kernel
claudeUniversal cognitive kernel. Stack-agnostic thinking patterns, memory management, and planning tools.
39 skills · 11 commands · 1 agent · hooks
Adversarial agent teams. Verification that cannot be self-issued. Standalone; pairs well with kernel.
Plugin panel from marketplace the-foundry in attac-t/the-foundry. Commands read from the repo's manifest — 30 days ago.
craft-charterThe goal gate. Nothing runs until the charter is approved.
craft-oracleGates that exit 0 or 1. Choosing the commands, and promoting judgment into them.
craft-specFrom business need to code, in order. Eleven steps, two gates.
craft-verdictThe committed verdict. Severity, one row per finding, and how the loop ends.
decide-boundaryIs this one project or several? Fires at charter, authoring, and verdict.
/panel:panelOpen a charter and convene a panel. Nothing runs until it is approved.
/panel:verdictRun the gates and the chain, then record a disposition. Oracles execute here, not in a judge.
adversaryThe Adversary. Judges work it did not write. Never repairs. Approves when residual risks are recorded.
authorThe Author. Implements against an approved charter. Writes source and tests; never writes verdicts.
newcomerThe Newcomer. Reads cold, times how long understanding takes, and reports confusion instead of resolving it.
Universal cognitive kernel. Stack-agnostic thinking patterns, memory management, and planning tools.
39 skills · 11 commands · 1 agent · hooks
Domain-driven design patterns for Laravel. Standalone; pairs well with kernel.
47 skills
The package author's playbook. Ecosystem-wide patterns for crafting, shipping, and sustaining pinnacle Laravel packages.
29 skills
Testing syntax and patterns, written against Pest 3. Standalone; pairs well with kernel.
11 skills
Plain English harness. States the budget before the agent writes, and reads what came back.
4 skills · hooks
Where work happens. A run is one attempt at one work item, held outside every repository it changes.
2 skills · hooks
IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware
5 skills · 1 command · 4 agents
Find and verify professional email addresses, search contacts by domain, and enrich company data -- directly in Claude.
13 skills · 1 MCP server
Portable operating method: session lifecycle agents, pre-ship code review, deploy with live verification and state doc update, and production log health check
5 agents
32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.
35 skills · hooks
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Includes LaTeX templates, citation verification, reviewer guidelines, publication-quality figure generation, systems paper structural blueprints, and conference presentation slides.
98 skills
理论溯源与案例重释。审查 PPT、课程、文案或方法论中的经验判断,先判断命题是否成立,再匹配并核实可信理论,用该理论重释案例并标明边界。适用于给自创理论找依据、给 PPT 补理论来源、判断一句话能否上升为理论、检查是否硬套名人;聚焦单次理论锚定,不默认展开历史同构研究。
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.