Archive228/loopkit

Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop.

Archive228/loopkit

Get JSON out of the model reliably. An agent skill from Archive228/loopkit.

Archive228/loopkit

A skill your agent uses when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including…

Archive228/loopkit

Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable).

Archive228/loopkit

Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed.

Archive228/loopkit

Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order.

Archive228/loopkit

Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn.

Archive228/loopkit

Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context.

Archive228/loopkit

Negotiate a pre-code contract between generator and evaluator personas that defines what "done" means before any code is written.

Archive228/loopkit

Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so featurelist.json stays immutable

Archive228/loopkit

Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off.

Archive228/loopkit

Review a diff against the goal spec assuming the code is BROKEN.

Archive228/loopkit

Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.

Archive228/loopkit

A skill your agent uses for ANY bug, test failure, crash, or unexpected behavior.

Archive228/loopkit

Before picking new work, smoke-test the last "completed" feature.

Archive228/loopkit

Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.

Archive228/loopkit

Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.

Archive228/loopkit

Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.

Archive228/loopkit

Get a PDF into the model without blowing the context window or losing structure.

Archive228/loopkit

Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.

Archive228/loopkit

Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work.

Archive228/loopkit

Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically.

Archive228/loopkit

Test the boundary between two systems by the contract, not the implementation.

Archive228/loopkit

Make frontend output look intentional, not AI-generated. An agent skill from Archive228/loopkit.

Archive228/loopkit

Diagnose and fix tests that pass sometimes and fail other times.

Archive228/loopkit

Design the three states every data UI forgets. An agent skill from Archive228/loopkit.

Archive228/loopkit

Write safe, reversible database migrations for this repo's conventions.

Archive228/loopkit

Reduce a change to the minimum that solves the problem. An agent skill from Archive228/loopkit.

Archive228/loopkit

Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context.

Archive228/loopkit

Don't over-equip an agent with tools/MCP servers. An agent skill from Archive228/loopkit.

Archive228/loopkit

Catch the accessibility failures that ship in almost every AI-built UI.

Archive228/loopkit

Verify that an endpoint checks ownership, not just authentication.

Archive228/loopkit

Find the exact commit that introduced a bug. An agent skill from Archive228/loopkit.

Archive228/loopkit

Turn messy WIP into clean, atomic commits with messages that explain why.

Archive228/loopkit

Keep the agent's context lean so accuracy doesn't collapse. An agent skill from Archive228/loopkit.

Archive228/loopkit

Validate and constrain untrusted input at the boundary. An agent skill from Archive228/loopkit.

Archive228/loopkit

Write a PR description a reviewer can approve fast. An agent skill from Archive228/loopkit.

Archive228/loopkit

Check whether a README actually lets a stranger run the project.

Archive228/loopkit

Rebase, squash, or rewrite history without losing work or breaking shared branches.

Archive228/loopkit

Undo a bad change without nuking unrelated work. An agent skill from Archive228/loopkit.

Archive228/loopkit

Write the goal spec on disk before the agent acts, so it can't drift.

Archive228/loopkit

Review SQL and ORM queries for correctness, safety, and performance before they ship.

Archive228/loopkit

Before fixing any bug, write a test that reproduces it and watch it fail.

Archive228/loopkit