mystilleef

Atomic execution for the project framework. Executes exactly one atomic task from `PLAN.md`.

Comprehensive Execution for the `SPAE` framework. Executes all tasks from `PLAN.md` sequentially in one invocation.

Optimization & Verification for the `SPAE` framework. Performs gap analysis on `PLAN.md`.

Orchestrate SPAE subagents sequentially through the structured workflow and lifecycle.

Task Decomposition for the `SPAE` framework. Decomposes `SPEC.md` into a `DAG` of atomic tasks in `PLAN.md`.

Orchestrate SPAE subagents sequentially through the spec, plan, and inspect phases of the structured workflow.

Executes the build phase of the SPAE structured workflow autonomously.

Given a proposal, or task, generate a spec and state file for SPAE structured workflow.

Refactor code to simplify it while preserving behavior.

Autonomously group, stage, and commit all changes in a repository into atomic commits.

Review code for correctness, security, and style.

Fill coverage gaps with tests.

Document code

Fix, refine, consolidate, and optimize markdown files.

Aggressively simplify and optimize code

Creates a new agent skill optimized for token and context efficiency.

Present the status of the git repository to the user. Use to display the status of the repository after a successful git commit by the agent. The agent should not use this internally for its own needs.

Fix lint, formatting, and prose issues in markdown files using Prettier and Vale. Use when the user or agent needs to fix lint, formatting, and prose issues in markdown files.

Autonomously select files to stage for an atomic Git commit. Use when the agent wants to stage selected files for a git commit. Only stages selected files, but does not commit them.

Iteratively, commit atomic changes to the respository. Use when the user or agent needs to autonomously commit atomic changes to the repository. Employs the "git-add", "git-message", and "git-status" in skills in sequence to perform the commit.

Generate a commit message for changes already in the Git staging area, and await approval from the user. Use when the agent needs to generate a commit message for staged changes. Only generates the commit message, but does not perform the commit.

Creates a new agent skill. Use when agent or user needs to create a new skill for the agent.

Format changelog and remove empty sections.

Edit changelog using git commit history via script.

Executes roadmaps and requests requiring project modifications with a verification-first mindset. Use when you need to perform write operations and ensure quality standards.

Executes approved roadmaps or requests with a verification-first mindset and robust troubleshooting. Use when you need to implement specific changes and provide a detailed session summary.

Investigates and creates a preparation roadmap to accomplish a task. Use when you need a detailed roadmap for a complex objective.

Critically reviews roadmaps, code, and strategies. Use when you need a technical review to identify flaws, risks, and improvements.

Enable read-only mode for safety enforcement. Use when the agent or user wants to protect the project from modifications.

Enable write mode by removing the safety marker. Use when the user explicitly authorizes changes.

Records observed mistakes, successes, and user preferences with `vibe learn` after task outcomes. Use after errors, user corrections, explicit praise, reusable wins, or preference discoveries that should persist across sessions.

Manages persistent vibe constitution rules for constraints, safety requirements, and preferences that must survive across multiple vibe checks. Use when a user states a standing rule, a task has a persistent risk boundary, a session resumes with stale rules, or existing rules conflict with new requirements.

Automatically validates complex ideas, plans, and solutions with the vibe CLI before execution. Use before risky, ambiguous, irreversible, or multi-step work to obtain mentor approval, revise unsafe plans, or abort when safe planning needs more information.