Install
$ agentstack add skill-leslielinxinxiang-dde-agent-skills-dde-ext-brainstorm ✓ 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
DDE Extension: Brainstorm
Skill Version: v0.1
Authority Chain
- Commander:
dde-bootstrap - Write gate:
dde-code-guard - Completion gate:
dde-task-closer - This skill is advisory-only and cannot modify files directly.
When to Use
Use this skill when:
- User asks for:
brainstorm,ideation,options,tradeoff,alternatives - User asks for:
头脑风暴,方案对比,思路发散,可行性讨论,怎么选方案 - Requirement has multiple feasible paths and needs decision support before implementation
- DDE workflow explicitly selects ideation mode
Do Not Use When
- User explicitly requests direct file modifications now
- Task is deterministic mechanical edit with no decision branches
- A final approved plan already exists and user asks to execute immediately
Hard Constraints
- Advisory-only: no writes to code/docs/skills in this skill.
- No requirement authority takeover: Layer 0-4 remains source of truth.
- If a proposed direction conflicts with Layer docs, emit
RFC_REQUIREDand stop for DDE RFC flow. - If user chooses a direction that requires edits, emit handoff only and return control to
dde-code-guard.
Workflow
Phase 1: Problem Framing
- Restate objective in 1-3 lines.
- List constraints (performance, safety, timeline, compatibility).
- Mark unknowns and assumptions explicitly:
ASSUMPTION: ...
Phase 2: Option Generation
Generate at least 2 options (prefer 3):
- Option A: conservative / low-risk
- Option B: balanced / default
- Option C: aggressive / high-upside (optional)
For each option include:
- Core idea
- Required changes (high-level)
- Dependencies/tools needed
- Risks/failure modes
- Cost (time/complexity)
- Expected benefit
Phase 3: Tradeoff Matrix
Provide side-by-side matrix scored 1-5:
- feasibility
- implementation effort
- maintainability
- scalability
- risk level (inverse score: lower risk = higher score)
- alignment with Layer docs
Phase 4: Recommendation
- Recommend one option with rationale.
- Provide fallback option.
- List decision locks (what must stay true for this recommendation to hold).
Phase 5: Decision Gate
Ask user to select:
SELECTED_OPTION: A|B|C- or request refinement round.
If selection implies requirement/document change:
- emit
RFC_REQUIREDand stop for DDE RFC flow.
If selection implies code/doc writes without requirement conflict:
- emit
DDE_EXTENSION_HANDOFF_REQUIREDand transfer todde-code-guard.
Phase 6: Decision Artifact Contract
When user confirms selected option, produce a DDR draft (without writing files in this skill) using this target convention:
docs/decisions/DDR-YYYYMMDD-.md- Template source priority:
- Project instance:
docs/decisions/DDR_TEMPLATE.md - Skill template fallback:
templates/DDR_TEMPLATE.md
DDR required fields:
- Decision Question
- Options Considered
- Selected Option
- Why Selected
- Impacted Files
Output Contract (Mandatory)
Output in this exact structure:
BRAINSTORM BRIEFASSUMPTIONSOPTIONSTRADEOFF MATRIXRECOMMENDATIONDECISION REQUESTHANDOFF STATUS
Where HANDOFF STATUS is one of:
NO_WRITE_NEEDEDRFC_REQUIREDDDE_EXTENSION_HANDOFF_REQUIRED
Handoff Block Format
When handoff is required, append:
DDE_EXTENSION_HANDOFF_REQUIRED
Fields:
- Reason
- Selected option
- Target files (if known)
- Expected effect
- Risk notes
- Rollback note (high-level)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: LeslieLinXinxiang
- Source: LeslieLinXinxiang/dde-agent-skills
- 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.