Archive228

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

中文简介正在准备中。当前显示原文说明。

Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

Reduce a change to the minimum that solves the problem. Use when code is over-engineered or a diff is bloated.

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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 a minute.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

Diagnose and fix tests that pass sometimes and fail other times. Use when CI is red intermittently.

中文简介正在准备中。当前显示原文说明。

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

中文简介正在准备中。当前显示原文说明。

Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.

中文简介正在准备中。当前显示原文说明。

Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.

中文简介正在准备中。当前显示原文说明。

Compare two schema states and surface the risky changes. Use before applying migrations or after a model change.

中文简介正在准备中。当前显示原文说明。

Catch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.

中文简介正在准备中。当前显示原文说明。