Debugging workflow with an explicit rule: no fixes until the root cause is understood. The flow is investigate, analyze, hypothesize, then implement.
Automate repetitive workflows and reduce manual effort
Example: Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example: Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example: Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Time estimate: 15-45 minutes depending on use case complexity
Prerequisites
Submit your Claude Code skill and start earning
epx add garrytan/gstack --skill gstackCompatible with
Supported agents
Debugging workflow with an explicit rule: no fixes until the root cause is understood. The flow is investigate, analyze, hypothesize, then implement. Imported from investigate/SKILL.md in garrytan/gstack.
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versioninvestigateExecute the skills CLI command in your project's root directory to begin installation:
epx add garrytan/gstack --skill gstackFetches investigate from garrytan/gstack and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
.cursor/skills/investigate
Restart Cursor to activate investigate. Access via /investigatein your agent's command palette.
Learn more:View source on GitHubSkills CLI docsAbout CursorWhat are agent skills?
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
gstack-upgrade
garrytan/gstack · gstack-utility · same repo
freeze
garrytan/gstack · gstack-safety · same repo
context-save
garrytan/gstack · gstack-memory · same repo
benchmark-models
garrytan/gstack · gstack-multi-ai · same repo
design-consultation
garrytan/gstack · gstack-design · same repo
github
steipete/clawdis · Productivity · tag: github
investigate fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
We added investigate from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Solid pick for teams standardizing on skills: investigate is focused, and the summary matches what you get after install.
I recommend investigate for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Solid pick for teams standardizing on skills: investigate is focused, and the summary matches what you get after install.
We added investigate from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
investigate reduced setup friction for our internal harness; good balance of opinion and flexibility.
investigate fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
investigate has been reliable in day-to-day use. Documentation quality is above average for community skills.
Registry listing for investigate matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 26