Secondary workflow skills and commands split out from superpowers: systematic debugging, agent communication, evolutionary algorithm discovery, and more
Plugin lesserpowers from marketplace asermax-plugins in asermax/claude-plugins. Commands read from the repo's manifest — 5 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
agent-communicationUse when user explicitly requests to coordinate with other Claude Code agents, join an agent chat, or communicate across multiple repositories/projects
financial-summaryParse and analyze personal financial transaction CSV exports to calculate account totals and generate detailed breakdowns. Use when the user asks to analyze transaction data, generate financial summaries, calculate account balances, or review spending from CSV exports. Supports account grouping (Gal
hunk-reviewInteracts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files and hunks, reloads session contents, and adds inline review comments. Use when the user has a Hunk session running or wants to review diffs interactively.
self-maintaining-claude-mdUse when starting any task in a project - keeps CLAUDE.md instruction file current with high-level project state, prompts for init if missing, adds reflection todo before work to ensure documentation stays updated
systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
/lesserpowers:evolve-mlML subskill for /evolve - optimizes model accuracy and performance
/lesserpowers:evolve-perfPerformance subskill for /evolve - optimizes runtime speed for algorithms
/lesserpowers:evolve-sizeSize subskill for /evolve - optimizes for minimal code/text length
/lesserpowers:evolveEvolve novel algorithms through LLM-driven mutation, crossover, and selection
${CLAUDE_PLUGIN_ROOT}/hooks/background-daemons.sh
${CLAUDE_PLUGIN_ROOT}/hooks/auto-approve.sh
Problems found in this repo's manifests
Small, single-job software engineering skills where the human makes every decision and the agent executes: explore, shape, design, program architecture, blast radius, agentic and human review, documentation into the project's docs folder, and a wiki of distilled technical knowledge
43 skills · 14 agents
Spec-driven development framework with iterative growth, progressive adoption, and retrofit support
32 skills · 13 agents
Curated development workflow skills for browser automation, documentation, and code directives
9 skills · 4 commands · 1 agent · hooks
An Obsidian-vault quest log: journeys that clear unknown ground one question at a time, raids that build what they settled, and durable notes the project owns
15 skills
FPF reasoning methodology for structured decision-making with auditable hypothesis-evidence trails (formerly quint)
12 skills · 1 MCP server · hooks
Code review surface: agent skill generates a guided JSON view of a PR, local server renders it in the browser
4 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.