archive228/loopkit
54 skills
$npx skills add archive228/loopkitSkillInstalls
a11y-passCatch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.active-memory-reminderBefore 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.adversarial-verifyReview a diff against the goal spec assuming the code is BROKEN. The reviewerauthz-checkVerify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.bisect-regressionFind the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.broken-window-checkBefore 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.changelog-from-diffTurn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.clean-commitsTurn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.context-budgetKeep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.contract-testTest the boundary between two systems by the contract, not the implementation. Use for APIs, integrations, and shared interfaces.coverage-gapsFind the untested code paths that actually matter, not just the coverage percentage. Use after adding tests.decision-recordCapture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.dependency-auditDecide whether to add, keep, or remove a dependency. Use before adding any package.design-systemMake frontend output look intentional, not AI-generated. Use for any UI work — components, pages, layouts.eval-harnessBuild 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 — evaluator-calibrationCalibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.feature-list-jsonEnumerate 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 nexflaky-hunterDiagnose and fix tests that pass sometimes and fail other times. Use when CI is red intermittently.harness-strippingSystematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.hitl-escalateEscalate 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 approvinit-script-contractAuthor idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.input-validationValidate and constrain untrusted input at the boundary. Use on any handler that accepts external data.kill-dead-codeFind and remove unreachable/unused code safely. Use during cleanup or before a refactor.loading-empty-error-statesDesign the three states every data UI forgets. Use for any component that fetches or lists data.migration-writerWrite safe, reversible database migrations for this repo's conventions. Use for any schema change.model-routingSplit the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.owasp-reviewSecurity-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.pdf-ingestionGet 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.planner-spec-expandExpand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.pr-from-diffWrite a PR description a reviewer can approve fast. Use when opening any pull request.progress-reading-protocolRun 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 letsprompt-cachingCache 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.read-the-traceExtract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.readme-auditCheck whether a README actually lets a stranger run the project. Use on any repo's README before publishing.rebase-safelyRebase, squash, or rewrite history without losing work or breaking shared branches. Use before any history rewrite.reduce-nestingFlatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.revert-surgicalUndo a bad change without nuking unrelated work. Use when a specific commit or change broke something.schema-diffCompare two schema states and surface the risky changes. Use before applying migrations or after a model change.secret-scanCatch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.self-eval-biasDetect 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.shift-notesWrite 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 simplifyReduce a change to the minimum that solves the problem. Use when code is over-engineered or a diff is bloated.spec-firstWrite the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.sprint-contractNegotiate 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 gesql-reviewReview SQL and ORM queries for correctness, safety, and performance before they ship.structured-outputGet 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.subagent-fanoutParallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.suggest-next-featuresRead git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so feature_list.json stays immutablesystematic-debuggingUse for ANY bug, test failure, crash, or unexpected behavior. ForcestemplateOne 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 ttool-restraintDon'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.using-loopkitUse 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.verification-before-completionUse 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 succwrite-failing-test-firstBefore fixing any bug, write a test that reproduces it and watch it fail. Use for every bug fix.