Install
$ agentstack add skill-jlong-quiddity-q-setup ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/q-setup
You are running the full Quiddity setup flow for the user's project. This will discover their process and tools, then generate all three build-loop skills.
Process
- Welcome the user. Briefly explain what Quiddity does: it will scan their
project, learn about their development process and tools, set up CLIs and MCPs, then generate three custom skills (/new-issue, /next-task, /approve) tailored to their project.
- Run /q-scan-project to scan the project structure. This documents key
files, tech stack, conventions, and project layout in .quiddity/project.md.
- Run /q-which-process to discover the user's SDLC. This captures their
branching strategy, code review process, issue workflow, and other conventions in .quiddity/process.md. It can reference project.md for context.
- Run /q-which-tools with all categories needed across the three skills:
`` /q-which-tools issues source-control ci pr ` Because /q-which-process has already run, /q-which-tools can reference .quiddity/process.md` to pre-fill answers and ask smarter questions.
- Run /q-setup-tools to walk through CLI and MCP setup for each tool
discovered in the previous step. This checks what's already installed and helps set up anything missing.
- Run /q-setup-new-issue to generate the
/new-issueskill.
Since project.md, process.md, and tools.json are already populated, this will skip the interviews and go straight to skill-specific questions.
- Run /q-setup-next-task to generate the
/next-taskskill.
- Run /q-setup-approve to generate the
/approveskill.
- Summarize. Show the user what was generated:
- The location of
.quiddity/project.md,.quiddity/process.md, and.quiddity/tools.json - The three generated skills and their locations
- A quick reminder of how to use each skill:
/new-issue [description]— create a new issue/next-task— pick up and implement the next task/approve [pr-number]— merge an approved PR- Suggest they review each generated skill and tweak as needed
- Remind them to commit
.quiddity/and the generated skills to source
control so the whole team shares the same configuration
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jlong
- Source: jlong/quiddity
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.