Web Application Testing
anthropics/skills
Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner.
Install Adversarial Deliberation
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yogsoth-ai/de-anthropocentric-research-engine adversarial-deliberation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/adversarial-deliberation .claude/skills/adversarial-deliberation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "adversarial-deliberation" agent skill from https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/adversarial-deliberation into .claude/skills/adversarial-deliberation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-deliberation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/adversarial-deliberationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yogsoth-ai/de-anthropocentric-research-engine adversarial-deliberation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/adversarial-deliberation .agents/skills/adversarial-deliberation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "adversarial-deliberation" agent skill from https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/adversarial-deliberation into .agents/skills/adversarial-deliberation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-deliberation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yogsoth-ai/de-anthropocentric-research-engine adversarial-deliberation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/adversarial-deliberation .cursor/skills/adversarial-deliberation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "adversarial-deliberation" agent skill from https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/adversarial-deliberation into .cursor/skills/adversarial-deliberation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-deliberation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git --path skills/adversarial-deliberation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yogsoth-ai/de-anthropocentric-research-engine adversarial-deliberation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/adversarial-deliberation .gemini/skills/adversarial-deliberation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "adversarial-deliberation" agent skill from https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/adversarial-deliberation into .gemini/skills/adversarial-deliberation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-deliberation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yogsoth-ai/de-anthropocentric-research-engine adversarial-deliberationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/adversarial-deliberation .github/skills/adversarial-deliberation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "adversarial-deliberation" agent skill from https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/adversarial-deliberation into .github/skills/adversarial-deliberation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-deliberation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yogsoth-ai/de-anthropocentric-research-engine adversarial-deliberation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/adversarial-deliberation .opencode/skills/adversarial-deliberation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "adversarial-deliberation" agent skill from https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/adversarial-deliberation into .opencode/skills/adversarial-deliberation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-deliberation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
adversarial-deliberation- GitHub stars
- 505
- Token cost
- ~1.3k tokens
- SKILL.md length
- 382 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner.
- Works in 4 steps: You MUST load skill construct-critique… → You MUST load skill surface-assumptions… → You MUST load skill cross-examine to… → …
- Testing & QA work in your project
- SKILL.md covers Purpose, Input contract, Execution protocol and Output contract, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Adversarial Deliberation is an agent skill from yogsoth-ai/de-anthropocentric-research-engine. Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth, loser-resurrection, and steelman/winner-stress modes are parameters; role execution is runtime-agnostic.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA. The repository describes itself as: A 267-skill research graph in pure markdown — 51 research operations built from 216 single-purpose steps, composed in any order with explicit backtracking. One npx install, no… The licence is Apache-2.0.
When your agent uses it
- Testing & QA work in your project
Example prompts
- “/adversarial-deliberation”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- You MUST load skill construct-critique to construct the strongest attack. You MUST load skill construct-defense to construct the strongest…
- You MUST load skill surface-assumptions to expose load-bearing assumptions. You MUST load skill construct-perspective-set to construct…
- You MUST load skill cross-examine to cross-examine each exchange. You MUST load skill assess-sensitivity to perturb load-bearing choices.
- You MUST load skill adjudicate-exchange to adjudicate against declared criteria. You MUST load skill calibrate-adversarial-confidence to…
What it can do on your machine
Read from SKILL.md and the folder at commit bdb3524. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Adversarial Deliberation loads about 1.3k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 382 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from yogsoth-ai/de-anthropocentric-research-engine at commit bdb3524, republished under its Apache-2.0 licence (© yogsoth-ai). 382 words, ~1,313 tokens.
Download SKILL.mdSave it as
.claude/skills/adversarial-deliberation/SKILL.md (or your agent's skills folder).- name
- adversarial-deliberation
- description
- Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth, loser-resurrection, and steelman/winner-stress modes are parameters; role execution is runtime-agnostic.
adversarial-deliberation
Purpose
Run structured attack, defense, cross-examination, and adjudication over a claim, candidate, criterion set, or current winner.
Input contract
mode_contracts:
critic-defender-judge: &deliberation_input
required: [target, claim_or_candidate, criteria]
optional: [perspectives, escalation_depth]
constraints: [target_scope_and_criteria_must_be_explicit, evidence_provenance_required]
courtroom: *deliberation_input
winner-stress: *deliberation_input
resurrection-advocacy: *deliberation_input
criteria-interrogation: *deliberation_input
stakeholder-objection: *deliberation_input
counter-thesis: *deliberation_inputExecution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- You MUST load skill
construct-critiqueto construct the strongest attack. You MUST load skillconstruct-defenseto construct the strongest defensible case. - You MUST load skill
surface-assumptionsto expose load-bearing assumptions. You MUST load skillconstruct-perspective-setto construct alternate perspectives. - You MUST load skill
cross-examineto cross-examine each exchange. You MUST load skillassess-sensitivityto perturb load-bearing choices. - You MUST load skill
adjudicate-exchangeto adjudicate against declared criteria. You MUST load skillcalibrate-adversarial-confidenceto update calibrated confidence. If the task shifts from balanced exchange to direct attack-surface probing, considerstructured-red-team. If an exposed assumption requires focused perturbation, considerassumption-stress-test. If the surviving claim needs a decisive falsification program,falsification-first-auditmay be the better next tactic. Deviation: skip defense only when the target is explicitly exploratory; skip sensitivity only when no perturbable input is declared; otherwise retain all steps.
Output contract
mode_contracts:
critic-defender-judge: &full_deliberation_output
produces: [attack_record, defense_record, adjudication, confidence_trace]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
courtroom: *full_deliberation_output
winner-stress:
produces: [attack_record, adjudication, confidence_trace]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
resurrection-advocacy: &defense_deliberation_output
produces: [defense_record, adjudication, confidence_trace]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
criteria-interrogation:
produces: [attack_record, defense_record, adjudication]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
stakeholder-objection: *full_deliberation_output
counter-thesis: *defense_deliberation_outputThresholds and quality gates
- A-class debate calibration: declared universe = all rounds and claims; numerator = rounds with evidence-linked confidence updates; batch increment = one completed exchange; stopping reason = confidence stabilizes or unresolved disagreement is explicitly reported; source references = evidence IDs and round IDs; direction/threshold reason = escalate when new evidence changes ranking, terminate only when criteria are adjudicated or a non-resolvable uncertainty is recorded.
- Every verdict must cite criteria and preserve dissent.
Show full SKILL.md (133 more words)Show less
Failure and counterexamples
Do not treat rhetorical fluency as evidence. Mark unresolved when attack and defense share an untested assumption or criteria are absent.
Provenance map
- resolved: multiagent-debate
- resolved: critic-defender-judge
- resolved: courtroom-structured
- resolved: adversarial-escalation
- resolved: steel-manning
- resolved: resurrection-advocacy
- resolved: winner-stress-testing
- resolved: adversarial-debate-protocol
- resolved: assumption-excavation
- resolved: multi-perspective-attack
- intermediate: Pass5/adversarial-debate
- intermediate: Pass5/steelman-validation
Preserved source criteria ledger
| source | source line | kind | source criterion |
|---|---|---|---|
| v4 architecture | node desc | textual | Structured attack/defense/adjudication; loser-resurrection and steelman/winner-stress are parameters. |
Context checkpoint / Delta notes
Append claim, criteria, attack/defense records, dissent, confidence changes, and unresolved questions.
Mode branches
critic-defender-judge: attack, defense, adjudication.courtroom: add cross-examination and explicit evidentiary ruling.winner-stress: perturb the current winner and record failure triggers.resurrection-advocacy: re-open a rejected candidate with a steelman.criteria-interrogation: challenge the criteria before ranking.stakeholder-objection: add perspective-specific objections.counter-thesis: require a mechanism-distinct opposing thesis.
© yogsoth-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/adversarial-deliberation of yogsoth-ai/de-anthropocentric-research-engine.
Open the folder on GitHubat commit bdb3524
Compare with similar skills
Adversarial Deliberation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Adversarial Deliberation this skillyogsoth-ai/de-anthropocentric-research-engine | 505 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Web Application Testinganthropics/skills | 180k | 51 repos | ~966 | Automated safety check: Pass | Apache-2.0 | |
| Diagnosing Bugsfossasia/eventyay-interpretation | 1.6k | 32 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| TDDpietheinstrengholt/rssmonster | 564 | 30 repos | ~906 | Automated safety check: Pass | MIT | |
| TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph | 112 | 11 repos | ~2.4k | Automated safety check: Pass | None | |
| TDDsanity-io/sanity | 6.4k | 20 repos | ~1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Diagnosing Bugs
fossasia/eventyay-interpretation
Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.
TDD
pietheinstrengholt/rssmonster
Test-driven development. An agent skill from pietheinstrengholt/rssmonster.
TDD Workflow
hellangleZ/burn-in-cceverywhere-ralph
A skill your agent uses when writing new features, fixing bugs, or refactoring code.
- Official
TDD
sanity-io/sanity
Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.
Context Driven Development
Ibrahim-3d/orchestrator-supaconductor
A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…
More from yogsoth-ai/de-anthropocentric-research-engine
All 12 skills in this repoEvaluate Scenario Impact
yogsoth-ai/de-anthropocentric-research-engine
Evaluate a fixed candidate, research path, or portfolio under one explicit scenario using stable criteria and return impact, tradeoffs, and failure triggers.
Evaluate Scenario Robustness
yogsoth-ai/de-anthropocentric-research-engine
Aggregate a candidate, strategy, or portfolio across explicit scenarios under a declared robust-decision rule such as worst-case score, minimax regret, maximin, threshold survival, or pivot-trigger…
Evaluate Optionality
yogsoth-ai/de-anthropocentric-research-engine
Evaluate the value of staging, deferral, reversible commitment, and information-gathering options under uncertainty; return decision-relevant option value and trigger conditions.
Adjust Abstraction Scope
yogsoth-ai/de-anthropocentric-research-engine
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system boundary) until the representation has useful…
Aggregate Ranking
yogsoth-ai/de-anthropocentric-research-engine
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Analogical Discovery
yogsoth-ai/de-anthropocentric-research-engine
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
Related
Categories
Questions about Adversarial Deliberation
What does Adversarial Deliberation do?
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Adversarial Deliberation is an agent skill from yogsoth-ai/de-anthropocentric-research-engine. Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner.
When should I use Adversarial Deliberation?
Adversarial Deliberation fits situations like: testing & QA work in your project.
How do I install Adversarial Deliberation in Claude Code?
Run `npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a claude-code`. Or copy the skill folder (skills/adversarial-deliberation in yogsoth-ai/de-anthropocentric-research-engine) into .claude/skills/adversarial-deliberation in your project. Claude Code loads it when a task matches its description.
How do I install Adversarial Deliberation in Codex?
Run `npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a codex`. Or copy the skill folder (skills/adversarial-deliberation in yogsoth-ai/de-anthropocentric-research-engine) into .agents/skills/adversarial-deliberation in your project. Codex loads it when a task matches its description.
Can I use Adversarial Deliberation in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill adversarial-deliberation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adversarial-deliberation, .gemini/skills/adversarial-deliberation, .github/skills/adversarial-deliberation and .opencode/skills/adversarial-deliberation in your project.
What does Adversarial Deliberation need to run?
SKILL.md names no scripts, command-line tools or credentials: Adversarial Deliberation is instructions for the agent only.
Does Adversarial Deliberation access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Adversarial Deliberation safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Adversarial Deliberation use?
Adversarial Deliberation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Adversarial Deliberation use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Adversarial Deliberation?
Skills that share tags, products or a category with Adversarial Deliberation: Web Application Testing (anthropics/skills, 180k stars), Diagnosing Bugs (fossasia/eventyay-interpretation, 1.6k stars), TDD (pietheinstrengholt/rssmonster, 564 stars) and TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Adversarial Deliberation?
yogsoth-ai (a GitHub organization) maintains it in yogsoth-ai/de-anthropocentric-research-engine, which has 505 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 29, 2026.
Source: yogsoth-ai/de-anthropocentric-research-engine on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.