Skip to content
cccskills
FreePublished on GitHub

implement-refactor

Execute an assessor task file and every generated follow-up in dependency order. Use when a refactoring task file already exists.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Implement Refactor

<refactor_input> $ARGUMENTS </refactor_input>

1. Resolve And Read

If the input is a markdown path, use it. Otherwise resolve .plugin-creator/plans/tasks-refactor-{slug}.md. Read the complete task file and linked design. Extract each task's ID, status, dependencies, target, execution role, acceptance criteria, verification steps, and safe parallel peers.

Gate: stop with STATUS: BLOCKED when either file is absent, a task lacks an execution contract, or dependency edges conflict with the design.

2. Build The Work Graph

Create one tracking item per task plus completion validation. A task is ready only when it is incomplete and every dependency is complete. Run ready tasks in parallel only when the task file marks them as safe peers and their write targets do not overlap. If incomplete tasks remain and none are ready, return the dependency deadlock as STATUS: BLOCKED.

3. Route And Execute

Use the task's execution role when it is reachable in the current harness. The canonical routes for plans produced by /plugin-creator:assessor are:

Task typeReachable route
SKILL_SPLITActivate /plugin-creator:refactor-skill
AGENT_OPTIMIZEDispatch plugin-creator:subagent-refactorer
DOC_IMPROVE or ORPHAN_RESOLVEDispatch plugin-creator:ai-doc-optimizer
read-only quality auditDispatch plugin-creator:skill-auditor
upstream documentation syncDispatch plugin-creator:skill-content-updater
description-only changeActivate /plugin-creator:write-frontmatter-description
STRUCTURE_FIXDispatch the harness-native general-purpose agent

Reject an unavailable role instead of assuming a project-level or separately installed agent. Pass the task file and task ID, then activate /plugin-creator:start-refactor-task for the task's execution contract.

After each task returns:

  1. Verify its acceptance criteria and command evidence.
  2. Verify the task file status is complete.
  3. Mark its tracking item complete.
  4. Recalculate ready tasks.

A failed task remains incomplete. Return its evidence and blocker; do not skip it or ask the user to choose a weaker completion path.

4. Validate And Recurse

Activate /plugin-creator:ensure-complete <task-file-path> exactly once. It owns assessment, refactor validation, documentation validation, and follow-up planning for that task file. Do not run those checks separately here and do not ask it to re-enter itself.

If it returns follow-up task files, execute each through Steps 1-4 in dependency order. This skill is the sole owner of follow-up recursion. Completion means every task and follow-up task is complete, each ensure-complete call returned STATUS: DONE, and the plan index records the result.

Return:

STATUS: DONE
Plugin: {plugin}
Task file: {path}
Completed tasks: {IDs}
Validation: {commands and results}
Follow-up tasks: {completed paths or "none"}
Plan index: {updated path}

When blocked:

STATUS: BLOCKED
Task: {ID or "workflow"}
Reason: {specific blocker}
Completed: {verified task IDs}
Remaining: {task IDs}

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

See all skills by Jamie-BitFlight

Report a problem with this skill