Chalk Labs
Need help deploying continuous-cognition?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/trevormentis-spec-continuous-cognition
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/continuous-cognition
What's inside
- Skill name
continuous-cognition- Description
- Lightweight persistent cognition layer. DeepSeek Flash runs every 15 minutes to summarize events, update confidence state, detect anomalies, evolve source trust, and maintain situational awareness. Escalates to Pro/Opus when thresholds are crossed. No recursive loops, no endless reflection.
- License
- unknown
- Metadata
- author: Trevor · version: 1.0.0 · difficulty: advanced · displayName: Continuous Cognition
- Instructions
- 96 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (6)
- SKILL.md
- config.json
- config.yaml
- flash_cognition.txt · prompts/
- cognition_pipeline.py · scripts/
- utils.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from trevormentis-spec/OpenClawTrevorMentis
- 0.474score
daily-intel-brief
trevormentis-spec
Produce Trevor's Daily Intelligence Brief — a dated, structured intelligence product with ten regional sections (Europe, North America, Central America &…
SkillCFreshness: CClaude Code +9 - 0.474score
data-charts-visualization
trevormentis-spec
Default skill for structured-data visualization, chart generation, and dashboard-style reporting.
SkillCFreshness: CClaude Code +9 - 0.469score
bluf-report
trevormentis-spec
Produce a BLUF (Bottom Line Up Front) executive report — one-page or shorter, headline judgment first, calibrated confidence, three things-you-need-to-know…
SkillCFreshness: CClaude Code +9 - 0.467score
akashic-doc-analyzer
trevormentis-spec
Parse, analyze, and extract content from documents (PDF, DOCX, PPTX, audio).
SkillCFreshness: CClaude Code +9 - 0.467score
corpusgraph
trevormentis-spec
Document ETL, entity extraction, and relationship graphing engine.
SkillCFreshness: CClaude Code +9 - 0.467score
agent-intelligence
trevormentis-spec
Query agent reputation, detect threats, and discover high-quality agents across the ecosystem.
SkillCFreshness: CClaude Code +9 - 0.467score
a2a
Google / Linux Foundation
Google A2A (Agent-to-Agent) Protocol — lets Trevor discover, communicate with, and be discovered by other AI agents.
SkillCFreshness: CClaude Code +9 - 0.467score
content-generation
trevormentis-spec
Generate high-quality content across multiple formats.
SkillCFreshness: CClaude Code +9 - 0.466score
social-poster
trevormentis-spec
Write and adapt content for multiple social platforms.
SkillCFreshness: CClaude Code +9 - 0.462score
trevor-web-collection
trevormentis-spec
Use for any collection task that involves extracting structured data from a website.
SkillCFreshness: CClaude Code +9 - 0.462score
Data Analysis
trevormentis-spec
Data analysis and visualization.
SkillCFreshness: CClaude Code +9 - 0.456score
Content Marketing
trevormentis-spec
Plan, create, and distribute content with editorial calendars, funnel strategy, and repurposing workflows.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 6
- Last commit (this folder)
- May 27, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get continuous-cognition running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
continuous-cognition skill. Agent Mart. https://agentmart.dev/skills/trevormentis-spec-continuous-cognition (last updated 2026-10-24)