Learn-skills.dev mcp-sequential-thinking
Use the sequential thinking MCP server (@modelcontextprotocol/server-sequential-thinking) to break down complex problems into ordered, testable steps; use when the task requires careful multi-step reasoning, risk reduction, or dependency-sensitive refactors.
install
source · Clone the upstream repo
git clone https://github.com/NeverSight/learn-skills.dev
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/NeverSight/learn-skills.dev "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data/skills-md/7spade/black-tortoise/mcp-sequential-thinking" ~/.claude/skills/neversight-learn-skills-dev-mcp-sequential-thinking && rm -rf "$T"
manifest:
data/skills-md/7spade/black-tortoise/mcp-sequential-thinking/SKILL.mdsource content
MCP Skill: Sequential Thinking
Scope
Use the MCP server configured as
sequentialthinking in .vscode/mcp.json to produce step-by-step reasoning artifacts for complex changes.
Preconditions
- Ensure
contains a server entry named.vscode/mcp.json
.sequentialthinking
Operating Rules
- Prefer short, ordered steps that can be validated locally.
- Call out unknowns explicitly and convert them into concrete discovery steps (search files, read AGENTS, inspect type errors).
- Keep the solution Occam-simple: avoid introducing new abstractions without a demonstrated need.
When To Use
- Refactors crossing multiple modules (shell/workspace/capability/eventing/integration).
- Any change that might impact DDD boundaries or the append-before-publish contract.
- Debugging nondeterministic behavior (signals/streams, event ordering).
Output Shape
- A numbered sequence of actions.
- Each action includes: target file(s), expected outcome, and how to verify (command or observation).
Prompt Templates
- "Think sequentially about implementing <feature>. Identify risks (DDD boundaries, event causality, signals boundary) and produce a minimal step plan with verification per step."
- "Given this error/log: <paste>, produce an ordered debug plan with the smallest set of probes/changes."