Self-referential loop until task completion with configurable verification reviewer — from yeaight7/agent-powerups
Use to identify and safely delete unused functions, classes, exports, and files.
Use when mining PR review comments and text diffs for reusable writing, documentation, tone, and editorial improvement patterns.
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 reviewing code (or your own plan) to allocate attention based on the danger of the change.
Use when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
Use to isolate a bug from a large application into a standalone, runnable script or single test case.
Use when modifying dbt metrics or semantic models to ensure mathematical correctness and backwards compatibility.
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
Inspect GitHub PR checks, fetch actionable failure logs, summarize the breakage, and propose a local fix plan before changing code.
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…
Use at the beginning of a new task. Ensures you fully understand the requirements, boundaries, and acceptance criteria before writing code.
Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.
Audit documentation for broken file paths, outdated commands, and renamed variables.
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Analyzes ML training scripts to enforce seed setting, deterministic operations, and environment tracking for exact reproducibility.
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.
Use to audit and remove unused or redundant third-party dependencies from package manifests.
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.
Use before tagging a release or deploying to production to ensure all quality gates have passed.
Relay questions and tasks to a local Codex CLI using one-shot subprocesses per ask.
Verify that all hyperparameters, metrics, and data references are properly logged.
Review SQL for business logic correctness, semantic drift, aggregation risk, and silent definition changes.
Use when a bug was recently introduced but you don't know which commit caused it.
Deterministic 3-cycle loop for gathering codebase context before acting. Broad search → exact source and tests → target-specific docs and setup.
Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.
Check version bump, changelog, compare range, package metadata, validation commands, publish steps, and rollback plan before cutting a release.
Use when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.
Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.
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…
Ensure the project README provides immediate, exact commands for setup, testing, and deployment to help agents and humans bootstrap quickly.
Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming…
Maintain short, focused Markdown files per subsystem to provide agents with isolated context.
Run a review and CI loop around a pull request with explicit approval gates for code changes, remote writes, and follow-up actions.
Coordinate multi-system deployment steps as a review-first runbook with explicit approval before any external write or promotion action.
Use when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.
Compact context at logical phase boundaries — after research, after planning, after debugging — rather than mid-task. Preserves useful state while clearing noise.
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.
Create or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.
Use after fixing a bug to generate a blameless post-mortem summary for human review.
Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.
Use when migrating APIs, libraries, or patterns across a large codebase. Ensures safe, step-by-step progress rather than risky mega-commits.
Use to collapse over-engineered abstractions, remove unnecessary layers, or consolidate redundant logic.
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.
Parallel execution engine for high-throughput task completion — from yeaight7/agent-powerups
Fix broken builds, type errors, or test failures with the smallest safe diff — no opportunistic refactors, no cleanup, no unrelated changes.
Use when confronted with an unknown failure in CI or production to rapidly categorize the issue before deep debugging.
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…
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
Evaluate metric and semantic model changes for BI/reporting breakage and business meaning drift.
Inspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.
Inspect and test web UIs using screenshots, browser automation, accessibility snapshots, and console/network signals with structured visual evidence collection.
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.
Use to enforce consistent naming conventions and file structures across a project without changing business logic.
Use when completing a task or running out of context limit. Ensures the next session or human engineer has exactly what they need to resume work instantly.
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,…
Use when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.