# Sequential Thinking > [AI & Tools] Use when you need to apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. - Skill: `duc01226/sequential-thinking-3` (Agent Skill, multi-file: 15 files) - Install (CLI): `npx skillmds@latest add duc01226/sequential-thinking-3` - Raw SKILL.md: https://api.skillmd.com/api/skills/duc01226/sequential-thinking-3/raw - Safety review: pending (external: skill-scanner PASS, skillspector CAUTION) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - License: MIT - Author: duc01226 (https://skillmd.com/u/duc01226) - Updated: 2026-09-22 - Page: https://skillmd.com/skills/duc01226/sequential-thinking-3 --- ## Quick Summary **Goal:** Solve complex problems through structured, reflective thought sequences with dynamic adjustment and revision. **Workflow:** 1. **Estimate** — Start with loose thought count, adjust as understanding evolves 2. **Structure Thoughts** — One aspect per thought; state assumptions and uncertainties 3. **Revise/Branch** — Mark revisions of earlier thoughts; branch for alternative approaches 4. **Hypothesize & Verify** — Generate solution hypothesis, test it, iterate until verified 5. **Complete** — Mark final only when solution verified and confidence achieved **Key Rules:** - Dynamically expand/contract thought count as complexity changes - Explicitly mark revisions with original reasoning and why it changed - Can apply explicitly (visible markers) or implicitly (internal methodology) **Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).** # Sequential Thinking Structured problem-solving via manageable, reflective thought sequences with dynamic adjustment. ## When to Apply - Complex problem decomposition - Adaptive planning with revision capability - Analysis needing course correction - Problems with unclear/emerging scope - Multi-step solutions requiring context maintenance - Hypothesis-driven investigation/debugging ## Core Process ### 1. Start with Loose Estimate ``` Thought 1/5: [Initial analysis] ``` Adjust dynamically as understanding evolves. ### 2. Structure Each Thought - Build on previous context explicitly - Address one aspect per thought - State assumptions, uncertainties, realizations - Signal what next thought should address ### 3. Apply Dynamic Adjustment - **Expand**: More complexity discovered → increase total - **Contract**: Simpler than expected → decrease total - **Revise**: New insight invalidates previous → mark revision - **Branch**: Multiple approaches → explore alternatives ### 4. Use Revision When Needed ``` Thought 5/8 [REVISION of Thought 2]: [Corrected understanding] - Original: [What was stated] - Why revised: [New insight] - Impact: [What changes] ``` ### 5. Branch for Alternatives ``` Thought 4/7 [BRANCH A from Thought 2]: [Approach A] Thought 4/7 [BRANCH B from Thought 2]: [Approach B] ``` Compare explicitly, converge with decision rationale. ### 6. Generate & Verify Hypotheses ``` Thought 6/9 [HYPOTHESIS]: [Proposed solution] Thought 7/9 [VERIFICATION]: [Test results] ``` Iterate until hypothesis verified. ### 7. Complete Only When Ready Mark final: `Thought N/N [FINAL]` Complete when: - Solution verified - All critical aspects addressed - Confidence achieved - No outstanding uncertainties ## Application Modes **Explicit**: Use visible thought markers when complexity warrants visible reasoning or user requests breakdown. **Implicit**: Apply methodology internally for routine problem-solving where thinking aids accuracy without cluttering response. ## Scripts (Optional) Optional scripts for deterministic validation/tracking: - `scripts/process-thought.js` - Validate & track thoughts with history - `scripts/format-thought.js` - Format for display (box/markdown/simple) See README.md for usage examples. Use when validation/persistence needed; otherwise apply methodology directly. ## References Load when deeper understanding needed: - `references/core-patterns.md` - Revision & branching patterns - `references/examples-api.md` - API design example - `references/examples-debug.md` - Debugging example - `references/examples-architecture.md` - Architecture decision example - `references/advanced-techniques.md` - Spiral refinement, hypothesis testing, convergence - `references/advanced-strategies.md` - Uncertainty, revision cascades, meta-thinking --- > **[IMPORTANT]** Use `TaskCreate` to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip. > **AI Mistake Prevention** — Failure modes to avoid on every task: > > **Re-read files after context changes.** Context compaction, resume, or long-running work can make memory stale; verify current files before acting. > **Verify generated content against source evidence.** AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. > **Check downstream references before deleting or renaming.** Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. > **Trace the full impact chain after edits.** Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. > **Verify ALL affected outputs, not just the first.** One green check is not all green checks; validate every output surface the change can affect. > **Assume existing values are intentional — ask WHY before changing OR flagging one as a defect.** Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. > **Surface ambiguity before acting — don't pick silently.** Multiple valid interpretations require an explicit question or stated assumption with risk. > **Assert the outcome your system owns, not the intermediate state your infrastructure owns.** When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. > **Keep shared guidance role-relevant.** Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols. > **Critical Thinking Mindset** — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. > **Anti-hallucination:** Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. **MUST ATTENTION** apply critical + sequential thinking — every claim needs appropriate traced evidence (`file:line` for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence. **MUST ATTENTION** apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting. > **Project Protocol Overlay** — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the `Target` column of the project's skill-protocol index (`docs/project-reference/skill-protocols-reference.md` by default; a `referenceDocs` entry in `docs/project-config.json` overrides the path), taking the most specific matching tier ONLY — exact name > glob > `*`. **That precedence orders overlays against EACH OTHER, never against this skill.** Read ONLY the matched bodies, resolved as `/.md`; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: `.claude/skills/project-skill-protocol/references/registry.md`. > > Overlays are **ADDITIVE ONLY**: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently. **MUST ATTENTION** resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > `*`, which ranks overlays against each other, NEVER against this skill), read only matched bodies at `/.md`; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user. ## Closing Reminders **IMPORTANT MUST ATTENTION** break work into small todo tasks using `TaskCreate` BEFORE starting **IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries):** - **AI Mistake Prevention:** verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity. - **Critical Thinking:** critical+sequential thinking; traced `file:line` proof, confidence >80% to act. **IMPORTANT MUST ATTENTION** search codebase for 3+ similar patterns before creating new code **IMPORTANT MUST ATTENTION** cite `file:line` evidence for every claim (confidence >80% to act) **IMPORTANT MUST ATTENTION** add a final review todo task to verify work quality **[TASK-PLANNING]** Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.