Loading...
Loading...
Found 70 Skills
Harvest coding-agent session transcripts already on disk (Claude Code, Codex, OpenCode, Cursor, Pi) and extract durable knowledge — topics, people, facts, events, quotes — into whatever persistent memory the agent can reach. Cursor-tracked, budgeted, read-only on sources. Use when asked to collect/import/mine session history into memory, build memory from past sessions, or as a scheduled task. Composes with memory-gardener, which tends what this skill plants.
build a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates
Cheat sheet + workflow for launching interactive coding-agent CLIs (Claude Code, Gemini CLI, Codex CLI, Cursor CLI, and pi itself) via the interactive_shell overlay or headless dispatch. Use for TUI agents and long-running processes that need supervision, fire-and-forget delegation, or headless background execution. Regular bash commands should use the bash tool instead.
Paired benchmark orchestration for comparing coding-agent performance with recursive-mode off and on. Use when the user wants to benchmark recursive-mode, compare recursive vs non-recursive execution on the same project, generate disposable benchmark repos, capture timing/build-test logs, or write a benchmark report.
Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for coding tasks, refactors, feature builds, bug fixes, or other multi-step execution where scope drift is a risk.
Report coding-agent progress, questions, decisions, blockers, tests, PRs, human replies, inbox instructions, and handoffs to the Agora coordination server. Use for every coding task when AGORA_URL is set, especially at session start, before risky or shared edits, when blocked, when asking for human or agent input, after running tests or verification, when opening or updating PRs, when polling for human replies or instructions, and before the final response.
Use when mining coding-agent session history, archived transcripts, memories, or repeated local work to discover recurring workflows that should become new Agent Skills.
Portable OKF knowledge bundle for coding-agent memory and LLM wikis. Use when the user wants to start a wiki, ingest a source, document a repository, query project knowledge with citations, lint for drift, or visualize connections; whenever a repo has a knowledge/ bundle that should inform the task; and when another kb-* skill needs the shared spec, glossary, templates, or trust model.
Coach an AlignFirst spec-plan-execute or AAD workflow using a CLI wrapper around a coding-agent CLI. Use when orchestrating coding agents through AlignFirst protocols non-interactively.
Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta, mean ± stddev, benchmarked). Use whenever you need to test, benchmark, validate, grade, or quantify a skill's quality, check if a skill "actually works," compare two skill versions, optimize a skill's triggering, or set up an eval suite — even if the user just says "is this skill any good," "does my skill work," or "benchmark this skill." Drives Claude Code, OpenAI Codex, Antigravity (agy), Cursor, GitHub Copilot, Amp, opencode, or Grok in headless mode.
interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow
Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model via OpenRouter on DeepSWE", or to verify vendor-reported coding scores. Covers setup, the OpenRouter wiring for mini-swe-agent, single-task / subset / full 113-task runs, and leaderboard submission.