geist

What geist does, in the publisher's words

From the project README, punctuation lightly normalized · Open the README on GitHub →

Links

• github.com/tsharp/agent-exchange
• plugins/geist/plugin.json (manifest)

Skills · 11

refine-with-docs

Help a user refine an idea, plan, requirements, process, or draft through focused questions, concrete scenarios, and evolving documentation. Use when the user wants an iterative refinement interview with written outcomes; direct edits and factual questions do not require this workflow.

slop-checker

Classify a response, draft, code change, or assistant trace as slop or not slop, explain why with concrete evidence, and recommend specific fixes. Use when asked for a slop check; do not turn every task into a critique or attempt to identify AI authorship.

swe-architecture

Examine and explain the current architecture of a whole repository or a named section in a visual HTML report. Use for system context, domains, domain terminology, components, layers, dependencies, data ownership, runtime flows, and architectural decisions; improvement candidates belong to an impro…

swe-author

Create or refine SWE skills from the user's requirements, interviews, and representative engineering work. Use for authoring engineering practices, language styles, communication rules, or engineering workflows; activating existing packages is separate setup work.

swe-diagnose

Diagnose and fix a reported software failure or performance regression using a reproduction, targeted investigation, and verification of the original symptom. Use for debugging; an obvious local correction does not require a full investigation.

swe-improve-architecture

Find architecture improvement candidates, generate a visual before/after report, and explore the selected design. Use for module deepening, dependency problems, responsibility changes, or architectural refactoring; a descriptive architecture survey is a separate task.

swe-improve-maintainability

Find and prioritize maintainability improvements with a visual HTML report. Use for reducing change cost, improving testability and ownership, or addressing recurring maintenance friction; use a change review for diff correctness.

swe-init

Configure or repair Geist startup routing for selected personal or workspace style skills. Use when asked to activate existing styles; creating or refining style content is separate authoring work.

swe-prototype

Build a small disposable experiment to answer a concrete engineering, state-model, integration, or UI design question. Use when an experiment would resolve uncertainty faster than discussion; ordinary implementation does not require a prototype.

swe-retro

Review an engineering session or repeated workflow friction and propose evidence-backed improvements to tools, checks, navigation, and guidance. Use for a requested retrospective; do not add a retrospective to every task.

swe-review

Review a branch, commit range, or working changes against the requested behavior and applicable engineering standards. Use for code review or an authorized implementation review; ordinary edits do not require a separate review workflow.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

MCP servers · 1

geiststdio

node ${PLUGIN_ROOT}/runtime/mcp/run.mjs

Read from the plugin's own mcp.json. We list environment variable names, never values.

Category

Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

agent-skills · hooks · productivity

Related by publisher and keywords

• dex-agent-plugindavekilleen

  Dex's portable Agent Skills and MCP surface for compatible harnesses.

• ai-skills-pluginStarraider

  Portable Agent Skills for AI-harness diagnosis, AGENTS.md guidance, prompt design, IDE-native agents, hooks, slash commands, workflow creation, skill authoring and upkeep, and Agent Plugin creation.

• tbd-boardCamerash

  A calm way for your coding agent to ask you for decisions: one HTML page of question cards that you answer in any browser, an add-only decision log, and a list of the small choices the agent made alone.

• mattpocock-skills-productivityAtnic

  General workflow skills from Matt Pocock's Productivity collection, packaged for Codex.

• worldmonitorkoala73

  World Monitor agent plugin: live global-intelligence MCP servers plus task-focused agent skills for country risk, conflict, markets, chokepoints, energy, climate, and related situational awareness.

• scientific-agent-skillsK-Dense-AI

  Ready-to-use scientific and research Agent Skills for biology, chemistry, medicine, and related workflows.