Agent Skills by lary
Showing 15 vetted skills indexed across 1 GitHub repositories.
songlairuiagent-merge
Merge multiple agent context capsules into a unified project state.
songlairuicli-to-skill
Convert a command-line tool into a focused AI workflow guide with recipes and guardrails.
songlairuimake-it-loop
Rewrite task instructions into a loop charter with stopping conditions.
songlairuihandoff
Summarize verified agent work into a handoff artifact with next actions.
songlairuispecimen-card
Package a solved troubleshooting session into a structured specimen card.
songlairuiharness-graph
Organize vague ideas into a persistent local graph with schema-validated nodes and edges.
songlairuisancai-zhen
Route agent tasks through confidence-based arbitration to select execution modes.
songlairuiintent-anchor
Anchors user intent into a session contract with horizon, done state, and drift signals.
songlairuireading-breath
Rewrite dense Chinese prose to restore natural reading rhythm and reduce cognitive strain.
songlairuiagent-bridge
Extract agent work state into a normalized context capsule for handoffs.
songlairuiagent-init
Normalize raw project state into a standardized handoff context for AI agents.
songlairuiforewrite
Write present and future pages to compare project idea gaps.
songlairuisancai-ren
Classify blocked execution and route user feedback in multi-agent workflows.
songlairuisancai-di
Build a confidence-scored execution plan from ambiguous user intent and project context.
songlairuisancai-tian
Seed ideas, render panoramas, and compress graph state in persistent JSON.