loopkit

In the author's own words, from each skill's SKILL.md — showing the first 29 of 54 files.

• a11y-pass

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

  skills/a11y-pass/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/active-memory-reminder/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/adversarial-verify/SKILL.md on GitHub (opens in a new tab)

• authz-check

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

  skills/authz-check/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/bisect-regression/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/broken-window-check/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/changelog-from-diff/SKILL.md on GitHub (opens in a new tab)

• clean-commits

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

  skills/clean-commits/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/context-budget/SKILL.md on GitHub (opens in a new tab)

• contract-test

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

  skills/contract-test/SKILL.md on GitHub (opens in a new tab)

• coverage-gaps

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

  skills/coverage-gaps/SKILL.md on GitHub (opens in a new tab)

• decision-record

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

  skills/decision-record/SKILL.md on GitHub (opens in a new tab)

• dependency-audit

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

  skills/dependency-audit/SKILL.md on GitHub (opens in a new tab)

• design-system

  Make frontend output look intentional, not AI-generated. Use for any UI work — components, pages, layouts.

  skills/design-system/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/eval-harness/SKILL.md on GitHub (opens in a new tab)

• evaluator-calibration

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

  skills/evaluator-calibration/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/feature-list-json/SKILL.md on GitHub (opens in a new tab)

• flaky-hunter

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

  skills/flaky-hunter/SKILL.md on GitHub (opens in a new tab)

• harness-stripping

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

  skills/harness-stripping/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/hitl-escalate/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/init-script-contract/SKILL.md on GitHub (opens in a new tab)

• input-validation

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

  skills/input-validation/SKILL.md on GitHub (opens in a new tab)

• kill-dead-code

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

  skills/kill-dead-code/SKILL.md on GitHub (opens in a new tab)

• loading-empty-error-states

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

  skills/loading-empty-error-states/SKILL.md on GitHub (opens in a new tab)

• migration-writer

  Write safe, reversible database migrations for this repo's conventions. Use for any schema change.

  skills/migration-writer/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/model-routing/SKILL.md on GitHub (opens in a new tab)

• owasp-review

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

  skills/owasp-review/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/pdf-ingestion/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/planner-spec-expand/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill