Claude Skills by oprogramadorreal

Runs an iterative auto-fix loop on a chosen target — review, refactor, or coverage — dispatching the base skill into fresh subagent contexts per iteration, applying fixes automatically without per-change approval, running tests with bisection on failure, and checkpoint-committing until convergence or the cap. Requires /optimus:init and a test command in .claude/CLAUDE.md.

Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase, then presents the plan and asks before deleting. Requires Claude Code auto-memory; run periodically after heavy stretches of work.

Runs a Gauntlet Loop: turns an ambitious goal and optional quality references into a minimal builder/critic prompt judged against a concrete comparison bar, confirms with the user, then executes it as the lead agent until the output beats the bar or the user stops the run — or emits it as a paste-ready /goal prompt for a fresh session. Use for long-horizon goals judged against an inspectable reference. Long-running; spawns many subagents, edits project files, and commits finished pieces to a ...

Builds a self-contained paper-context bundle for implementing a research paper — sources, transcription, figures, references (blocking citations fetched), an implementation spec with the reported results, open questions, dataset provenance — under paper/, with datasets in a gitignored data/. Warns when reproduction outstrips local hardware. Downloads files and edits .gitignore and the root README. Stack-agnostic; writes no implementation code. Use when implementing a paper from a URL, PDF, DO...

Creates or updates a pull request (GitHub) or merge request (GitLab) for the current branch in the Conventional PR format — intent, summary, changes, rationale, and test plan. Pushes the branch if needed (asks before any force-push) and captures the implementation conversation's intent into the PR description. Use when a feature branch is ready for review or to refresh an existing PR/MR description.

Guides structured design brainstorming — explores the codebase, asks clarifying questions, proposes multiple approaches with trade-offs, and writes an approved design doc to the project. Use before implementation to think through design decisions and avoid premature coding. Produces a persistent artifact that feeds into plan mode and TDD. For stakeholder-facing or acceptance-criteria-driven work, the design doc includes a Given/When/Then Scenarios section consumed by /optimus:tdd.

Creates and switches to a new, conventionally named branch — derives the name from an inline description, conversation context, or local git diffs. Preserves all local changes. Never commits or pushes. Use when you want a properly named branch for new or in-progress work.

Reviews local changes, PRs/MRs, or branch diffs against project coding guidelines using 5 to 7 parallel review agents (bug detection, security/logic, guideline compliance x2, code simplification, test coverage, contract quality). Use before committing, on open PRs/MRs, or to review any branch diff. HIGH SIGNAL only: real bugs, logic errors, security concerns, and guideline violations. Supports a "deep" mode for iterative auto-fix — reviews and fixes code in a loop until clean.

Suggests conventional commit messages by analyzing staged, unstaged, and untracked git changes — read-only, never commits. Use when a commit message suggestion is needed without actually committing.

Stages, commits, and optionally pushes local changes with a conventional commit message — analyzes diffs, generates the message, confirms with the user, and commits. On protected branches, offers to create a feature branch automatically. Multi-repo aware. Use when ready to commit work in one step.

Compacts the current conversation into a single self-contained handoff document under docs/handoffs/ so a fresh agent — a new session, a different AI tool, or another developer on a different machine — can resume the work by reading only that file. References committed artifacts (PRDs, plans, ADRs, issues, commits) by path or URL and inlines anything not yet pushed. Redacts secrets and PII. Re-running on an existing handoff lets you enhance the shared doc or overwrite it. Use when pausing wor...

Generates or updates a project's HOW-TO-RUN.md — a single document that teaches a new developer how to set up their environment and run the project locally. Detects build system, toolchain, SDKs, source dependencies (git submodules, sibling repos), external services, environment config, and hardware/OS requirements. Works for web apps, C/C++ desktop apps, native mobile, JVM/Android, game engines, embedded/firmware, and backend services. Audits an existing HOW-TO-RUN.md against actual project ...

Prepares a project for Claude Code — generates CLAUDE.md with progressive disclosure docs, auto-format hooks, and test infrastructure (framework, coverage tooling, testing docs). Detects empty directories and offers new-project scaffolding via official stack tooling before setup. Also audits and syncs existing documentation against source code. Replaces /init. Supports single projects, monorepos, and multi-repo workspaces (separate git repos under a shared parent directory). Use to bootstrap ...

Fetches and optimizes context from a JIRA issue for AI-assisted development. Searches assigned issues or fetches by key. Distills title, description, acceptance criteria, sprint context, and comments into a structured task description. Analyzes the codebase to surface missing criteria, scope, and risks. Optionally enriches the JIRA issue with a structured analysis comment, and for Complex-scope work can spawn implementation tickets in JIRA. Re-running on the same key refreshes the local task ...

Configures Claude Code permissions for safe agent autonomy. Creates settings.json with allow/deny rules and a path-restriction hook. Use after /optimus:init to enable autonomous agent workflows, or standalone to lock down a project's permission boundaries.

Creates or updates a pull request (GitHub) or merge request (GitLab) for the current branch using the Conventional PR format — intent, summary, changes, rationale, and test plan. Captures the implementation conversation's intent into the PR description when run in the same session. Use when a branch is ready for review, or to update an existing PR/MR description.

Crafts optimized, copy-ready prompts for any AI tool — LLMs, coding agents, image generators, workflow tools. Extracts intent, selects the right template, runs a diagnostic checklist, and delivers a token-efficient prompt. Accepts input in any language; English output by default. Use when writing, fixing, improving, or adapting a prompt for any AI tool.

Refactors existing code for guideline compliance and testability using 4 parallel analysis agents (guideline compliance, testability barriers, duplication/consistency, code-simplifier). Two goals — align code with project guidelines AND make untestable code testable so /optimus:unit-test can safely increase coverage. Use after /optimus:init to align existing code, before /optimus:unit-test to remove testability barriers, or periodically to prevent tech debt. Supports "testability" focus (afte...

Removes files installed by /optimus:init and /optimus:permissions from the project. Compares each file against plugin templates and classifies as unmodified, likely generated, or user-modified. Always asks before deleting. Git-tracked files are noted as recoverable. Tests are never touched. Monorepo and multi-repo aware. Use for clean reinstall or to stop using optimus.

Guides test-driven development — decompose a feature or bug fix into behaviors, then cycle through Red (failing test) → Green (minimal implementation) → Refactor for each one. Requires /optimus:init and working test infrastructure. Use when starting a new feature or bug fix with test-first discipline.

Improves unit test coverage on demand — discovers testing gaps and generates tests that follow project conventions. Requires /optimus:init to have set up test infrastructure first. Conservative — only adds new test files, never refactors existing source code. Supports `deep` mode for iterative in-conversation test generation and `deep harness` mode for an automated multi-cycle unit-test + testability-refactor loop with fresh context per phase. Use when test coverage is low, after adding new c...

Creates a git worktree for isolated parallel development — new branch in a separate directory with project setup and test baseline. Enables multiple Claude Code sessions on different tasks simultaneously. Multi-repo aware. Use when you need to work on something else without disturbing current work.