Agent skills

Use when revising an ACM PODS paper for a precise model and result on the first page, exact theorem statements with matching bounds…

Analyzes events through poetic lens using close reading, metaphor analysis, imagery, rhythm, form analysis, and attention to language's…

Augment a BC Transformer agent with 2-ply bounded search using the cg library's SearchBegin/SearchStep API.

Submit a BC (behavioral cloning) Transformer agent for the Pokémon TCG AI Battle competition.

Select the right Proof of Life (PoL) probe based on hypothesis, risk, and resources.

Define a Proof of Life probe to test a risky hypothesis cheaply.

Set up Affonso affiliate program tracking with Polar integration.

Add Polar billing to a TypeScript/JavaScript app using the @polar-sh/sdk package — Checkout, Customer Portal, and Webhooks endpoints in…

Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff.

Draft a firm AI usage policy from published model policies, adapted to your practice profile — a research-and-synthesis tool whose output…

Audit the allow/deny/ask rules across the user, project and local settings scopes, then dedupe them and promote read-only rules up the…

Controlled polling for async operations at specified intervals

Streamlines environment setup and development workflows across multiple programming languages using a unified task runner.

Specialized skill for polymer materials analysis including molecular weight distribution, thermal transitions, crystallinity, and…

Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.

Use a cost-controlled coding workflow in which the primary task gives a detailed execution plan, then exactly one fresh, user-selected…

Use when packaging a POPL artifact — above all a mechanized proof development in Rocq/Coq, Lean, Agda, or Isabelle — for the…

Use when designing the empirical component of a POPL paper — deciding whether evidence should be a mechanization, a prototype, case…

Use when making a POPL paper's results independently checkable — deciding which theorems to mechanize versus hand-prove, maintaining a…

Use when interpreting where a POPL submission stands — the full double-blind pipeline from the July HotCRP deadline through reviews, the…

Use when preparing a POPL submission for the single July HotCRP deadline — auditing the 25-pages-of-text acmsmall cap, summary-rejection…