New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Deep Think Maximum Cognitive Effort Protocol Mq8kvw92

by nexu-io in nexu-io/open-design

Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.

Apache-2.0Auto-check passed

Install Deep Think Maximum Cognitive Effort Protocol Mq8kvw92

skills CLI
$ npx skills add nexu-io/open-design --skill deep-think-maximum-cognitive-effort-protocol-mq8kvw92 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nexu-io/open-design deep-think-maximum-cognitive-effort-protocol-mq8kvw92 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nexu-io/open-design.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/community/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 .claude/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deep-think-maximum-cognitive-effort-protocol-mq8kvw92
GitHub stars
100k
Token cost
~1.7k tokens
SKILL.md length
867 words
Files
3 (incl. references)
Skills in repo
245
Repo updated
First seen
Licence
Apache-2.0

At a glance

Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.

  • Works in 8 steps: ORIENT (Memory + Context) → QUESTION (Challenge the Request) → RESEARCH (Evidence Collection) → …
  • Wants a maximum-effort reasoning workflow for a complex
  • SKILL.md covers Complexity Gate (decide first), Phase 1: ORIENT (Memory +…, Phase 2: QUESTION (Challenge… and Phase 3: RESEARCH (Evidence…, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 is an agent skill from nexu-io/open-design. Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `open-design.json` and `references/source-1-mpj79mp4-deep-think.md`).

The repository describes itself as: 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes… The licence is Apache-2.0.

When your agent uses it

  • Wants a maximum-effort reasoning workflow for a complex

Example prompts

  • “/deep-think-maximum-cognitive-effort-protocol-mq8kvw92”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. ORIENT (Memory + Context)
  2. QUESTION (Challenge the Request)
  3. RESEARCH (Evidence Collection)
  4. AUDIT (Gap Analysis)
  5. SYNTHESIZE (Multi-Perspective Analysis)
  6. PLAN (Surgical Execution Design)
  7. EXECUTE + VERIFY (Work → Check → Correct)
  8. CHALLENGE (Adversarial Self-Review)

What it can do on your machine

Read from SKILL.md and the folder at commit 17e2559. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 loads about 1.7k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 867 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nexu-io/open-design at commit 17e2559, republished under its Apache-2.0 licence (© nexu-io). 867 words, ~1,677 tokens.

Download SKILL.mdSave it as .claude/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
deep-think-maximum-cognitive-effort-protocol-mq8kvw92
description
Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.

/deep-think — Maximum Cognitive Effort Protocol

Goal: Activate the highest level of cognitive architecture for complex, multi-step, or ambiguous tasks where quality matters more than speed. Time: 5-15 minutes depending on complexity tier. When to use: Architecture decisions, multi-system changes, irreversible actions, anything where being wrong is expensive.

This is NOT /reason. /reason = "follow the reasoning engine checklist" (fast, lightweight). /deep-think = "maximum effort with structured thinking, research, gap analysis, multi-perspective debate, and adversarial review" (slow, thorough).

Complexity Gate (decide first)

Before starting, classify the task:

TierWhenPhases Used
SIMPLEQuick but thorough — single-domain analysis, clear questionPhases 1 + 5 only
MEDIUMResearch + analysis — multi-source synthesis, comparisonPhases 1-5
COMPLEXFull adversarial — architecture decisions, multi-system changes, irreversible actionsAll 8 phases

Phase 1: ORIENT (Memory + Context)

Load ALL available context before forming any opinion.

  1. Read project memory if available (e.g., MEMORY.md, SESSION.md, or status logs)
  2. Read known pitfalls and gotchas for the target domain (e.g., knowledge/gotchas.md if present)
  3. Read the most relevant local knowledge, READMEs, or chunk files
  4. Query any active workspace memory system (e.g., Honcho or agentmemory) when recent session continuity is needed
  5. Check conversation logs or history for prior attempts or context on this topic
  6. Identify which projects, modules, or systems are involved

If any tool fails: Note "degraded mode" and continue with available sources. Do NOT stall.

Phase 2: QUESTION (Challenge the Request)

Before solving, challenge the problem statement itself.

  1. Use a sequential thinking or reasoning tool (such as sequential-thinking MCP, if available) to decompose the problem into component parts
  2. Ask explicitly:
    • "Is this the right question? Is there a better framing?"
    • "What assumptions are embedded in this request?"
    • "What would go wrong if I do the obvious thing?"
    • "Has this been attempted before? What happened?"
  3. If the framing reveals a deeper issue, address THAT instead

Phase 3: RESEARCH (Evidence Collection)

Gather evidence from multiple sources. Do NOT rely on training data alone.

  1. Run web searches for current best practices, official documentation, and known issues
  2. Use available documentation search tools (such as Context7 MCP, if available) for any referenced libraries, frameworks, or APIs
  3. Check repository skills and custom workspace procedures (e.g., under .agent/skills/ or similar locations)
  4. Load domain-specific context or chunk files using workspace routing maps (e.g., WORKSPACE-AUTOMAP.md or equivalent)
  5. Review workspace-specific conventions and code style files (e.g., knowledge/conventions.md or local READMEs) for established patterns

Rule: Every factual claim must trace to a retrieved source, not memory.

Phase 4: AUDIT (Gap Analysis)

For architecture and system tasks. Skip for pure analysis questions.

  1. What exists? List all relevant files, tools, configs currently in place
  2. What SHOULD exist? Based on research and requirements, what's the ideal state?
  3. What's the delta? Enumerate every gap between current and ideal
  4. What's stale? Cross-reference sources for contradictions and outdated information
  5. What's broken? Check tool health, file integrity, reference validity
Show full SKILL.md (383 more words)Show less

Phase 5: SYNTHESIZE (Multi-Perspective Analysis)

Evaluate the problem from multiple expert perspectives.

  1. Council of Experts — consider the problem as:
    • A Lead Developer: Is this technically sound? What are the edge cases?
    • A Business/Product Strategist: Does this serve the core project objectives and business outcomes?
    • A UX/Ops Pro: Is this maintainable? Will it create friction?
  2. Reconcile conflicts between perspectives and sources
  3. Produce a structured recommendation with:
    • The recommended approach
    • The key tradeoff
    • The risk if wrong
    • The success criteria

Phase 6: PLAN (Surgical Execution Design)

Break the recommendation into executable steps.

  1. Decompose into the smallest possible steps — each independently verifiable
  2. Run the 5-step Pre-Action Verification Protocol on EACH step:
    • Are assumptions stated?
    • Am I targeting the correct file/resource?
    • Is scope minimal?
    • Is action reversible?
    • What are the success criteria?
  3. Define measurable success criteria for the overall task
  4. Sequence steps so failures are caught early (dependencies first)

Phase 7: EXECUTE + VERIFY (Work → Check → Correct)

Execute the plan one step at a time.

  1. One step at a time. Verify output after each step before proceeding.
  2. Work → Verify → Self-Correct loop. Do not assume success.
  3. Anti-Bulk Enforcement: Use the most surgical edit mechanism available. Never rewrite files unless creating from scratch.
  4. 80% Confidence Threshold: If confidence drops below 80% on a high-stakes decision, STOP and ask the user/product owner for input.
  5. Follow Karpathy Doctrine: surgical, minimal, explicit.

Phase 8: CHALLENGE (Adversarial Self-Review)

After producing the result, attack it.

  1. Re-read the original request word by word. Did you actually answer THE question?
  2. What did you miss? What would a senior expert critique about this output?
  3. Would you stake your reputation on this? If not, what needs to change?
  4. Edge cases: What happens under unusual conditions? Empty inputs? Scale? Concurrent use?
  5. Save key learnings to the appropriate memory layer:
    • Debugging insights → update known gotchas (e.g., knowledge/gotchas.md)
    • New patterns → update conventions/standards (e.g., knowledge/conventions.md)
    • Decisions made → update decisions log (e.g., knowledge/decisions.md)
    • Recent continuity worth reusing soon → write a milestone/handoff breadcrumb to the workspace memory system (e.g., Honcho or agentmemory)

What This Workflow Does NOT Do

  • It does NOT replace /reason for quick analysis — use /reason for fast reasoning engine activation.
  • It does NOT save session state — that's /wrap.
  • It does NOT consolidate memory — that's /dream.

© nexu-io, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in plugins/community/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 of nexu-io/open-design.

  • SKILL.md
  • open-design.json
  • references/source-1-mpj79mp4-deep-think.md

Open the folder on GitHubat commit 17e2559

Compare with similar skills

Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 this skillnexu-io/open-design100k—~1.7kAutomated safety check: PassApache-2.0
Cognitive Patternruvnet/ruflo74k—~384Automated safety check: NotesMIT
Deepseek Reasonruvnet/ruflo74k—~626Automated safety check: NotesMIT
Meta Cognitive Reasoningaiskillstore/marketplace4331 repos~3.4kAutomated safety check: PassNone
Ejentum Reasoning Harnesssickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassMIT
Ten-Stage Think LoopAgriciDaniel/claude-obsidian15k—~1.2kAutomated safety check: PassMIT

Similar skills

  • Cognitive Pattern

    ruvnet/ruflo

    Define and manage cognitive patterns for agent reasoning and decision-making

    74k GitHub stars~384 tokensUpdated yesterday
    Auto-check: notes

  • Deepseek Reason

    ruvnet/ruflo

    Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions.

    74k GitHub stars~626 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

  • Meta Cognitive Reasoning

    aiskillstore/marketplace

    Meta-cognitive reasoning specialist for evidence-based analysis, hypothesis testing, and cognitive failure prevention.

    433 GitHub starsUsed in 1 repo~3.4k tokens
    DevelopmentAuto-check passed

  • Ejentum Reasoning Harness

    sickn33/agentic-awesome-skills

    MCP server exposing four cognitive harness modes (reasoning, code, anti-deception, memory).

    47k GitHub starsUsed in 1 repo~1.9k tokens
    DevelopmentAuto-check passed

  • Ten-Stage Think Loop

    AgriciDaniel/claude-obsidian

    Walks a consequential decision through ten reasoning stages, separating observed facts from inferences and unknowns, and stays read-only throughout.

    15k GitHub stars~1.2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Think Tank

    davila7/claude-code-templates

    Run a Virtual Think Tank — a structured multi-persona debate — before planning or making architectural/design/strategic decisions.

    33k GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

More from nexu-io/open-design

All 245 skills in this repo

  • Humanize PPT

    nexu-io/open-design

    Turns raw notes into a talk-ready slide outline with per-page image, diagram or video decisions, then checks the rendered deck against that outline.

    100k GitHub stars~4k tokensUpdated yesterday
    Auto-check passed

  • Last 30 Days Trend Research

    nexu-io/open-design

    Produces a cited Markdown briefing on recent community sentiment and social reaction to a topic, labeling every source it could not actually check.

    100k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • OpenDesign Contribution Flow

    nexu-io/open-design

    Helps newcomers contribute to OpenDesign: ship a skill or design system, translate docs, fix docs or report a bug, ending in a pull request or issue.

    100k GitHub stars~3.5k tokensUpdated yesterday
    Auto-check: notes

  • Chat Motion Overlay Generator

    nexu-io/open-design

    Turns a chat transcript or screenshot into a configurable animated chat clip, rendered as a Remotion bundle with optional transparency.

    100k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Flowai Live Dashboard Template

    nexu-io/open-design

    Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity…

    100k GitHub stars~865 tokensUpdated yesterday
    Auto-check passed

  • Hatch Pet

    nexu-io/open-design

    Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references.

    100k GitHub stars~6k tokensUpdated yesterday
    Auto-check passed

Questions about Deep Think Maximum Cognitive Effort Protocol Mq8kvw92

What does Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 do?

Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task. Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 is an agent skill from nexu-io/open-design. Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.

When should I use Deep Think Maximum Cognitive Effort Protocol Mq8kvw92?

Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 fits situations like: wants a maximum-effort reasoning workflow for a complex.

How do I install Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 in Claude Code?

Run `npx skills add nexu-io/open-design --skill deep-think-maximum-cognitive-effort-protocol-mq8kvw92 -a claude-code`. Or copy the skill folder (plugins/community/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 in nexu-io/open-design) into .claude/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 in your project. Claude Code loads it when a task matches its description.

How do I install Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 in Codex?

Run `npx skills add nexu-io/open-design --skill deep-think-maximum-cognitive-effort-protocol-mq8kvw92 -a codex`. Or copy the skill folder (plugins/community/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 in nexu-io/open-design) into .agents/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 in your project. Codex loads it when a task matches its description.

Can I use Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nexu-io/open-design --skill deep-think-maximum-cognitive-effort-protocol-mq8kvw92 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92, .gemini/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92, .github/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 and .opencode/skills/deep-think-maximum-cognitive-effort-protocol-mq8kvw92 in your project.

What does Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 need to run?

SKILL.md names no scripts, command-line tools or credentials: Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 is instructions for the agent only.

Does Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 use?

Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 100 tokens, read only when the agent opens those files.

What are the alternatives to Deep Think Maximum Cognitive Effort Protocol Mq8kvw92?

Skills that share tags, products or a category with Deep Think Maximum Cognitive Effort Protocol Mq8kvw92: Cognitive Pattern (ruvnet/ruflo, 74k stars), Deepseek Reason (ruvnet/ruflo, 74k stars), Meta Cognitive Reasoning (aiskillstore/marketplace, 433 stars) and Ejentum Reasoning Harness (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Think Maximum Cognitive Effort Protocol Mq8kvw92?

nexu-io (a GitHub organization) maintains it in nexu-io/open-design, which has 100,280 GitHub stars. The repository holds 245 skills in this directory. The repository was last updated on October 10, 2026.

Source: nexu-io/open-design on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.