in_progress` and report the failure
-7. Check **TaskList** for newly unblocked tasks
-
-Continue until all tasks are completed.
-
-## Complete
-
-Use **TaskList** to generate a summary showing:
-- Total tasks completed
-- Any tasks that failed or remain in progress
-
-After completing this phase, tell the user: "To continue, run `/project-review $ARGUMENTS`"