364 skills · sorted by relevance
Uses multiple agents with different critical roles to challenge assumptions, complexity, risks, and alternatives. Findings that withstand review go to a dedicated planner, who turns them into sequenced tasks with explicit success criteria.
Solve competition mathematics problems and examine proofs through independent agents that actively look for gaps, counterexamples, and misused theorems. Produces a checked argument or clearly states what remains unresolved, with optional PDF output.
Design tests that assess an AI agent's capabilities and reliability. Covers repeated runs to measure variation, checks for required behavior, and adversarial testing to expose failures that ordinary successful examples may miss.
Prepare for board meetings, investor updates, and fundraising presentations by reviewing key numbers, rehearsing difficult questions, and shaping an honest business narrative. Includes preparation for individual directors and follow-up actions after the meeting.
Reviews code changes through documented engineering and product principles associated with named practitioners. Combines two engineering perspectives and one product perspective to produce findings with severity, attribution confidence, and technical reasoning for architecture, performance, or user experience issues.
Stress-test ideas, strategies, and plans by breaking them into individual claims for parallel expert agents to challenge. Receive the strongest supporting case, surviving counterarguments, and findings ranked by severity with suggested ways to address weaknesses.
Stress-test a paper with a focused rejection argument, then have a separate reviewer assess each objection against the current text. The report identifies unresolved weaknesses, their severity, and priority fixes for submission or rebuttal preparation.
Review completed code through three roles: a critical reviewer, a verifier, and an adjudicator. Check evidence, look for bugs introduced by fixes, and produce an actionable repair list with regression tests and traceable review reports.
Reviews code for common security weaknesses, authentication problems, exposed credentials, and unsafe configuration. It adjusts review depth to the changes and offers an adversarial workflow, where defensive and attacking perspectives guide fixes and subsequent verification.
Choose how to handle repository initialization, code review, and security review requests. Start with Claude’s built-in commands for ordinary tasks, and route requests for multiple opinions, adversarial analysis, or specific providers to Octopus.
[omh] Hostile scenario testing: adversarial QA and fix loops. Use when the user says: ultraqa, adversarial qa, hostile scenarios, e2e qa, real-world qa, qa scenario, release qa, 敵対的QA.
The English summary is being prepared. Showing the original description.
Adversarial dual-model code review that runs two AI models in parallel, cross-references findings, and produces a consensus severity table with fix confidence ratings. Use when asked for a thorough code review, adversarial review, dual-model review, confidence-rated review, or 'Hanselman review'.
The English summary is being prepared. Showing the original description.
Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
The English summary is being prepared. Showing the original description.
Für Abtretung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: abtretung-adversarial-test.
The English summary is being prepared. Showing the original description.
Für Adversarial Test AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
The English summary is being prepared. Showing the original description.
Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML). DIRECT-EDIT mode (common): the user describes a change in Chinese or English and the manuscript (LaTeX or Markdown) is edited directly through a CS-venue writing toolkit with author sign-off (use for 改这段 / 把中文想法写成 latex / polish / de-AI / translate / compress a passage). REVIEW mode (occasional, pre-submission): harden the paper through an adversarial courtroom review engine (N holistic domain reviewers / contestability routing / two-sided trial / three-way verdict / clerk-converged multi-round loop) with consensus-gated, author-signed revisions (use for review / critique / 审稿 / 评审 / mock-review). AUTO mode (unattended, opt-in via /goal): run the review-revise loop toward a verifiable goal, applying safe fixes under a drift-bounded policy and queueing risky ones. Resolves all inputs at runtime, no hardcoded paths. Not a from-scratch drafter (use ml-paper-writing) and not an official-venue rebuttal.
The English summary is being prepared. Showing the original description.
Adversarial "perfection" review — hold a change to an *ideal* bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. Use when the user asks to review "for perfection", to make a defect "impossible to express", or to hunt where a defect "relocates" across review rounds. Grounds every claim in the diff, fans out adversarial verifiers via Workflow, and reports residual surfaces with a structural fix for each. ONLY invoke when the user explicitly asks for a perfection / ideal-bar review.
The English summary is being prepared. Showing the original description.
Act as experienced opposing counsel to attack, undermine, and expose weaknesses in a legal argument, submission, witness statement, or structured reasoning. Produces a six-part adversarial analysis: 1. A core theory of attack identifying the single most effective way to defeat the argument; 2. A reconstructed version of the opposing argument stripped of rhetoric to expose its fragility; 3. Primary lines of attack grouped by category (legal misstatement, evidential gaps, causation failures, internal inconsistency, over-reliance on assertion, procedural weakness); 4. An "if I were the judge" section showing how a sceptical tribunal would dismantle the argument; 5. Surgical strikes - 3 to 5 high-impact points ready for oral submissions; and 6. An analysis of what the argument is trying to hide. Written in formal, adversarial British English for a legally trained audience.
The English summary is being prepared. Showing the original description.
Prepare a lawyer for an adversarial proceeding the way Neal Katyal's "Harvey" prepared him for the SCOTUS tariffs argument: profile the tribunal from their prior opinions and questions, predict the specific questions you will face, map narrow "escape routes" each judge can walk through without abandoning prior commitments, and spar adversarially until only the strongest answers survive. The model is the sparring partner. The human still wins the case. Use when: preparing for oral argument, appellate argument, motion hearing, evidentiary hearing, deposition (taking or defending), arbitration, mediation, or any proceeding where a known decision-maker will fire questions at you in real time. Also useful for stress-testing a brief before filing. Proactively suggest when: the user mentions an upcoming hearing/argument with named judges or arbitrators, drafts a brief and wants it pressure-tested, asks "what will Justice X / Judge Y ask me," or talks about preparing for a specific bench.
The English summary is being prepared. Showing the original description.
Adversarial premortem for England & Wales civil litigation - builds the strongest version of a case, then attacks it from four angles to find where it loses before opposing counsel does. Runs an adversarial premortem on a UK litigation matter. Builds the strongest version of the case, then attacks it from four angles — procedural, substantive, evidentiary, strategic — to find where it actually loses. Returns a ranked stress-test brief: failure scenarios, evidence inconsistencies, blind spots, mitigations, and one brutal one-sentence verdict. Use before issue, before settlement negotiations, before a litigation-funder pitch, or before deciding whether to take a case.
The English summary is being prepared. Showing the original description.
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified", "is this actually done", "maker checker", "second pair of eyes on this change". Not for prose, docs or typo edits.
The English summary is being prepared. Showing the original description.
Adversarially review something just built — presume it is broken and find where. Use after implementing a feature, finishing a build, or before shipping, or whenever ATLAS or Boss wants a hostile second opinion on a diff, a running app, or a whole codebase. Spawns clean-context reviewers with opposing lenses (correctness, security, empty-world) and reproduces every finding by running the target before believing it. Distinct from /code-review, which statically reads a diff and never runs the app.
The English summary is being prepared. Showing the original description.
OI-3 spike harness — ADVERSARIAL inline guidance variant. Worst-case anchor: ends with a final-sounding completion statement and gives NO instruction to return to the caller. Use only when a spike consumer skill invokes it.
The English summary is being prepared. Showing the original description.
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.
The English summary is being prepared. Showing the original description.