changeset
01Skill Claude CodeCodex
Analyze commits since last release and create a changeset .md file to trigger the release CI workflow.
Local-first semantic code search for AI coding assistants. Indexes your codebase with local embeddings and serves context over MCP — find code by meaning, check impact before editing, and surface complexity hotspots, all without sending code externally.
Skill Claude CodeCodex
Analyze commits since last release and create a changeset .md file to trigger the release CI workflow.
Skill Claude CodeCodex
Evaluate Lien Review's AI review quality by creating a PR with known violations, waiting for the automated review, then scoring output against ground truth.
Skill Claude CodeCodex
Build Lien, restart MCP, then use a 7-agent team to test tools, review docs, audit code quality, evaluate architecture, review tests, audit security, and assess DX — all in parallel.
Skill Claude CodeCodex
Run the agent-review prompt harness in CC iteration mode against a rule or fixture. Free, low-fidelity. Use for prompt-authoring inner loop. The 9/10 reliability bar must still be measured via npm run test:harness -w @liendev/review -- --calibrate 10 against OpenRouter (the prod default model) before shipping any…