Install
$ agentstack add skill-jlong-quiddity-q-setup-next-task ✓ 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
Setup /next-task
You are generating a custom /next-task skill for the user's project.
Required categories
This skill needs the following tools.json categories: issues, source-control, ci
Process
- Ensure tools are configured. Check if
.quiddity/tools.jsonexists and
contains the issues, source-control, and ci categories. For any missing categories, run /q-which-tools with those categories (e.g., /q-which-tools issues source-control ci).
- Read the configuration. Load all available Quiddity context:
.quiddity/project.md— project structure, tech stack, test commands,
source directories, entry points
.quiddity/process.md— branching strategy, code review process,
commit conventions
.quiddity/tools.json— extract theissues,source-control, and
ci categories
.quiddity/architecture.md— technical architecture and design direction
(if it exists)
- Ask skill-specific questions not covered by tools.json:
- How should the next task be selected? (highest priority, oldest, specific
label, assigned to me, etc.)
- Should the skill assign the issue to the current user?
- Any PR title/description conventions beyond what's in tools.json?
- Should it run local checks before pushing?
- What should it do when blocked? (report back, skip to next task, etc.)
- Generate the skill. Write a complete
/next-taskSKILL.md to the
project's skills directory. The generated skill should:
- Query the issue tracker for the highest-priority available task using the
configured tool and filters
- Assign the issue and move it to the "In Progress" state
- Create a branch following the configured naming convention
- If
.quiddity/architecture.mdexists, read it before implementing to
understand design direction, constraints, and patterns — it may describe things not yet built that are relevant to the current task
- Implement the changes described in the issue
- Run local CI checks before pushing
- Open a PR with the right format and link it to the issue
- Update the issue status
- Include judgment — if something blocks the task, report back instead of
plowing ahead
- Reference
.quiddity/tools.jsonfor all tool-specific configuration
- Show the generated skill to the user and ask for confirmation before
finalizing.
Generated skill template
The generated /next-task skill should follow this general structure, adapted to the user's specific tools:
---
name: next-task
description: Pick up the next task, implement it, and open a PR.
---
# /next-task
[Instructions tailored to the user's issue tracker, source control,
branch naming, CI checks, and PR conventions.]
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.