Results for “runs”

Two-stage review engine with four-layer quality model for the WinDAGs meta-DAG. Receives completed node outputs and produces ReviewResult containing QualityVector. Stage 1 (Haiku) checks Floor + Wall on every node. Stage 2 (Sonnet) runs Ceiling evaluation conditionally using economic escalation formula. Enforces BC-EVAL-001 through BC-EVAL-006. Activate when operating as the Evaluator role in the meta-DAG, when reviewing node outputs, when computing quality vectors, or when deciding Stage 2 escalation.

Build, update, and query a persistent project knowledge graph from skills, memory, docs, and code structure — stdlib Python only, no external tools. Dual-mode: skill-library (agent-loom) or application (any consumer repo). Load when the user asks for a knowledge graph, project map, skill relationships, query the graph, update the graph, or trace how components connect. Auto-runs on memory-handoff and project-setup bootstrap. Also triggers on "build the graph", "what connects to X", "map this project".

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Reviews a pull request: runs its own baseline review of the PR diff, then a persistent Monitor watches CI and incoming reviewer comments, triages each comment through an independent skeptical agent, applies only verified fixes, and commits+pushes via inline git commands until CI passes and no comments remain to adopt — then asks whether to merge. Use this skill when the user asks to "review a PR", "monitor PR review comments", "address reviewer feedback on #123", or "watch CI on a pull request".

Composite skill — runs the postmortem chain after any production incident (`/hotfix`, rollback, or prod outage acknowledged). Chains adt-research (root-cause learning) → adr-write (decision capture) → generate-tests (regression test) → security-sweep (conditional, only if root cause is auth/input/secret-related) → knowledge-loop (memory + RAG curation) → handoff. Stops the silent-postmortem failure mode where a hotfix ships and the lessons evaporate. Auto-queues after `/hotfix` Phase 10 completes; also fires when user says "postmortem", "what did we learn", "write up the incident".

Walk through the manual-capture.md checklist for a slug, driving Chrome via the Claude in Chrome MCP to capture each visual that needs more than a static URL — multi-step flows, conversation states, settings panels, age gates on third-party sites. Runs equally well locally (your desktop Chrome) or on a VPS with always-on Chrome + the extension installed. Defaults to unattended mode when `BLOG_AGENT_AUTONOMOUS=1` (which forces `UNATTENDED=1`). Use after /generate-visuals has flagged action-shot or failed-screenshot entries.

User-Mode Driver Framework v2 (UMDF). User-mode driver model that uses the same WDF object model as KMDF but runs in a host process (WUDFHost.exe) protected by the reflector. Required for some categories (Indirect Display Drivers, many sensor and camera drivers) and recommended for any driver that doesn't strictly need kernel mode. USE WHEN: user mentions "UMDF", "WUDFHost", "user-mode driver", "reflector", "IDD", "ISensor", "WDFHOST", "UMDF v2", "FX2" DO NOT USE FOR: KMDF (use `wdf-kmdf`), classic UMDF v1 (deprecated, COM-based)

OWL v5.2 — Pure contrarian. One scanner, one thesis: the crowd is wrong. Monitors crowding across top 30 assets (funding extremity, OI concentration, SM tilt). When crowding persists 4+ hours AND exhaustion signals fire (volume declining, price stalling, RSI divergence), enters AGAINST the crowd to ride the liquidation unwind. 1-2 trades per day max. Re-crowding exit: if the crowd comes back, thesis is dead, exit immediately. DSL High Water Mode (mandatory). The patient predator. v5.2: funding floor lowered from 20% to 12% so the five-factor scoring model actually runs. Added observability logging (top 3 crowding scores per scan cycle).

Runs an evidence-based investigation of a bug, failure, or unexpected behavior with investigate and publishes the resulting investigation report to a user-specified Confluence location. Use when the user wants something debugged, diagnosed, or root-caused AND the findings posted to a Confluence space or page. Requires a configured Atlassian MCP server. Does not investigate to a local file only — use investigate. Does not publish an arbitrary existing markdown file — use markdown-to-confluence. Does not document an already-understood feature to Confluence — use project-documentation-to-confluence. Does not plan or specify a new feature to Confluence — use plan-a-feature-to-confluence. Does not publish to Jira — use work-items-to-jira.

Drive CodeBurn, a free open-source local-first CLI/TUI/web/menubar tool that reads the session files already on disk from 40 AI coding tools (Claude Code, Codex, Cursor, Gemini CLI, Grok, OpenCode, and more) and breaks down token usage and dollar cost by task, model, tool, and project. Use when the user wants to see where their AI coding spend went, find and fix token waste in a Claude Code / agent setup, cap a session's budget before it runs away, compare which model is actually worth its price, check whether AI spend shipped or was reverted, or wire live usage/savings data into an agent over MCP. Triggers on: "codeburn", "npx codeburn", "AI token usage", "AI coding cost", "where did my Claude spend go", "codeburn optimize", "codeburn guard", "codeburn compare models", "codeburn yield", "token waste in CLAUDE.md", "AI spend dashboard".

Turn a work-items.md file (produced by /plan-work-items) into Linear issues, one per slice, in a single target Linear team. Use when you want to publish work items as Linear issues, create implementation tickets to track in Linear, or push a broken-down plan into a Linear team. Requires a configured Linear MCP server and a target team. Reads the team's real workflow states, labels, Projects, and members and resolves every option against them before creating anything; defaults each issue to the team's initial state, unassigned, uncategorized, with no parent or Project unless you ask. Links within-file `Depends on` relationships as native Linear "blocked by" relations and annotates the source file so re-runs resume cleanly. Does not produce the work-items file itself — use plan-work-items first. Does not post to Jira — use work-items-to-jira. Does not post to GitHub — use work-items-to-issues.