cortex-profile skill
✓ VerifiedBuilds and manages a cognitive profile by analyzing session history to identify work patterns, cognitive styles, and blind spots.
- GitHub stars
- 76
- Files
- 1
- Last commit
- Nov 12, 2026
- License
- MIT
- Allowed tools
- —
What does the cortex-profile skill do?
cortex-profile builds and manages a cognitive profile by analyzing session history to identify work patterns, cognitive styles, and blind spots.
Summary generated from the skill's SKILL.md.
About the cortex-profile skill
Analyzing your session history to identify work patterns, cognitive styles, and blind spots is what cortex-profile enables. Developers use this skill to build a detailed cognitive profile based on how they explore code and which tools they prefer. By examining Claude Code session history, the tool produces insights into Felder-Silverman dimensions, recurring behavioral patterns, and connection bridges between different project domains.
An agent should load this skill at the start of a session to calibrate responses or when a user asks to see their methodology or patterns. It relies on session history stored in the ~/.claude/projects/ directory to function. Users can perform a full rescan of all history using the rebuild profiles command or update profiles incrementally by recording session ends. The tool provides specific data like persona vectors, domain lists, and attribution traces to show how decisions relate to behavioral signals.
What an agent can do with it
- 1Analyze personal work patternsAsk the AI to explain your specific cognitive style and how you typically approach tasks.
- 2Identify professional blind spotsRequest a report on the specific tools or categories you frequently overlook during development.
- 3Refresh outdated cognitive dataTrigger a complete rescan of all session history to ensure the profile reflects recent work.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the cortex-profile skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the cortex-profile skill in Plugin
/plugin marketplace add cdeust/Cortex /plugin install hypermnesia-mcp@cortex-plugins
Install the cortex-profile skill in Claude Code
~/.claude/skills/cortex-profile/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-profile ~/.claude/skills/cortex-profileInstall the cortex-profile skill in Claude Code (project)
.claude/skills/cortex-profile/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-profile .claude/skills/cortex-profileInstall the cortex-profile skill in Codex
~/.agents/skills/cortex-profile/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-profile ~/.agents/skills/cortex-profileInstall the cortex-profile skill in Gemini CLI
~/.gemini/skills/cortex-profile/SKILL.md
$ npx degit cdeust/Cortex/skills/cortex-profile ~/.gemini/skills/cortex-profileInstall the cortex-profile skill in Claude.ai
npx degit cdeust/Cortex/skills/cortex-profile cortex-profile && zip -r cortex-profile.zip cortex-profile # claude.ai → Customize → Skills → + → Create skill → Upload a skill → cortex-profile.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablecdeust/cortex/skills/cortex-profile is public and reachablegithub.com/cdeust/cortex/tree/HEAD/skills/cortex-profile ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-12github.com/cdeust/cortex/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/cdeust/cortex/blob/HEAD/skills/cortex-profile/SKI ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/cdeust/cortex/blob/HEAD/skills/cortex-profile/SKI ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 89 linesgithub.com/cdeust/cortex/blob/HEAD/skills/cortex-profile/SKI ↗Pass
SKILL.md
View on GitHubProfile — Cognitive Profiling and Methodology
Keywords
profile, methodology, cognitive style, work patterns, blind spots, how do I work, thinking style, domains, rebuild profile, my patterns, session history, cognitive, behavioral, persona
Overview
Cortex builds a cognitive profile from your Claude Code session history — how you explore code, which tools you prefer, what patterns you repeat, where you have blind spots, and how your style connects across different project domains. This profile is used to calibrate responses and surface relevant context.
Use this skill when: Starting a session (auto-injected via hook), wanting to understand your work patterns, or needing to rebuild profiles after significant new work.
Workflow
Step 1: Load Current Profile
cortex:query_methodology({
"cwd": "<current working directory>",
"first_message": "<what the user is working on>"
})
Returns:
- Cognitive style — Felder-Silverman dimensions (active/reflective, sensing/intuitive, visual/verbal, sequential/global)
- Entry patterns — How you typically start work in this domain
- Recurring patterns — Behavioral patterns that repeat across sessions
- Blind spots — Categories, tools, or patterns you tend to miss
- Connection bridges — Cross-domain analogies and structural similarities
- Hot memories — Most relevant active memories for this context
- Fired triggers — Prospective memories activated by the current context
Step 2: Explore Behavioral Features
Dive deeper into your behavioral profile:
cortex:explore_features({ "mode": "persona" })
Returns the 9-dimensional persona vector of every domain and their session-weighted composition (add "domain" for one domain): activeReflective, sensingIntuitive, sequentialGlobal, thoroughness, autonomy, verbosity, riskTolerance, focusScope, iterationSpeed. The response's dimensions lists them in vector order.
Other exploration modes:
"mode": "features"— The sparse behavioral feature dictionary and the features that persist across domains"mode": "attribution"— How the pipeline traces decisions back to behavioral signals"mode": "crosscoder"— With"domain"and"compare_domain", the active features the two domains share and those unique to each; without both, the behavioral patterns that persist across all domains
Step 3: View All Domains
cortex:list_domains({})
Shows all detected project domains with session counts, cognitive style per domain, and last activity timestamps.
Step 4: Rebuild Profiles
When profiles seem stale or after significant new work:
cortex:rebuild_profiles({})
Full rescan of ~/.claude/projects/ session history. Rebuilds all domain profiles, re-extracts patterns, re-classifies cognitive styles, and re-learns behavioral features.
Step 5: Record Session End
Normally automatic via hook, but can be called manually:
cortex:record_session_end({
"domain": "<current domain>",
"summary": "<what was accomplished>"
})
Updates profiles incrementally via EMA (Exponential Moving Average) — no full rebuild needed.
Tips
- Profiles improve over time: The more sessions you have, the more accurate the cognitive profiling becomes
- Cross-domain bridges are powerful: If Cortex detects you use similar patterns in different projects, it surfaces those connections
- Blind spots are actionable: If Cortex says you under-use certain tools or miss certain categories, consider addressing those gaps
- Domain detection is automatic:
cortex:detect_domainclassifies the current working directory into a known domain — no manual tagging needed
Files in this skill
1cortex-profile skill questions
How do I install the cortex-profile skill in Claude Code?
Run npx degit cdeust/Cortex/skills/cortex-profile ~/.claude/skills/cortex-profile. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the cortex-profile skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What information is included in my cognitive profile?
The profile includes your cognitive style (Felder-Silverman dimensions), entry and recurring patterns, blind spots, connection bridges, hot memories, and fired triggers.
How can I update my profile if it becomes outdated?
You can perform a full rescan of your session history using the rebuild command, or record the end of a session to update profiles incrementally.