Updated today
by jmagly
aiwg
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and MCP tools for Claude Code, Codex, Copilot, Cursor and more, plus SDLC workflows, session memory, and Jev decision support that offloads bounded LLM decisions to save tokens.
228 GitHub stars (228)
+5 in 25 days
| Period | New stars |
|---|---|
| Oct 13 | 0 |
| Oct 14 | +1 |
| Oct 15 | 0 |
| Oct 16 | 0 |
| Oct 17 | 0 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | 0 |
| Oct 21 | 0 |
| Oct 22 | 0 |
| Oct 23 | +1 |
| Oct 24 | 0 |
| Oct 25 | 0 |
| Oct 26 | 0 |
| Oct 27 | −1 |
| Oct 28 | +1 |
| Oct 29 | 0 |
| Oct 30 | +2 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | +1 |
| Nov 4 | 0 |
| Nov 5 | 0 |
| Nov 6 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 34 forks (34 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add jmagly/aiwg
Asks which skills and agents to install. Just one: npx skills add jmagly/aiwg --skill portable-complete — add -g for every project.
Claude Code
git clone https://github.com/jmagly/aiwgcp -r "aiwg/test/fixtures/agent-skills/lifecycle/portable-complete" ~/.claude/skills/
Copies the portable-complete skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add jmagly/aiwg
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 1178 files.
-
portable-complete
Use this complete portable fixture to verify Agent Skills round trips.
test/fixtures/ on GitHub (opens in a new tab)agent-skills/ lifecycle/ portable-complete/ SKILL.md -
flow-syntax
Use when validating YAML flow syntax accepted by the pinned reference parser.
test/fixtures/ on GitHub (opens in a new tab)agent-skills/ upstream-38a2ff82958afee88dadf4831509e6f7e9d8ef4e/ flow-syntax/ SKILL.md -
minimal
Use when validating the minimal normative Agent Skills fixture.
test/fixtures/ on GitHub (opens in a new tab)agent-skills/ upstream-38a2ff82958afee88dadf4831509e6f7e9d8ef4e/ minimal/ SKILL.md -
agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ agent-loop-ext/ SKILL.md -
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ agent-loop/ SKILL.md -
auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ auto-test-execution/ SKILL.md -
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ cross-task-learner/ SKILL.md -
debug-memory
Query and manage the executable feedback debug memory
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ debug-memory/ SKILL.md -
execute-feedback
Execute tests on generated code and iterate until passing
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ execute-feedback/ SKILL.md -
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ infer-completion-criteria/ SKILL.md -
mission-control
Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ mission-control/ SKILL.md -
ralph-abort
Abort a running agent loop and optionally revert changes
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-abort/ SKILL.md -
ralph-analytics
Show analytics and metrics from agent loop execution history
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-analytics/ SKILL.md -
ralph-attach
Attach to a running agent loop's live output stream
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-attach/ SKILL.md -
ralph-config
View and configure agent loop settings — show, set, reset, and apply named presets
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-config/ SKILL.md -
ralph-external
Crash-resilient external loop with state persistence and CI/CD integration
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-external/ SKILL.md -
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-memory/ SKILL.md -
ralph-reflect
View and manage agent loop reflections and episodic memory
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-reflect/ SKILL.md -
ralph-resume
Resume an interrupted agent loop from last checkpoint
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-resume/ SKILL.md -
ralph-status
Check status of current or previous agent loop
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph-status/ SKILL.md -
ralph
Execute iterative task loop until completion criteria are met - iteration beats perfection
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ ralph/ SKILL.md -
reflection-injection
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them
agentic/code/ on GitHub (opens in a new tab)addons/ agent-loop/ skills/ reflection-injection/ SKILL.md -
agent-persistence
Enable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
agentic/code/ on GitHub (opens in a new tab)addons/ agent-persistence/ skills/ agent-persistence/ SKILL.md -
cockpit-headless-deploy
Guide or repair a headless Linux AIWG Cockpit plus Agentic Sandbox deployment when host topology, SSH access, service persistence, or runtime readiness must be planned safely.
agentic/code/ on GitHub (opens in a new tab)addons/ agentic-installer/ skills/ cockpit-headless-deploy/ SKILL.md -
setup-generate
Generate a `setup.manifest.yaml` file for a project using the `setup.aiwg.io/v1`
agentic/code/ on GitHub (opens in a new tab)addons/ agentic-installer/ skills/ setup-generate/ SKILL.md -
setup-run
Execute a `setup.aiwg.io/v1` SetupManifest, performing cross-platform installati
agentic/code/ on GitHub (opens in a new tab)addons/ agentic-installer/ skills/ setup-run/ SKILL.md -
setup-validate
Validate a `setup.aiwg.io/v1` SetupManifest file against the schema and run cons
agentic/code/ on GitHub (opens in a new tab)addons/ agentic-installer/ skills/ setup-validate/ SKILL.md -
dev-doctor
Run a development-focused health check on the AIWG repository structure
agentic/code/ on GitHub (opens in a new tab)addons/ aiwg-dev/ skills/ dev-doctor/ SKILL.md -
dev-mode-init
Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent
agentic/code/ on GitHub (opens in a new tab)addons/ aiwg-dev/ skills/ dev-mode-init/ SKILL.md -
devkit-create-addon
Create a new AIWG addon with AI-guided setup
agentic/code/ on GitHub (opens in a new tab)addons/ aiwg-dev/ skills/ devkit-create-addon/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
skillsby NVIDIA Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA,…
-
taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
-
archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
-
khazix-skillsby KKKKhazix 数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
-
Kamiby tw93 👩 🚒 Good content deserves good paper. Layout rules and templates that let AI agents export PDF, PNG and editable PowerPoint.
-
gentle-aiby Gentleman-Programming Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Or…