flamemida Sequential Thinking
A tool for dynamic, reflective problem-solving through a chain of numbered thoughts. Full parity with the Sequential Thinking MCP server — same parameters, same state management, same behavioral contract.
How to Use This Skill
When this skill is activated, use scripts/think.ts as your primary reasoning mechanism. Do not reason in prose — reason through the script. Every step of your analysis should be a thought submitted via the script, making your reasoning chain explicit and trackable.
Workflow
- Reset state at the start of every new thinking session
- Loop: Submit thoughts one at a time via the script, incrementing
thoughtNumbereach time - Adapt: Revise earlier thoughts, branch into alternatives, or extend depth as needed
- Terminate: Set
nextThoughtNeeded falseonly when you have a confident final answer - Respond: After the final thought, provide the answer to the user
Each thought should be a single Bash tool call. Think in the thought, not outside it.
Script Location
scripts/think.ts
Run via bun from the skill's base directory.
Commands
Reset (required before every new session)
bun scripts/think.ts --reset
Submit a Thought
Required flags: --thought, --thoughtNumber, --totalThoughts, --nextThoughtNeeded
bun scripts/think.ts \
--thought "Your analysis for this step" \
--thoughtNumber 1 \
--totalThoughts 5 \
--nextThoughtNeeded true
Submit a Revision
Revises a previous thought. The original stays in history; the revision is appended as a new entry. Requires --isRevision and --revisesThought.
bun scripts/think.ts \
--thought "Corrected analysis" \
--thoughtNumber 3 \
--totalThoughts 5 \
--nextThoughtNeeded true \
--isRevision --revisesThought 1
Submit a Branch
Explores an alternative path from a prior thought. Requires both --branchFromThought and --branchId.
bun scripts/think.ts \
--thought "Alternative approach" \
--thoughtNumber 4 \
--totalThoughts 7 \
--nextThoughtNeeded true \
--branchFromThought 2 --branchId alt-approach
Extend Depth
Signal that more thoughts are needed beyond the original estimate.
bun scripts/think.ts \
--thought "Scope is larger than expected" \
--thoughtNumber 6 \
--totalThoughts 8 \
--nextThoughtNeeded true \
--needsMoreThoughts
Inspect Full State
bun scripts/think.ts --status
Returns JSON with fullHistory and branchDetails.
Output Format
Each thought invocation prints the thought to stderr and a compact status line to stdout:
💭 Thought 3/7
The analysis shows that...
[3/7] history=3 next=true
Revision and branch thoughts use 🔄 Revision and 🌿 Branch headers respectively.
Parameters (Full MCP Parity)
| Parameter | Type | Required | Description |
|---|---|---|---|
--thought |
string | yes | The content of this thinking step |
--thoughtNumber |
int >= 1 | yes | Current thought number in the sequence |
--totalThoughts |
int >= 1 | yes | Estimated total thoughts needed (adjustable) |
--nextThoughtNeeded |
bool | yes | true to continue, false to terminate |
--isRevision |
flag | no | Marks this thought as revising a previous one |
--revisesThought |
int >= 1 | no | Which thought number is being revised (required with --isRevision) |
--branchFromThought |
int >= 1 | no | Create a branch starting from this thought number |
--branchId |
string | no | Label for the branch (required with --branchFromThought) |
--needsMoreThoughts |
flag | no | Signal that totalThoughts should be expanded |
Behavioral Rules
These match the MCP server's tool description exactly:
- Start with an initial estimate of
totalThoughts, but adjust freely as understanding deepens - Auto-adjust: If
thoughtNumberexceedstotalThoughts, the script raisestotalThoughtsto match - Revise previous thoughts when you realize an earlier step was wrong or incomplete — set
--isRevisionand--revisesThought N. The original stays in history; the revision is appended - Branch to explore alternative reasoning paths — set both
--branchFromThought Nand--branchId label. This does not abandon the main line - Extend beyond the initial estimate at any time with
--needsMoreThoughtsand an increased--totalThoughts - Express uncertainty — not every thought needs confidence. Questioning and exploring is encouraged
- Filter noise — ignore information irrelevant to the current step
- Generate hypotheses when you have enough evidence, then verify them against prior thoughts in the chain
- Iterate hypothesis-verification cycles until satisfied with the answer
- Terminate only when you have a satisfactory answer — set
--nextThoughtNeeded false - Non-linear paths are first-class — branching, backtracking, and revision are features, not failures
State Management
- State is persisted to
scripts/.think_state.jsonbetween invocations thoughtHistory[]is append-only — thoughts are never deletedbranches{}maps branch IDs to their thought arrays--resetclears all state for a fresh session--statusdumps the full state as JSON for inspection
Example Session
See references/example-session.md for a complete worked example demonstrating normal thoughts, revisions, branches, and dynamic depth adjustment.