principle-attack-the-premise
Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-21 00:15
54,051 results
Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then…
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator,…
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime…
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and…
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence…
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data…
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller…
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default;…
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use…
Cut AI tells from any writing. Must always apply.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity…
A relentless interview that asks every frontier question at once, round by round.
Use when connecting Hermes Agent gateway to a Block Buzz community (CLI, allowlist/hex, env load, mention rules).
Use when self-hosting Block Buzz, mobile pairing, Hermes gateway, or always-on buzz-acp agents.
Drive the OpenAI Codex CLI (`codex` / `codex exec`) from another agent: official Windows installer, one-shot exec --json, resume, sandbox. Triggers:…
Harden Windows Defender privacy settings for authorized pentest engagements. Disables telemetry uploads, sample submission, and cloud reporting to prevent…
Use for domain and subdomain enumeration during authorized pentests. Trigger on DNS-backed host discovery, record review, and expanding an approved domain…
Use for controlled web content discovery, endpoint enumeration, and narrow retest of hidden routes during authorized pentests. Trigger on finding directories,…
Headless GNOME Shell on Wayland with gnome-remote-desktop (GRD) for RDP — the GDM/GNOME-native path (not xrdp/X11). Use when packaging or debugging GNOME 46+…
Use for directory, DNS, and virtual host enumeration during authorized pentests. Trigger on hidden content discovery, vhost review, DNS brute-force within…
Offload one bounded job to agy, opencode, copilot, codex, or hermes via a shared contract (worker, dir, prompt, allow_tools, session). Use when the host agent…
Drive the Nous Hermes Agent CLI (`hermes`) from another agent: official install.ps1, one-shot -z / chat -q -Q, resume, --yolo, ACP/MCP. Triggers:…
Use for high-speed network exposure discovery during authorized pentests. Trigger on very large approved address spaces, strict discovery windows, and cases…