garrytan

2★

@garrytan

Executes the full automated test suite, collects pass/fail counts and coverage deltas, and surfaces any newly introduced failures with concise root-cause notes.

3★

@garrytan

Builds a complete design system by researching the product and competitors, then proposing a coherent package of typography, colours, spacing, layout, and motion — persisted as a DESIGN.md file that serves as the project's authoritative design source of truth.

3★

@garrytan

Drives a browser to a target URL, navigates multi-step user journeys, and captures screenshots or structured observations for downstream verification or reporting.

2★

@garrytan

Launches a new headless or headed browser session with the Gstack environment variables and extension profile pre-loaded, ready for automation commands.

2★

@garrytan

Injects pre-authenticated session cookies into the browser context so subsequent automation steps can access gated pages without a manual login flow.

3★

@garrytan

Automates the final production shipping stages — merging a PR, monitoring CI/deploy completion, and verifying live site health through canary checks — picking up where /ship leaves off with safety gates at each step to prevent broken deployments reaching users.

2★

@garrytan

Provisions the deployment environment by creating secrets, configuring environment variables, and running infrastructure-as-code init steps before the first deploy.

3★

@garrytan

Comprehensive, interactive architecture and implementation review before coding begins, systematically evaluating scope, architecture, code quality, test coverage, and performance through structured questioning — synthesising findings into actionable tasks and an explicit not-in-scope section.

3★

@garrytan

Pre-landing code review combining structured checklist analysis with specialist subagents covering testing, security, and performance — plus adversarial review from both Claude and Codex — to catch SQL safety issues, LLM trust boundary violations, conditional side effects, and structural problems before merging.

3★

@garrytan

Activates a conservative execution profile that pauses before irreversible actions, requests explicit confirmation for destructive operations, and logs all side effects.

2★

@garrytan

Sets a change-freeze flag that blocks non-critical commits and PR merges until explicitly lifted, protecting release branches or post-incident windows.

2★

@garrytan

Applies configurable content and output guardrails to agent responses, flagging or blocking unsafe outputs and logging violations with structured evidence for audit.

2★

@garrytan

Clears the active change-freeze flag and restores normal merge permissions, logging the unfreeze event with a timestamp and justification.

3★

@garrytan

Synthesises commit history, PR comments, and issue notes into a written sprint retrospective covering wins, misses, root causes, and action items.

2★

@garrytan

The definitive autonomous "Founder mode" review and decision suite. An auto-review pipeline that reads the full CEO, design, engineering, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles.

3★

@garrytan

Infrastructure-first security audit focusing on secrets archaeology, dependency supply chain, and CI/CD security. Includes OWASP Top 10, STRIDE threat modeling, and active verification with daily (zero-noise) and monthly (comprehensive) scan modes.

3★

@garrytan

Automated end-to-end deployment workflow that merges the base branch, runs tests, reviews the diff, bumps the VERSION file, updates the CHANGELOG, commits, pushes to the remote, and creates a pull request in a single command.

1★

Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through perplexity-research for the actual web lookup, then formats results as a citation-checked brain page. Use when a book/article/conversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized.

1★

Systematic claim-by-claim verification for any content before it ships. Modeled on professional fact-checking desks (The New Yorker, ProPublica, IFCN standards): extract every verifiable claim, check each against live citable sources (never training data), assign a 6-level confidence status, apply corrections, and produce a scored pass/fail report. Includes a data-derived-claims gate for outputs produced FROM the brain or a database: PRODUCER ≠ VERIFIER (re-derive each claim via a different query path) and AFFILIATION ≠ AUTHORSHIP (person→thing claims resolve through typed edges), with delivery hard-blocked on unsupported claims.

3★

@garrytan

Generates structured documentation using the Diataxis framework — tutorials, how-to guides, reference materials, and explanations — by thoroughly researching the codebase before writing, tailored to the needs of different reader types.

2★

@garrytan

Reads the diff between two version tags and drafts concise, user-facing release notes following the Gstack changelog format.

2★

@garrytan

Converts markdown or structured data into a polished PDF document with consistent heading styles, table formatting, and page layout ready for distribution.

2★

@garrytan

Fetches target URLs with a headless browser, parses structured data from rendered HTML, and returns clean JSON or markdown ready for downstream analysis or ingestion.

1★

Universal archivist for personal file archives (Dropbox/B2/Gmail-takeout/local-mount/hard-drive-dump). Filters for high-value content (the user's own writing, ideas, relationships) and surfaces it interactively. REFUSES TO RUN without an explicit gbrain.yml `archive-crawler.scan_paths:` allow-list.

1★

Feed and whole-publication ingestion: turn an entire blog, newsletter, or RSS/Atom archive into brain source pages. Covers feed discovery, pagination walking, normalization to a common article shape, canonical-URL dedup, idempotent re-runs, 429 pacing, and empty-husk repair. This is the PUBLICATION-scope skill — a single article URL routes to idea-ingest instead. Per-article enrichment hands off to the brain-ingest-gate skill; public posts only (gated content is skipped, never worked around).

1★

End-to-end discipline for turning any large data source (audio libraries, email takeouts, document corpora, chat exports, API dumps) into brain pages at scale. The lifecycle spine: SCHEMA → ACCESS → TRIAL → EVALUATE → IMPROVE → CODIFY → TEST → SKILLIFY → BULK → MONITOR. State is tracked in a durable JSON manifest (see MANIFEST-PATTERN.md) so any crash, session boundary, or subagent fan-out resumes from ground truth instead of memory.

1★

Tiered LLM extraction pattern for large corpus processing (email archives, document dumps, transcript libraries). A utility-tier model triages and classifies at speed; the reasoning tier does the default deep read; the deep tier is the escalation for the highest-value content. Prevents spending deep-tier money on noise while ensuring the important content gets the best eyes. A deterministic privacy wall runs before any LLM call.

2★

@garrytan

Runs a standardised prompt suite across multiple model versions, records latency and quality scores, and produces a ranked comparison table to guide model selection.

1★

Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session transcripts — a user correction after an invocation is the gold signal — then synthesize an eval_contract plus 4-8 replayable cases with honesty labels (SPEC-DERIVED vs HISTORY-IMPLIED) and stage the result at skills/<name>/eval/autobench-<date>.md as PENDING-HUMAN-APPROVAL. Never rewrites SKILL.md. Ships two guard companions: panel integrity (multi-model judging must prove each provider actually responded) and the fail-improve taxonomy (logged LLM-fallback cases convert to deterministic code over time).

3★

@garrytan

Web performance benchmarking that captures baseline metrics, compares current performance against those baselines, and identifies regressions in load times, Core Web Vitals, and bundle sizes across specified pages.

3★

@garrytan

Rigorous product strategy and scope review in four modes — SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, and SCOPE REDUCTION — evaluating architecture, security, data flows, testing, and edge cases to ensure plans ship at the highest standard before implementation begins.

1★

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's life, NOT a therapist assigning homework. The reader decides what to do about it. Layout is a top-aligned HTML table or stacked sections, never a bare markdown pipe table (pipe tables center-misalign uneven columns). Output is a single brain page at media/books/<slug>-personalized.md plus an optional PDF via brain-pdf.

1★

Read a book, article, transcript, or case study through the lens of a specific strategic problem you're facing. Produces an applied playbook that maps the source onto the problem and gives short/medium/long-term recommendations. NOT for general book summaries.

3★

@garrytan

Performs the brain-first read, enrich, write, attribution, and backlink cycle for a persistent knowledge base.

2★

@garrytan

Bootstraps the GBrain knowledge store for a new project: creates the index structure, ingests seed documents, and validates retrieval with a sample query.

2★

@garrytan

Incrementally syncs new documents and updated pages into the GBrain index, deduplicates embeddings, and reports ingestion counts and any errors.

3★

@garrytan

Post-deployment monitoring that captures pre-release baseline screenshots, then continuously watches pages for console errors, performance regressions, and broken links — designed to surface failures within the first 10 minutes so problems are caught before they reach users at scale.

3★

@garrytan

Captures thoughts and content into a persistent personal knowledge brain through one idempotent ingestion entrypoint.

1★

Import AI-assistant chat exports (ChatGPT, Claude, Perplexity) and agent session transcripts into the brain as one dated page per conversation under conversations/, validate each page against the native conversation parser, extract facts via the native conversation-facts flow, and keep the archive gap-free with a detect-and-backfill loop. Then answer archive questions: "when did I first discuss X", trace how an idea evolved across past conversations, pull a specific thread.

1★

Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge. One unified pipeline: normalize the source into a standard transcript record, split multi-meeting recordings, resolve speakers by evidence, create the page, pass every surprising claim through the consistency check (transcript + brain + plausibility), enrich every entity, then run the verification checklist — substance AND sequence. A meeting is NOT fully ingested until the enrich skill has processed every entity AND the verification checklist passes, including the sequence verify (PASS or explicit user waive).

1★

Opt-in ambient signal capture. After explicit enablement, applies on substantive inbound messages to detect original thinking and entity mentions. Use an authorized sub-agent where supported; otherwise detect inline. Aim to never block the main response.

1★

Build a TYPED citation/reference graph over an ingested corpus — not just embeddings. Flat similarity retrieval cannot tell you that document A *overrules* B, *distinguishes* C, or *relies_on* D. This skill extracts every inter-document reference, classifies the edge TYPE with LLM judgment, and writes first-class typed edges via `gbrain link`, so `gbrain graph-query --type` can walk the argument ("everything this brief relies on, minus anything overruled since"). Every cite-heavy corpus is the same shape: law, academic papers, patents, regulatory filings, a book's bibliography.

2★

@garrytan

Spins up a structured Claude-versus-Codex debate over a proposed implementation, with each agent mounting adversarial critiques, to surface hidden design flaws before code lands.

3★

@garrytan

Synthesizes and curates raw knowledge concepts into a grounded, tiered intellectual map.

1★

Trace one idea's evolution through the brain: first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version. Use for single-idea conceptual lineage, not broad concept-map synthesis or structured entity metrics.

1★

Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the bootstrap-rendered identity files (SOUL.md, USER.md, ACCESS_POLICY.md, HEARTBEAT.md) or their harness equivalents. Finds redundancy, contradictions, stale content, compression candidates, and skill-extraction candidates; produces a ranked action list sorted by token savings with a risk class per finding. REPORT-ONLY: this skill never edits any audited file. Recommendations for bootstrap-rendered files target the interview answer bank / templates, never the rendered output. Judging routes through `gbrain eval cross-modal` (single cheap model by default; full multi-model panel is explicit opt-in).

2★

@garrytan

Reads a saved context snapshot and reconstructs a warm session state, surfacing the last decision point and pending tasks so work can resume without recap.

2★

@garrytan

Compresses the current session context into a compact summary file that can be restored later, enabling long-running workflows to survive context-window limits.

1★

Structured data research: search sources, extract structured data, archive raw sources, maintain canonical tracker pages, deduplicate. Parameterized via YAML recipes for investor updates, donations, company updates, or any email-to-structured-data pipeline.

1★

Deep-research a topic end to end and produce a permanent, reusable knowledge asset: archive every primary source verbatim (gated by the user's privacy/retention posture), write one 1:1 summary per source, then synthesize a single self-contained compendium page. Depth is a dial (base synthesis → grounded primaries → books + counter-canon → saturation), each level an idempotent superset of the one below. Distinct from data-research (structured trackers) and perplexity-research (web deltas): this produces prose knowledge synthesis backed by an archived source corpus.

3★

@garrytan

Generates production-quality, Pretext-native HTML/CSS with real text reflow and dynamic layout from approved design mockups, CEO plans, or user descriptions — producing fully self-contained files with computed heights, responsive behaviour, and zero external dependencies.

2★

@garrytan

Runs a structured UX audit over a product interface, scoring layout clarity, affordance, and accessibility against the Gstack design rubric to surface actionable improvements.

3★

@garrytan

Rapid design exploration that generates multiple AI design variants, opens a comparison board for the user, collects structured feedback, and iterates until a preferred visual direction is reached.

3★

@garrytan

Interactive, designer-led audit of UI/UX plans rating seven dimensions — information architecture, interaction states, user journey, AI slop risk, design system alignment, responsive/accessibility, and unresolved decisions — before implementation begins, with optional visual mockup generation.

3★

@garrytan

Interactive multi-pass DX review for developer-facing products — APIs, CLIs, SDKs, and libraries — scoring eight UX dimensions from onboarding to error messaging via persona discovery and competitive benchmarking, producing an actionable improvement plan rather than just a score.

2★

@garrytan

Audits CLI ergonomics, API surface clarity, and onboarding friction from a developer perspective, producing a scored report with prioritised fixes.

1★

Ghostwrite content in a specific person's voice from a VALIDATED voice profile — tweets, replies, short posts, launch copy, recruiting blurbs, emails. Loads the subject's voice profile (people/<slug>-voice) plus first-party context from the brain, drafts 2-3 options in-register, then runs a hard voice-fidelity self-check before showing anything. Includes the profile BUILDER: if no validated profile exists, drafting hard-stops and this skill walks the corpus-to-fingerprint build instead. Never auto-posts.

1★

Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.

4★

@garrytan

The installable GBrain router and capstone for knowledge capture, operations, and concept synthesis.

2★

@garrytan

Scans the workspace for outdated dependencies, runs upgrades within semver-compatible bounds, re-runs tests, and commits a clean dependency bump PR.

5★

@garrytan

The legendary fusion of Garry Tan's complete agent discipline library — browser QA, security auditing, design exploration, vertical-slice planning, and founder-mode orchestration — unified into a single autonomous product-development workflow.

3★

@garrytan

Systematic root-cause debugging enforcing an Iron Law — no fix without first identifying root cause — guiding through four phases: investigation, analysis, hypothesis formation, and verified implementation with evidence gathering and pattern matching before any code changes.

1★

Before fixing a slow/stale/timeout alert, measure the step yourself. Kill the theory with a stopwatch, not a code change. Measure-first ops triage for temporal alerts (stale, timeout, freshness, wedged, N hours behind) from gbrain doctor, autopilot, sync, and cron monitors — runs BEFORE any timeout raise, threshold change, or pipeline rewrite.

2★

@garrytan

Generates a one-page project landing report from open issues, recent commits, and milestone progress, giving stakeholders a quick read on health and next steps.

2★

@garrytan

Reads the active memory store, consolidates new observations from the current session, deduplicates stale entries, and writes back an updated, ranked knowledge base for future sessions.

1★

Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. Replaces the older `gbrain-jobs` routing intent. Use when: submitting gbrain jobs, shell/background tasks, spawning subagents, checking progress, steering running work, pausing/resuming, parallel fan-out. One durable, observable, steerable queue interface. Also carries the durable-execution doctrine for any operation expected to exceed ~2 minutes: capability ladder, deadman checks that verify the result was reported, and content-addressed stage checkpoints for expensive pipelines.

3★

@garrytan

YC-style startup and builder brainstorming. Startup mode uses six forcing questions (demand reality, status quo, desperate specificity, narrowest wedge, observation, future-fit) to expose reality. Builder mode focuses on design thinking for side projects and hackathons.

2★

@garrytan

Wires a new MCP server into the Gstack agent environment, validates the tool manifest, and demonstrates round-trip invocation through a test prompt.

2★

@garrytan

Takes a draft plan or system prompt, identifies vague or ambiguous instructions, and rewrites them to reduce hallucination and improve task completion rate.

1★

Self-evolving skill optimization via SkillOpt-paper-grounded text-space optimizer.

3★

@garrytan

Browser-driven web application testing that explores pages as a real user, documents bugs with annotated screenshots, fixes issues with atomic commits and re-verification, and produces structured reports with before/after evidence and health scores showing quality improvement.

2★

@garrytan

Runs the scoped end-to-end test suite for a single feature or route without launching the full QA pipeline, for fast targeted regression checks.

1★

Publish the user's own gbrain over MCP so other devices, desktop apps and cloud agents can reach it. `gbrain mcp expose` installs and signs in Tailscale, publishes the running `gbrain serve --http` on the tailnet (HTTPS, tailnet-only by default; Funnel only when a client lives in a vendor cloud), keeps the server alive as a user service, and hands back the MCP URL. Then grant one least-privilege client per consumer, install the handoff inside that client, and verify a real memory round trip.

3★

@garrytan

Converts a freeform prompt, repo pattern, or workflow description into a complete, registry-ready named skill: writes the SKILL.md definition, populates frontmatter fields, and opens a PR for review.