Self-referential loop until task completion with configurable verification reviewer — from yeaight7/agent-powerups
Use to enforce consistent naming conventions and file structures across a project without changing business logic.
Use when starting work in a repository with Agent Powerups installed, when a task may match a reusable local skill, command, workflow, hook recipe, AGENTS.md template, or MCP…
Vendor-neutral routing guide for choosing the right model tier by task type. Mechanical work uses a smaller/faster model; implementation uses a standard model; architecture,…
Write state-restoration documents for passing tasks between agents or engineers.
Compact context at logical phase boundaries — after research, after planning, after debugging — rather than mid-task. Preserves useful state while clearing noise.
Coordinate multiple subagents through dependency-aware waves, stage handoffs, monitoring, and verification loops. Use when the work is too large or too mixed for a single agent.
Review SQL for business logic correctness, semantic drift, aggregation risk, and silent definition changes.
Use to restructure code while guaranteeing that all existing tests continue to pass.
Use when a CI pipeline fails to extract the actual error from thousands of lines of logs.
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
Coordinate multi-system deployment steps as a review-first runbook with explicit approval before any external write or promotion action.
Use when reviewing code (or your own plan) to allocate attention based on the danger of the change.
Parallel execution engine for high-throughput task completion — from yeaight7/agent-powerups
Create or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.
Audit agent configuration files for security vulnerabilities and misconfigurations. Covers settings.json, .mcp.json, .codex/config.toml, AGENTS.md, hooks, plugin manifests, and…
Maintain short, focused Markdown files per subsystem to provide agents with isolated context.
Inspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
Use at the beginning of a new task. Ensures you fully understand the requirements, boundaries, and acceptance criteria before writing code.
Analyzes ML training scripts to enforce seed setting, deterministic operations, and environment tracking for exact reproducibility.
Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or o — from…
Use when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.
Relay questions and tasks to a local Codex CLI using one-shot subprocesses per ask.
Use when confronted with an unknown failure in CI or production to rapidly categorize the issue before deep debugging.
Use when modifying dbt metrics or semantic models to ensure mathematical correctness and backwards compatibility.
Use to isolate a bug from a large application into a standalone, runnable script or single test case.
Use after fixing a bug to generate a blameless post-mortem summary for human review.
Use to identify and safely delete unused functions, classes, exports, and files.
Use continuously during long tasks. Teaches how to read less, output less, and keep the LLM context window lean and fast.
Analyze BigQuery usage, identify cost hotspots, repeated failures, and practical optimization opportunities.
Deterministic 3-cycle loop for gathering codebase context before acting. Broad search → exact source and tests → target-specific docs and setup.
Relay questions and tasks to a persistent local Gemini ACP session with cross-turn context.
Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.
Use when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.
Standardize the reporting of model metrics to ensure statistical rigor and business relevance.
Use when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.
Audit whether a dbt incremental model uses the right incremental strategy for the repo, the data shape, and the operational constraints.
Use when deciding the lowest-cost context path for a mixed corpus, especially when choosing among direct reading, helper conversion, graph build, graph update, or graph query.
Diagnose NaN losses, out-of-memory errors, and shape mismatches in deep learning or ML pipelines.
Use when about to commit, push, or publish -- staged changes touch config or environment files, generated artifacts (relay sessions, logs, build output) are being added, or the…
Use when a hook is about to be enabled or modified -- a hook recipe proposed for activation, a pre/post-tool or lifecycle hook added to agent settings, a git pre-commit hook added…
Use when a user needs to build or refresh persistent graph memory from a mixed corpus and the right path may include graphify, incremental update, or helper conversion before…
Use before submitting a PR or considering a task done to evaluate the 'blast radius' of your changes.
Use when validating rendered web pages, local dev servers, browser automation, screenshots, forms, auth sessions, or UI evidence with strict browser safety boundaries.
Use when mining PR review comments and text diffs for reusable writing, documentation, tone, and editorial improvement patterns.
Use when a bug was recently introduced but you don't know which commit caused it.
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.
Verify that all hyperparameters, metrics, and data references are properly logged.
Audit documentation for broken file paths, outdated commands, and renamed variables.
Run large codebase migrations in reviewable local batches with codemods, checkpoints, and verification. Use when a wide refactor is too risky to ship as one monolithic change.
Ensure the project README provides immediate, exact commands for setup, testing, and deployment to help agents and humans bootstrap quickly.
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use before tagging a release or deploying to production to ensure all quality gates have passed.
Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.
Full autonomous execution from idea to working code — from yeaight7/agent-powerups
Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.
Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.
Run a review and CI loop around a pull request with explicit approval gates for code changes, remote writes, and follow-up actions.