Bash agent skills, page 8

Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001).

modu-ai/moai-adk

Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment.

PackmindHub/packmind

Use before committing changes to auth, workspace scoping, channel webhooks, AI tools/MCP, permission settings, or anything handling untrusted channel content in ChatbotX.

ChatbotXIO/ChatbotX

Defense-in-depth security across Rust, TypeScript, and Bash for the Pump SDK — cryptographic key handling, memory zeroization, secure file I/O, input validation, privilege management, dependency…

nirholas/pump-fun-sdk

Create a literate org-mode document with executable bash source blocks (org-babel) so the user can re-run commands/queries themselves in Emacs, then open it via emacsclient.

meain/dotfiles

Run a command in a tmux pane/window/session and monitor its output for errors.

meain/dotfiles

OpenSpec-mode authoring for Chorus PM workflows in Kiro CLI.

Chorus-AIDLC/Chorus

OpenSpec-mode authoring for Chorus PM workflows in Hermes. An agent skill from Chorus-AIDLC/Chorus.

Chorus-AIDLC/Chorus

OpenSpec-mode authoring for Chorus PM workflows in Pi. An agent skill from Chorus-AIDLC/Chorus.

Chorus-AIDLC/Chorus

OpenSpec-mode authoring for Chorus PM workflows on OpenClaw — the default whenever OpenSpec is usable.

Chorus-AIDLC/Chorus

OpenSpec-mode authoring for Chorus PM workflows in Codex. An agent skill from Chorus-AIDLC/Chorus.

Chorus-AIDLC/Chorus

OpenSpec-mode authoring for Chorus PM workflows in Claude Code.

Chorus-AIDLC/Chorus

Guide for modifying the Chorus plugin (Claude Code, Codex, OpenClaw, Kiro, Pi, dsh, and Hermes ports), updating skill documentation, and releasing new plugin versions.

Chorus-AIDLC/Chorus

Read-only adversarial Chorus task reviewer — independently verifies an implementation against its acceptance criteria and posts a single structured VERDICT comment.

Chorus-AIDLC/Chorus

Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool.

AI4Scientist/nano-scientist

Constructive critique via 5 HackerNews personas with claim validation.

notque/vexjoy-agent

This skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule, or needs guidance on hookify rule syntax and patterns.

aAAaqwq/AGI-Super-Team

A skill your agent uses when verifying Rudder agent runtime behavior in a real local environment, especially MCP/native Rudder tools across Codex, Claude, OpenCode, Pi, or user-named runtimes.

Undertone0809/rudder

Bash 编写规范。当用户操作 .sh、Dockerfile、Makefile、.yml、.yaml 文件， 或在 Markdown 中编写 bash/shell 代码块时触发。

doccker/cc-use-exp

Bash 脚本与系统命令规范。禁止行尾注释，强制使用 tee/heredoc 写入，提升命令执行的可维护性. An agent skill from doccker/cc-use-exp.

doccker/cc-use-exp

Instructions for writing new Sculptor frontend integration tests.

imbue-ai/sculptor

The evidence gate. An agent skill from robertbarclayy/conducty.

robertbarclayy/conducty

Get a live job market snapshot for any role and tech stack by deploying parallel TinyFish agents across LinkedIn, Indeed, and Glassdoor.

tinyfish-io/tinyfish-cookbook

Find paid open-source work, OSS bounties, open source grants, or ways to get paid contributing to open source.

tinyfish-io/tinyfish-cookbook

Researches any project idea against live data from GitHub and Dev.to to surface what already exists, how mature the space is, and where the real opportunity lives.

tinyfish-io/tinyfish-cookbook

Drives a Dart or Flutter package fully green through a verify-fix-rerun loop across four gates: analyze, format, test, coverage.

VeryGoodOpenSource/vgv-ai-flutter-plugin

Query flow event logs to answer questions about past sensing events — "Have you seen anybody between 10pm and midnight?", "Is there any motion in the last hour?", "What happened while I was away?".

autonomous-ai/Physical-AI-Operating-System

Decision protocol for wiring a verify-then-fix loop around a code-editing LLM agent.

agentsope/SkillAlchemy

Creates a phased roadmap.json for a feature goal with acceptance criteria and TDD steps.

nWave-ai/nWave

Remove a subagent's .claude/worktrees/agent-<id dir after its PR merges.

vchelaru/FlatRedBall

Create, review, and debug Bash or POSIX sh scripts when portability, quoting, failure handling, or shell-specific validation matters.

ChrisTitusTech/titus-ai

Context-aware Q&A with auto context gathering. An agent skill from sd0xdev/sd0x-harness.

sd0xdev/sd0x-harness

Tech spec generation and review. An agent skill from sd0xdev/sd0x-harness.

sd0xdev/sd0x-harness

Start / stop / status of the Typhon Workbench dev servers (Kestrel :5200 + Vite :5173) with file-based PID tracking so state survives across Claude Code sessions

Log2n-io/Typhon

Explains and manages the PostToolUse hook that auto-syncs .pure file edits/creates/deletes to the running Pure LSP session's overlay, so the Agent's on-disk changes and the LSP's in-memory model…

finos/legend-engine

A skill your agent uses to wire adb reliably into CI — bash idioms, exit codes, parallel device fan-out with xargs -P, port forwarding (adb forward LOCAL REMOTE vs adb reverse REMOTE LOCAL —…

skydoves/android-testing-skills

This skill should be used when the user says "/tribunal", "tribunal", "review this", "3-way review", "risk-value-feasibility check", or wants multi-perspective adversarial review.

team-attention/hoyeon

Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.

asgeirtj/system_prompts_leaks

Operating system and shell scripting troubleshooting workflow for Linux, macOS, and Windows.

aiskillstore/marketplace

Rewrite the active Pneuma session's UI title + one-line summary so the launcher and ProjectPanel rows reflect what the session is actually about.

pandazki/pneuma-skills

Draft a new Claude Code subagent at .claude/agents/<name.md, using the official subagents format.

CorridorTech/PoseCap

Writes unit tests (for lib/.sh-style helpers) or mocked end-to-end tests (for executable scripts) using bats, and runs task tests:bash/tests:coverage.

agntcy/coffeeAgntcy

Understand and respond to the Interlinked PreToolUse guard — the local daemon that BLOCKS dangerous tool calls before they run.

QuentinCody/interlinked-cli

Smart partial rebase for squash-merge repositories. An agent skill from sd0xdev/sd0x-harness.

sd0xdev/sd0x-harness

Initialize uc-taskmanager for the current project. An agent skill from davepoon/buildwithclaude.

davepoon/buildwithclaude

Create git commits for dotfiles changes, grouping by component with conventional prefix style

meain/dotfiles

Guardrail patterns for opencode-swarm — pattern structure, bypass surfaces, regex anti-patterns, and test conventions for checkDestructiveCommand()

ZaxbyHub/opencode-swarm

Safe test execution patterns for opencode-swarm. An agent skill from ZaxbyHub/opencode-swarm.

ZaxbyHub/opencode-swarm