@cognitum/cog-dev
claudeSlash commands, skills, and subagents for the Cognitum cog dev/test/deploy/ops loop. Wires a Claude Code session to a seed's /mcp endpoint so cogs can be authored against live device state.
5 skills · 5 commands · 4 agents
Cognitum cog: Swarm Deploy. Install or remove cogs on all seeds at once
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin cog-swarm-deploy in cognitum-one/cognitum-claude-plugin. Commands read from the repo's manifest — 1 month ago.
/cog-swarm-deploy:swarm-deployInstall (if needed) and run the `swarm-deploy` cog on the paired seed
Slash commands, skills, and subagents for the Cognitum cog dev/test/deploy/ops loop. Wires a Claude Code session to a seed's /mcp endpoint so cogs can be authored against live device state.
5 skills · 5 commands · 4 agents
Cognitum Seed device plugin — connect to a local Seed appliance at https://169.254.42.1:8443 (HTTPS) or http://169.254.42.1 (USB mode), invoke its 114 MCP tools, and run guided setup / pairing / OTA / thermal / sensor / vector-store flows from Claude Code.
1 skill · 8 commands · 1 agent · 1 MCP server
Cognitum cog: Adversarial Detection. Detects tampered or spoofed sensor signals
1 command
Cognitum cog: Air Quality Monitor. Track indoor air quality with CO2 and particle sensors
1 command
Cognitum cog: Anomaly Attractor. Learns what's normal and catches anything weird
1 command
Cognitum cog: Audit Trail Logger. Record every action for compliance — tamper-proof log
1 command
Neural trading strategies — self-learning LSTM/Transformer/N-BEATS models with Rust/NAPI backtesting
9 skills · 1 command · 4 agents
Organic LinkedIn presence, end to end, with LinkedIn's own rules enforced in code. Orchestrator (context: fork) gates every request against User Agreement §8.2 — refusing automation, scraping, engagement pods, bulk DMs, fake identity and fabricated proof, each with a compliant substitute — then routes to profile / strategy / content / engagement / analytics. Headline and whole-profile scoring with fixes ranked by points per hour; positioning brief with a mandatory exclusion list; cadence priced against real hours with a 90-minute floor; newsletter eligibility + six-month sustainability gate; post linter blocking on engagement bait and screen-reader-hostile Unicode pseudo-bold; repurposing with a reuse ledger; capped commenting roster and template-refusing outreach; analytics that test patterns against a seeded permutation null and refuse to conclude below 10 posts. 17 stdlib tools, 15 references with per-claim confidence levels. No credentials, no API calls, nothing auto-sent. Answers discussion #934.
6 skills · 8 commands · 2 agents
Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the worker's contract block, with no flag to put them back, so the worker is asked for the outcome rather than handed the assertion. Redaction of those values elsewhere is literal over five encodings, so a reshaped copy can still get through; that gap is tracked in a public issue.
26 skills · 1 MCP server · hooks
Run and manage integration test suites with environment setup, database seeding, and cleanup
1 skill · 1 command
Generate realistic test data and seed databases
2 commands
Startup-Gründer: 18 Skills für eine zügige UG- oder GmbH-Gründung mit Satzung und Gesellschaftervereinbarung DE/EN. Cap Table, Geschäftsführung, Statusprüfung, Beirat, Geldwäsche und Vollzug; Seed bis Serie B als Folgerouten. Mit Werkstatt und Schnittflug-Testakte.
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.