Deep Think Maximum Cognitive Effort Protocol Mq8kvw92
nexu-io/open-design
Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.
Systematic improvement of thinking patterns, decision quality, problem-solving abilities, and mental performance.
$ npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills self-improving-cognition --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/self-improving-cognition .claude/skills/self-improving-cognition && rm -rf skills-srcUse ~/.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/
Install the "self-improving-cognition" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/self-improving-cognition into .claude/skills/self-improving-cognition/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-improving-cognition", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/self-improving-cognitionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills self-improving-cognition --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/self-improving-cognition .agents/skills/self-improving-cognition && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "self-improving-cognition" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/self-improving-cognition into .agents/skills/self-improving-cognition/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-improving-cognition", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills self-improving-cognition --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/self-improving-cognition .cursor/skills/self-improving-cognition && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "self-improving-cognition" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/self-improving-cognition into .cursor/skills/self-improving-cognition/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-improving-cognition", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/self-improving-cognition--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills self-improving-cognition --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/self-improving-cognition .gemini/skills/self-improving-cognition && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "self-improving-cognition" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/self-improving-cognition into .gemini/skills/self-improving-cognition/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-improving-cognition", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills self-improving-cognitionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/self-improving-cognition .github/skills/self-improving-cognition && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "self-improving-cognition" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/self-improving-cognition into .github/skills/self-improving-cognition/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-improving-cognition", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills self-improving-cognition --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/self-improving-cognition .opencode/skills/self-improving-cognition && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "self-improving-cognition" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/self-improving-cognition into .opencode/skills/self-improving-cognition/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-improving-cognition", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
self-improving-cognitionSystematic improvement of thinking patterns, decision quality, problem-solving abilities, and mental performance.
Self Improving Cognition is an agent skill from LeoYeAI/openclaw-master-skills. Systematic improvement of thinking patterns, decision quality, problem-solving abilities, and mental performance. Use when noticing cognitive biases, making important decisions, solving complex problems, or wanting to enhance mental clarity and effectiveness.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and assets (for example `_meta.json`, `assets/COGNITIVE_ASSESSMENT_TEMPLATE.md` and `clawhub.json`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Self Improving Cognition loads about 4.3k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 853 words of instructions outside code blocks.
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.
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); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 853 words, ~4,338 tokens.
.claude/skills/self-improving-cognition/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Structured approach to cognitive enhancement through measurable tracking of thinking patterns, bias identification, decision analysis, and mental skill development. Transforms vague "think better" into specific, improvable cognitive competencies.
| Situation | Action |
|---|---|
| Making important decision | Log decision context, alternatives, reasoning, track outcome |
| Noticing cognitive bias | Identify bias type, record instance, develop correction strategy |
| Solving complex problem | Document problem space, approaches tried, breakthrough insights |
| Feeling mentally foggy | Track mental clarity factors, identify patterns, adjust routines |
| Learning new complex concept | Map understanding, identify gaps, track mastery progression |
Append to .learnings/cognition/BASELINE.md:
## [COG-YYYYMMDD-001] Cognitive Baseline Assessment
**Assessed**: 2026-03-12T10:00:00Z
**Overall Cognitive Fitness**: 6.8/10
**Strengths**: Logical reasoning, Metacognition
**Areas for Improvement**: Sustained attention, Creative fluency
### Dimension Scores (1-10)
1. **Attention & Focus**: 5.5/10
- Sustained: 25 minutes average
- Selective: 6/10 (easily distracted by notifications)
- Recovery: 3 minutes after interruption
2. **Memory & Recall**: 6.0/10
- Working: 5±2 items (digit span)
- Long-term: 7/10 (good factual recall)
- Speed: 2.3 seconds average retrieval
3. **Logical Reasoning**: 8.0/10
- Deductive: 85% accuracy
- Inductive: 8/10 (strong pattern recognition)
- Fallacy Detection: 75% accuracy
4. **Creative Thinking**: 5.0/10
- Fluency: 12 ideas/10 minutes
- Originality: 4/10 (mostly conventional)
- Connections: 3 unusual associations/ session
5. **Metacognition**: 7.5/10
- Accuracy: 80% (self-assessment vs. performance)
- Strategy Awareness: 8/10 (knows thinking processes)
- Error Detection: 7/10 (catches 70% of own errors)
### Cognitive Bias Inventory
- **Confirmation Bias**: Moderate (seeks confirming evidence)
- **Anchoring**: High (influenced by initial information)
- **Availability Heuristic**: Moderate (overweights recent examples)
- **Planning Fallacy**: High (underestimates time requirements)
- **Sunk Cost Fallacy**: Low (willing to cut losses)
### Environmental & Lifestyle Factors
- **Sleep**: 6.5/10 quality, 7 hours average
- **Nutrition**: 7/10 (balanced, but afternoon sugar)
- **Exercise**: 5/10 (3x/week, inconsistent)
- **Stress**: 6/10 (moderate work pressure)
- **Mental Stimulation**: 7/10 (varied but not challenging)
### Improvement Priorities
1. **Primary**: Increase sustained attention to 40+ minutes
2. **Secondary**: Boost creative fluency to 20+ ideas/10min
3. **Tertiary**: Reduce planning fallacy impact
4. **Supporting**: Improve sleep quality to 8/10
---Append to .learnings/cognition/DECISIONS.md:
## [DEC-YYYYMMDD-001] Career Path Decision
**Decision Date**: 2026-03-12
**Importance**: High (career direction)
**Timeframe**: 6-12 month impact
**Status**: Decided (Option B)
### Context & Problem
Choose between:
- **Option A**: Stay current role (stable, limited growth)
- **Option B**: Take promotion (more stress, faster growth)
- **Option C**: Switch companies (unknown, potentially higher pay)
### Decision Process
1. **Information Gathering** (3 days)
- Talked to 5 people in similar positions
- Researched market salaries
- Assessed personal tolerance for stress
2. **Criteria Weighting**
- Growth potential: 30%
- Work-life balance: 25%
- Compensation: 20%
- Learning opportunity: 15%
- Team quality: 10%
3. **Option Scoring** (1-10 weighted)
- Option A: 6.2 (stable but stagnant)
- Option B: 7.8 (growth, manageable stress)
- Option C: 6.5 (high risk, high potential reward)
4. **Cognitive Bias Check**
- Status Quo Bias: Considered (Option A attractive due to comfort)
- Loss Aversion: Addressed (willing to risk for growth)
- Overconfidence: Guarded against (consulted others)
- Sunk Cost: Irrelevant (no prior investment)
### Reasoning & Rationale
- **Option B chosen** because:
1. Aligns with 3-year career goal (management track)
2. Stress increase tolerable (15% vs. 50% more pay)
3. Company investment in my growth (training budget)
4. Backup plan exists (can return to individual contributor if needed)
### Confidence Level & Uncertainty
- **Confidence**: 8/10 in decision quality
- **Key Uncertainties**:
- Actual stress level in new role (estimated)
- Team dynamics with new reports (unknown)
- Company stability (market conditions)
- **Contingency Plans**:
- 3-month review: If stress > 7/10, implement coping strategies
- 6-month exit: If miserable, start job search with new title
### Expected Outcome vs. Actual Tracking
- **Expected**: 20% skill growth, 50% pay increase, stress +2 points
- **Actual**: [To be filled after 3 months]
- **Variance Analysis**: [To be filled]
### Cognitive Lessons
1. **Bias Management**: Successfully resisted status quo bias
2. **Decision Quality**: Structured approach improved confidence
3. **Information Sufficiency**: Gathered enough but not too much
4. **Emotion Integration**: Acknowledged fear but didn't let it decide
---Append to .learnings/cognition/PROBLEMS.md:
## [PROB-YYYYMMDD-001] System Architecture Design Problem
**Problem Date**: 2026-03-12
**Complexity**: High (multiple constraints, novel requirements)
**Time Spent**: 8 hours over 2 days
**Solution Status**: Resolved (hybrid approach)
### Problem Definition
Design scalable notification system supporting:
- 1M+ users
- 10+ notification types
- <100ms latency requirement
- 99.99% reliability
- Cost < $500/month at scale
### Solution Approaches Considered
1. **Approach A**: Single monolithic service
- Pros: Simple, fast to build
- Cons: Hard to scale, single point of failure
- Viability: Low (scaling constraints)
2. **Approach B**: Microservices architecture
- Pros: Scalable, fault-tolerant
- Cons: Complex, operational overhead
- Viability: Medium (over-engineered for MVP)
3. **Approach C**: Serverless functions + queue
- Pros: Cost-effective, auto-scaling
- Cons: Cold start latency, vendor lock-in
- Viability: High (meets requirements)
4. **Approach D**: Hybrid (Approach C + simple service)
- Pros: Balances scalability and simplicity
- Cons: More moving parts
- Viability: Selected
### Breakthrough Insights
1. **Core Realization**: 80% of notifications are 3 types → optimize those
2. **Pattern Recognition**: Similar to email sending systems (existing patterns)
3. **Constraint Reframing**: Reliability requirement actually means "eventual consistency with retries"
4. **Simplification**: Batch processing acceptable for non-urgent notifications
### Solution Architecture
- **Urgent notifications** (<100ms): Dedicated service (5% of traffic)
- **Standard notifications**: Serverless functions + queue (95% of traffic)
- **Fallback**: Retry queue with exponential backoff
- **Monitoring**: Latency and error tracking for each type
### Cognitive Process Analysis
- **Initial Impasse**: Overwhelmed by constraints (30 minutes stuck)
- **Breakthrough Method**: Whiteboard diagramming → pattern emergence
- **Critical Thinking**: Questioned each requirement's validity
- **Creative Synthesis**: Combined approaches rather than choosing one
### Performance Metrics
- **Design Quality**: 8/10 (meets all requirements, elegant compromise)
- **Cognitive Effort**: High (complex trade-off analysis)
- **Time Efficiency**: Good (8 hours for complex problem)
- **Solution Novelty**: Medium (adapted existing patterns)
### Improvement Opportunities
1. **Faster Pattern Recognition**: Study more system design patterns
2. **Better Constraint Analysis**: Formalize requirement prioritization
3. **Reduced Overthinking**: Set timebox for decision making
4. **Collaborative Thinking**: Involve others earlier for perspective
---Append to .learnings/cognition/BIASES.md:
## [BIAS-YYYYMMDD-001] Confirmation Bias in Project Estimation
**Identified**: 2026-03-12T14:30:00Z
**Bias Type**: Confirmation Bias
**Context**: Software project timeline estimation
**Impact**: Moderate (2-week underestimation)
### Bias Manifestation
- **Situation**: Estimating new feature development time
- **Behavior**: Sought evidence supporting optimistic timeline
- **Ignored**: Previous similar projects that took longer
- **Result**: 4-week estimate (actual likely 6 weeks)
### Detection Process
1. **Trigger**: Felt too confident about estimate
2. **Check**: Asked "What evidence contradicts this?"
3. **Discovery**: Found 3 similar past projects averaged 6 weeks
4. **Recognition**: Realized seeking confirming evidence only
### Correction Applied
1. **Forced Consideration**: Listed all past similar projects
2. **Outsider View**: Asked "What would I estimate for someone else?"
3. **Pre-mortem**: Imagined project failed, identified causes
4. **Adjustment**: Revised to 6 weeks with risk buffer
### Root Cause Analysis
- **Motivation**: Wanted to please stakeholders with fast timeline
- **Pattern**: Recurring in estimation situations (3rd instance this year)
- **Environment**: Pressure to deliver quickly, reward for optimism
- **Cognitive Style**: Prefers action over caution
### Prevention Strategy
1. **Checklist**: Always review past similar projects before estimating
2. **Devil's Advocate**: Assign someone to challenge optimistic estimates
3. **Buffer Rule**: Add 30% to initial optimistic estimate
4. **Calendar Review**: Monthly review of estimates vs. actuals
### Bias Strength Assessment
- **Before Correction**: 8/10 (strong bias influence)
- **After Correction**: 3/10 (minimal residual influence)
- **Improvement**: 5-point reduction through structured process
- **Durability**: Expected to last 2-3 months before reinforcement needed
### Related Biases to Monitor
- **Planning Fallacy**: Often co-occurs with confirmation bias
- **Optimism Bias**: Similar root in underestimating difficulties
- **Anchoring**: Initial estimate anchors subsequent thinking
---Based on:
Integration Note: This skill provides the thinking toolkit for other self-improving skills, ensuring decisions and problem-solving are based on clear, bias-aware cognition rather than intuition or habit alone.
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (scripts, assets) in skills/self-improving-cognition of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Self Improving Cognition 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Self Improving Cognition this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Deep Think Maximum Cognitive Effort Protocol Mq8kvw92nexu-io/open-design | 100k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Vc Problem Solvingwithkynam/vibecode-pro-max-kit | 1.1k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Is This A Problemanthropics/claude-for-legal | 9.6k | 2 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| First Principles Thinkingmindfold-ai/Trellis | 15k | — | ~4.1k | Automated safety check: Pass | MIT | |
| Cognitive Patternruvnet/ruflo | 74k | — | ~384 | Automated safety check: Notes | MIT |
nexu-io/open-design
Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.
withkynam/vibecode-pro-max-kit
Apply systematic problem-solving techniques when stuck. An agent skill from withkynam/vibecode-pro-max-kit.
anthropics/claude-for-legal
Fast "is this a problem?" answer for the quick Slack question — pattern-matches against your calibration.
mindfold-ai/Trellis
Systematic first principles thinking for any problem domain.
ruvnet/ruflo
Define and manage cognitive patterns for agent reasoning and decision-making
swarmclawai/swarmclaw
Always-on guidance for solving tasks resourcefully. An agent skill from swarmclawai/swarmclaw.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Systematic improvement of thinking patterns, decision quality, problem-solving abilities, and mental performance. Self Improving Cognition is an agent skill from LeoYeAI/openclaw-master-skills. Systematic improvement of thinking patterns, decision quality, problem-solving abilities, and mental performance.
Self Improving Cognition fits situations like: noticing cognitive biases; making important decisions; solving complex problems; wanting to enhance mental clarity and effectiveness.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a claude-code`. Or copy the skill folder (skills/self-improving-cognition in LeoYeAI/openclaw-master-skills) into .claude/skills/self-improving-cognition in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a codex`. Or copy the skill folder (skills/self-improving-cognition in LeoYeAI/openclaw-master-skills) into .agents/skills/self-improving-cognition in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill self-improving-cognition -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/self-improving-cognition, .gemini/skills/self-improving-cognition, .github/skills/self-improving-cognition and .opencode/skills/self-improving-cognition in your project.
Going by SKILL.md and its folder, Self Improving Cognition needs a shell for the scripts in its folder. Our summary lists: A Bash shell.
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.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Self Improving Cognition is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Self Improving Cognition: Deep Think Maximum Cognitive Effort Protocol Mq8kvw92 (nexu-io/open-design, 100k stars), Vc Problem Solving (withkynam/vibecode-pro-max-kit, 1.1k stars), Is This A Problem (anthropics/claude-for-legal, 9.6k stars) and First Principles Thinking (mindfold-ai/Trellis, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.