Results for “runs”

Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits.

Validates Claude Ads contracts, bundles, scores, runs, capabilities, repositories, and releases with deterministic checks and recovery steps.

Runs the casr operator skill in a Codex environment, reading the source skill for behavior and using the local shell with JSON/NDJSON command surfaces.

Runs project tests, stages and commits changes with a conventional message, then rebases and pushes to the current branch, stopping on any failure.

Runs DNS, email security, SSL, WHOIS, and network checks by calling the dnsrobot.net API, with no API key required.

Runs a local teleprompter web app with a phone remote control, QR pairing, and dual-screen sync for video recording.

Launches a model evaluation batch with parameter collection, pre-flight checks, execution, and post-run analysis for interactive or foreground runs.

Improves skills by analyzing execution data to identify patterns in successful versus failed runs, staging changes for human approval.

Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benign over-refusal or measure refusal/KL trade-offs, not for training.

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment.

Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the user runs /si:status or asks how full or healthy the agent memory is.

Monthly P&L, cashflow forecast, runway calculation, and top movers. Investor-ready Gamma deck plus Slack summary, archived to Notion. Runs monthly on a 1st-of-month cron schedule.

Guides quality-first TDD for new behavior, bug fixes, and test changes. Selects the smallest test layer, proves a distinct regression risk, and runs bounded RED-GREEN-REFACTOR verification.

Manage golden dataset regression tests for LLM prompts using Promptfoo. Includes setup, test case capture, repeatable runs, and reports. Use after changing prompts or when checking for prompt regressions.

Validate skill outputs against assertion manifests to detect regressions, enforce quality gates, and bootstrap starter manifests from historical runs.

Runs five parallel review agents on code changes, validates findings, triages them, and applies approved fixes after confirmation.

Runs OWASP ZAP security scans against web applications using Java or Docker, with setup guidance and links to upstream documentation.

Runs a structured self-review checklist before committing substantial code changes, covering edge cases, error paths, test coverage, documentation, and code quality.

Generates or edits images for projects using the OpenAI Image API, with support for batch runs and structured prompt augmentation.

Runs an adversarial code review with two blind judges analyzing the same code from opposing perspectives to find flaws before production.

Runs commands, inspects git state, debugs CI failures, and makes narrow fixes with exact proof of what was executed and verified.

Runs a ten-round adversarial gauntlet to pressure-test absolute claims, refining them with explicit boundaries and an Oracle synthesis.

Runs API, performance, load, stress, and HTTP tests using the basjoofan CLI with configurable concurrency, duration, and statistics output.

Runs and interprets Elixir/Phoenix tooling (mix test, credo, dialyzer, format), generates OTP-conforming modules, and helps with Ecto and LiveView patterns.

Runs a structured, multi-round brainstorm to capture actors, features, scope, constraints, and business rules for a project before writing a spec.

Discovers, finds, audits, repairs, adapts, crafts, runs, debriefs, saves, and prepares repeatable AI-agent loops for publication, treating loops as bounded feedback systems.

Runs NGS read QC, alignment, and BAM processing, wrapping FastQC, BWA/Bowtie2/Minimap2, SAMtools, and MultiQC for automated read-to-BAM workflows.

Runs a test-driven rendering loop for Copier templates, writing E2E assertions first and iterating until every flavor renders cleanly before committing.

Runs Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Runs a five-phase pipeline—evaluation, specification, implementation, review, and QA—to build a feature end-to-end with specialized agents.

Implements a code change on a feature branch, opens a single pull request to main, and runs a code review loop before handoff.

Thin orchestrator — runs capture-brief, sam-scan, and competitive-snapshot in order for a new pursuit row. Use when user wants standard admin kickoff without running three buttons manually.

Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.

Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.

For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and perform a retrospective on a chosen run -- what went well, what failed, process suggestions, quality of effect design, breakpoint patterns -- mirroring the /babysitter:retrospect workflow but applied to an external repo. Invoke when asked to "retrospect on repo X's run", "analyze how someone else used babysitter", or "review an external babysitter run".

Routes research queries to specialist skills or runs a fallback search-and-synthesize workflow, with deterministic classification and transparent routing decisions.