Keep Last Light's docs in sync with the code. Use before committing changes to apps/server/workflows/, skills/, config/default.yaml, src/connectors, src/state, src/engine/router.ts, src/config/, packages/cli/src, packages/shared/src (providers/overlay helpers), or agent-context/ — or whenever the docs-check pre-commit…
The shared rules for the ADJUDICATE pass of a multi-pass PR review — the workspace layout, the severity vocabulary it ranks on, and the prior-review ledger plus the two APPROVE constraints it inherits as the only pass that owns the posted verdict. Use when turning a pile of hypotheses into one ranked, tiered review.…
Drive a real headless browser against a locally-served web UI and capture screenshot evidence, reporting step-level PASS/FAIL/BLOCKED with extracted DOM text and console errors. Use when a phase on the docker QA image must exercise a rendered UI and attach screenshots — it complements the text-evidence verify/qa-test…
Install dependencies and run the test/lint/typecheck gate for a change inside the sandbox — package-manager detection, install-first, and (when implementing) TDD discipline. Use when implementing, fixing, or verifying code in a pre-cloned repo.
Conversational assistant for messaging-platform threads (Slack, Discord). Answer questions about repos, PRs, and issues, explain code, and guide users to the natural-language workflow triggers listed in the system prompt.
The shared rubric for reviewing a code change — precision-first, high-signal findings only (Critical/Important), what to check (correctness, contracts between producer and consumer, security, edge cases, regression risk, test coverage), and what is NOT a finding (pre-existing issues, linter territory, aspirational…
Debug a running Last Light instance (usually production) via the lastlight CLI instead of SSH. Use when investigating a failed/stuck workflow, a bad agent run, a phase error, or "why didn't the bot do X" — anything that previously meant SSHing in to read SQLite or session logs.
Record a short demo VIDEO of a PR or feature — drive the repo's web UI in a real headless browser, capture the session, and composite a titled, size-capped mp4 with ffmpeg. Use on the docker QA image when the deliverable is a playable demo clip (single walkthrough or before/after comparison), not a text/screenshot…
Judge a MAJOR dependency bump by its blast radius — low / medium / high — from evidence you can gather without a checkout (release notes, dev-vs-runtime, import-site count, security sensitivity, the settled CI result). Use when a dependency PR is a major version bump and you must decide whether it can land…
Diagnose why a PR's CI failed — compare the CI definition against the sandbox, classify the failure, and make the minimal repair. Use when a PR is red and you must work out why before changing anything.
Answer a question directly — a sourced, neutral reply to an information/explanation/comparison request, from a GitHub issue or a Slack thread. Research repo docs and the web, output the answer, label question (GitHub only), leave open. Never write an agent brief, mark ready-for-agent, or change code.
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
Triage GitHub issues through the canonical state machine — classify, label, deduplicate, request missing info, write agent briefs, and manage stale issues. Use on demand or on a triage cron.
Answer a maintainer's question about an open PR with concrete, code-cited evidence. The PR-side counterpart to issue-comment — for questions tied to the diff, not a full review.
Review a GitHub pull request and post one formal review — advance the existing discussion and give precision-first, high-signal feedback. Judgement on the diff, not a build gate — CI validates that it builds, and a targeted probe is allowed as evidence. Use when asked to review a PR or on a cron PR scan.
Run an automated QA flow against a CLI or a locally-served app and report step-level pass/fail with evidence. Use when asked to QA-test a feature, exercise a flow end-to-end, or smoke-test what a PR changed.
Generate a health report for a GitHub repository — open-issue and PR backlog, unreviewed PRs, stale needs-info, failing CI, and the resulting action items. Use for a status report or on a weekly cron.
Process a maintainer's comment on a security scan-summary issue — break selected findings out into individual actionable issues, or record accepted risks / false positives in SECURITY.md.
Diff-scoped security review of SDLC concerns GitHub's scanners miss — workflow/CI hardening, auth changes, secret handling, supply-chain churn. Files one dated summary issue with a task-list of findings. Use on a security cron or when asked to scan a repo.
The shared rules for ONE pass of a multi-pass PR review — the workspace layout, the finding tiers, what is not a finding, and the one rule that separates a survey pass from a reviewer (the precision gate does not fire on you; over-produce). Use when discharging obligations for one family and appending hypotheses for a…
Test a behaviour claim as an investigator and report whether the evidence confirms or refutes it — CONFIRMED / REFUTED / INCONCLUSIVE with bash-captured evidence. Use when asked to verify a claim, prove a fix works, or check that a PR does what it says.
Install the lastlight CLI and connect it as a CLIENT to an existing Last Light server — log in, save the token, and verify the connection. Use when the user wants to "connect / point my lastlight CLI at a server", "log in to Last Light", "set up the lastlight client", or run lastlight commands against a remote…
Debug a running Last Light instance over its admin API with the lastlight CLI — no SSH. Use when the user wants to "look at / debug a failed or stuck workflow", "why didn't the bot do X", "check a bad agent run / phase error on ", "tail a session", "search the logs", "read the server/docker logs", "list/trigger a…
Drive a Last Light EVAL toward a target score with a disciplined, anti-gaming improvement loop — run → mine failures → propose candidate fix(es) → re-measure → keep the best or revert → repeat. Use when the user wants to "improve / raise the pr-review F1", "make the reviewer better against the eval", "close the loop…