Skip to content
cccskills
FreePublished on GitHub

ensure-complete

Validate a completed plugin refactor against its task evidence, baseline assessment, documentation, and current validators. Use after implement-refactor or when deciding whether refactoring is complete.

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

See how to install

Files included (1)

  • SKILL.md3.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Complete Refactor

<task_file> $ARGUMENTS </task_file>

Run the phases in order. Create one tracking item per phase and a final-summary item before Phase

  1. Mark each phase complete only after its output passes the stated gate. A STATUS: BLOCKED response stops the workflow and is returned with the completed and remaining phases.

Phase 1: Reassess

Dispatch plugin-creator:plugin-assessor with the task file and plugin root. Require its standard report through the preloaded plugin-creator:assessment-reporting skill, including:

  • current score and marketplace readiness;
  • comparison with the baseline assessment or refactor design;
  • remaining findings with severity and affected paths;
  • STATUS: DONE, or STATUS: BLOCKED naming the missing input.

Gate: verify the report exists, the score comparison is reproducible from the named baseline, and every current plugin component is accounted for.

Phase 2: Validate The Refactor

Dispatch plugin-creator:refactor-validator with the task file, plugin root, and before/after evidence. Let that agent own validator selection and canonical schema interpretation; do not copy its checklists here.

Gate: verify every completed task has acceptance evidence, all reported validator commands and results are present, and every finding has severity, file:line, evidence, and remediation.

Phase 3: Audit Documentation Drift

Dispatch plugin-creator:refactor-validator with a documentation-only scope: compare the task's changed capabilities and paths with the plugin README, skills, agents, references, and plugin manifest. Require resolved-link evidence and a list of stale, missing, or contradictory docs.

Gate: verify every changed or removed public component has a documentation disposition. An empty finding set must be stated explicitly.

Phase 4: Dispose Findings

Combine findings from Phases 1-3. If any finding remains, dispatch plugin-creator:refactor-planner to create .plugin-creator/plans/tasks-refactor-{plugin-slug}-followup-{N}.md and update the existing plan index. Every finding must map to one task or an explicit accepted disposition; every task must have dependencies, an execution role, acceptance criteria, and verification steps.

Gate: either no unresolved finding remains, or the follow-up task file exists and accounts for every unresolved finding.

Completion

If follow-up tasks exist, return their paths to the caller. This skill validates and plans exactly once; it does not execute follow-ups or re-enter validation. /plugin-creator:implement-refactor owns follow-up execution and invokes this skill once after each completed task file.

If no follow-up tasks exist, update .plugin-creator/plans/REFACTOR-PLAN.md using its existing completed-entry format. Do not invent a completion date or score when the evidence does not provide one.

Return:

STATUS: DONE
Task file: {path}
Plugin: {plugin}
Assessment: {report path or inline}
Score: {before} -> {after}
Refactor validation: {result}
Documentation drift: {result}
Follow-up tasks: {paths or "none"}
Plan index: {updated path}

When blocked:

STATUS: BLOCKED
Phase: {phase}
Reason: {specific missing input or failed gate}
Completed: {verified outputs}
Remaining: {uncompleted outputs}

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