Architect Discuss
Use only when the user explicitly includes `architect-discuss` or directly asks to use the architect-discuss skill. Turns raw or ambiguous product and technical requirements into a product and architecture draft before tracked Architect proposal work.
Install
$ agentstack add skill-hlhr202-swe-skills-architect-discuss ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-hlhr202-swe-skills-architect-discuss) 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
Architect Discuss
Use this skill to clarify early product or technical requirements and draft product/architecture direction before creating a tracked Architect proposal.
Core Rules
- Follow the bundled resource
references/discuss-protocol.mdas the source of truth. - Use Architect semantics consistently:
architect/,/architect-*,Architect methodology, andarchitect(...)commit scopes. - Use this skill only after explicit invocation. Do not use it for ordinary architecture discussion unless the user names
architect-discuss. - Inspect relevant project context when the topic touches existing product behavior, modules, APIs, data, or operations.
- Do not create or update tracked Architect artifacts during discussion: no
architect/tracks.mdedits and noarchitect/tracks//artifacts. - If saving a standalone draft, recommend
architect/drafts/.mdand use only a user-confirmed relative project path. Do not use absolute paths,.., tracked Architect artifact paths, or shell redirection, and do not overwrite existing files without explicit confirmation. - Do not modify implementation code, scaffold modules, or run implementation validation as if work has been built.
- Ask the user through the active agent runtime's user-interaction mechanism. If structured choices are unavailable, present the options in text and wait for the user's reply.
- Do not commit unless the user explicitly asks for a commit in the current conversation.
Execution
- Read the bundled resource
references/discuss-protocol.md. - Qualify the explicit
architect-discusstrigger. - Build shallow project context from
architect/docs and relevant code when needed. - Run progressive clarification loops with gates.
- Generate the final product and architecture draft only after the readiness gate passes, or when the user explicitly asks for synthesis with unresolved gates.
- Offer next paths: continue discussion, save standalone draft, split scope, or hand off to
architect-propose.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: hlhr202
- Source: hlhr202/swe-skills
- License: Apache-2.0
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.