meridianlabs-ai
- 17 skills
- 0 followers
- 1 day ago last updated
- ▌ Nightly Pr Triage · meridianlabs-aiTriage the nightly auto-update PR for the Harbor registry — fill in categories, title, repo, arxiv on newly-stubbed `docs/overrides.yml` entries so CI passes and the docs/AISI evals browser surface the dataset with proper branding.
- ▌ Land TS Mono · meridianlabs-aiLand a PR that requires a coordinated ts-mono submodule change. Use when the check-schema-and-types CI job fails, when a Python model change requires regenerating the OpenAPI spec / TypeScript types, or when any change touches the ts-mono submodule and needs to be landed.
- ▌ Welcome Banner · meridianlabs-ai bundleAssemble the welcome banner by reading the asset and running the script
- ▌ Email Corpus · meridianlabs-ai bundleRealistic corporate email archive for email-management audit scenarios
- ▌ Customer Service App · meridianlabs-ai bundleRealistic customer service application with system prompt, tool schemas, and sample tickets for grounding audit scenarios
- ▌ Dependabot Fix · meridianlabs-aiRecurring maintenance task — clear the current batch of GitHub dependabot security alerts by adding or updating pnpm override entries in pnpm-workspace.yaml. Use whenever the user mentions dependabot alerts, security advisories, CVEs/GHSAs, vulnerable dependencies, pnpm audit findings, or asks to "fix security issues" — even if they don't mention overrides.
- ▌ Verify Log Viewer · meridianlabs-ai bundleTriage, reproduce, and verify the real inspect log viewer (apps/inspect web UI) against real .eval fixtures. Use the feature map to turn a bug report, screenshot, or viewer change into the relevant routes, code owners, user journeys, and runtime evidence across listings, log workspaces, sample detail, transcripts, live data, and host modes.
- ▌ Reading Logs · meridianlabs-aiUse whenever the user needs to read, inspect, or process Inspect AI eval log files (`.eval` or `.json`). Covers the Python API (`read_eval_log`, `read_eval_log_samples`, `read_eval_log_sample_summaries`, `list_eval_logs`), `header_only` mode, the critical anti-pattern of unzipping `.eval` files, and memory-safe patterns for large logs.
- ▌ Analyzing Logs · meridianlabs-ai bundleUse whenever the user wants to analyze or understand what happened in an Inspect AI eval, sample, or set of logs. Routes to the right tool (`inspect_ai.log` for single-log work, `inspect_ai.analysis` for cross-log dataframes, Inspect Scout for transcript pattern detection) and covers the `inspect_ai.analysis` surface for ad-hoc analysis. Triggers on questions like "what happened in this eval/sample", "how did model X compare to Y", "show me outliers across these runs", "did any sample do X", or any follow-up where the user is analyzing logs (not just reading them).
- ▌ Babysitting Evals · meridianlabs-aiUse for monitoring, diagnosing, and intervening in RUNNING Inspect AI evaluations via the `inspect ctl` command-line control channel. Triggers when: watching a live eval for stalls/errors/retry failures, checking progress of an active eval process, launching an eval you'll monitor in parallel, finding problematic samples in a running eval, cancelling a stuck sample or task, pausing a running eval and resuming it in place (without killing the process), re-running an errored sample, or retuning a running eval's concurrency or timeouts.
- ▌ Map Inspect Packages · meridianlabs-aiUse whenever the user is working with Inspect AI or any of its ecosystem packages (Evals, Flow, Scout, Viz, SWE, Harbor, Sandboxes). Maps concerns to packages and points at each package's docs before calling its API.
- ▌ Import · meridianlabs-ai bundleImport an upstream inspect_ai issue into the fork — /import <upstream-issue-number-or-url> mirrors the UKGovernmentBEIS issue as a fork issue (snapshot body + machine-readable upstream link) and adds it to Atlas as Todo, so @auto can work it. Does NOT kick @auto — the user comments @auto with their own guidance.
- ▌ Promote · meridianlabs-ai bundlePromote a reviewed inspect_ai fork branch upstream — open the UKGovernmentBEIS PR with the fully-qualified Fixes ref, then do the tracking bookkeeping (Atlas Sign-off stage, Upstream PR field, issue comment, supersede the fork PR). Idempotent — also use it to heal the bookkeeping of an already-promoted issue.
- ▌ Checkout · meridianlabs-ai bundleCheck out the PR branch for an issue — /checkout <issue-number> finds the issue's PR (linked-PR chip fast path, then agent comments, then the claude/issue-N-* branch convention) and checks its branch out in the current repo clone.
- ▌ Resolve Board · meridianlabs-aiBring the Atlas board current in one shot — dispatch the hourly Atlas sync workflow (hosted in this agents repo) now (upstream state sync) and run the local link-upstream-chips sweep (clickable issue↔PR chips). Use when the board looks stale or after a batch of agent/upstream activity.
- ▌ Merge Approved Prs · meridianlabs-aiMerge approved upstream inspect_ai PRs from the Atlas board's Merge stage, one at a time — resolve conflicts against main, guard CHANGELOG/submodule invariants, coordinate companion ts-mono PRs and submodule pointer bumps when the viewer schema changed, watch CI, merge, and clean up the board. Handles both promotions (our branches) and approved External contributor PRs (their fork branches; maintainerCanModify is the prereq — skip and report those without it). Items whose issue carries hold:release are skipped unless holds are explicitly included (the post-release sweep). Use when Ransom says he's ready to merge approved PRs / clear the Merge queue.
- ▌ Post Upstream Review · meridianlabs-aiRelay an external review upstream — /post-upstream-review <proxy-issue-number> [instructions] takes the review findings from an External proxy issue, posts them as a single review on the contributor's upstream PR (inline comments on the right lines where possible), then moves the proxy to Contributor.