Archive228/loopkit

active-memory-reminder

Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.

原文の言語: 英語

model-routing

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

原文の言語: 英語

progress-reading-protocol

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. The orientation ritual that lets fresh-context sessions reconstruct project state in under…

原文の言語: 英語

suggest-next-features

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

原文の言語: 英語

using-loopkit

Use 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 clarifying questions.

原文の言語: 英語

my-new-skill

One sentence that describes WHEN to invoke this skill. Write it as a trigger phrase, not a summary — include the words a user would say ("fix bug", "add feature", "review diff"). The agent routes on this field.

原文の言語: 英語

hitl-escalate

Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop. Use when the loop hits an ambiguous spec, a missing credential, a destructive action needing approval, or 3+ consecutive verify failures on the same task.

原文の言語: 英語

evaluator-calibration

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

原文の言語: 英語

feature-list-json

Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order. The ledger fresh-context sessions read to know what's done, what's next, and what they're forbidden to touch.

原文の言語: 英語

harness-stripping

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

原文の言語: 英語

init-script-contract

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

原文の言語: 英語

planner-spec-expand

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

原文の言語: 英語

self-eval-bias

Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.

原文の言語: 英語

sprint-contract

Negotiate a pre-code contract between generator and evaluator personas that defines what "done" means before any code is written. Turns fuzzy specs into a testable target the evaluator can hold the generator to.

原文の言語: 英語

broken-window-check

Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.

原文の言語: 英語

eval-harness

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. Reuses loopkit's verifier subagent as the grader — do not build a new one.

原文の言語: 英語

pdf-ingestion

Get a PDF into the model without blowing the context window or losing structure. Native PDF beats OCR-then-text for most cases; extract-then-summarize beats native for very long docs.

原文の言語: 英語

prompt-caching

Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn. Use when the system prompt, tool defs, or reference docs are stable across many turns.

原文の言語: 英語

shift-notes

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. Structured prose, not JSON — the model writes prose better.

原文の言語: 英語

structured-output

Get JSON out of the model reliably. Prefer tool_use with a schema over prompted-JSON, validate on receive, retry on parse fail. Use when downstream code will parse the response.

原文の言語: 英語

verification-before-completion

Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off. Requires running the verification command in THIS turn and reading its output before any success claim.

原文の言語: 英語

authz-check

Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.

原文の言語: 英語

context-budget

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

原文の言語: 英語

contract-test

Test the boundary between two systems by the contract, not the implementation. Use for APIs, integrations, and shared interfaces.

原文の言語: 英語

input-validation

Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.

原文の言語: 英語

loading-empty-error-states

Design the three states every data UI forgets. Use for any component that fetches or lists data.

原文の言語: 英語

read-the-trace

Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.

原文の言語: 英語

reduce-nesting

Flatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.

原文の言語: 英語

revert-surgical

Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something.

原文の言語: 英語

spec-first

Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.

原文の言語: 英語

subagent-fanout

Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.

原文の言語: 英語

tool-restraint

Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load. Use when wiring tools or an agent underperforms.

原文の言語: 英語

a11y-pass

Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.

原文の言語: 英語

adversarial-verify

Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.

原文の言語: 英語

bisect-regression

Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.

原文の言語: 英語

changelog-from-diff

Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.

原文の言語: 英語

clean-commits

Turn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.

原文の言語: 英語

coverage-gaps

Find the untested code paths that actually matter, not just the coverage percentage. Use after adding tests.

原文の言語: 英語

decision-record

Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.

原文の言語: 英語

dependency-audit

Decide whether to add, keep, or remove a dependency. Use before adding any package.

原文の言語: 英語