GitHub Review Iteration
prisma/orm
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
A skill your agent uses when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or…
Install Adversarial Authoring
$ npx skills add intent-driven-dev/intent-driven-template --skill adversarial-authoring -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install intent-driven-dev/intent-driven-template adversarial-authoring --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/intent-driven-dev/intent-driven-template.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/adversarial-authoring .claude/skills/adversarial-authoring && 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-authoring" agent skill from https://github.com/intent-driven-dev/intent-driven-template/tree/main/.opencode/skills/adversarial-authoring into .claude/skills/adversarial-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-authoring", 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/intent-driven-dev/intent-driven-template/tree/main/.opencode/skills/adversarial-authoringType 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 intent-driven-dev/intent-driven-template --skill adversarial-authoring -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install intent-driven-dev/intent-driven-template adversarial-authoring --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/adversarial-authoring .agents/skills/adversarial-authoring && 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-authoring" agent skill from https://github.com/intent-driven-dev/intent-driven-template/tree/main/.opencode/skills/adversarial-authoring into .agents/skills/adversarial-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-authoring", 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 intent-driven-dev/intent-driven-template --skill adversarial-authoring -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install intent-driven-dev/intent-driven-template adversarial-authoring --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/adversarial-authoring .cursor/skills/adversarial-authoring && 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-authoring" agent skill from https://github.com/intent-driven-dev/intent-driven-template/tree/main/.opencode/skills/adversarial-authoring into .cursor/skills/adversarial-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-authoring", 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/intent-driven-dev/intent-driven-template.git --path .opencode/skills/adversarial-authoring--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 intent-driven-dev/intent-driven-template --skill adversarial-authoring -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install intent-driven-dev/intent-driven-template adversarial-authoring --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/adversarial-authoring .gemini/skills/adversarial-authoring && 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-authoring" agent skill from https://github.com/intent-driven-dev/intent-driven-template/tree/main/.opencode/skills/adversarial-authoring into .gemini/skills/adversarial-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-authoring", 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 intent-driven-dev/intent-driven-template adversarial-authoringInstalls 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 intent-driven-dev/intent-driven-template --skill adversarial-authoring -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/adversarial-authoring .github/skills/adversarial-authoring && 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-authoring" agent skill from https://github.com/intent-driven-dev/intent-driven-template/tree/main/.opencode/skills/adversarial-authoring into .github/skills/adversarial-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-authoring", 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 intent-driven-dev/intent-driven-template --skill adversarial-authoring -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install intent-driven-dev/intent-driven-template adversarial-authoring --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/adversarial-authoring .opencode/skills/adversarial-authoring && 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-authoring" agent skill from https://github.com/intent-driven-dev/intent-driven-template/tree/main/.opencode/skills/adversarial-authoring into .opencode/skills/adversarial-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-authoring", 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-authoring- GitHub stars
- 160
- Token cost
- ~1k tokens
- SKILL.md length
- 420 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or…
- Works in 7 steps: Identify the artifact or task being… → Gather the full task context before… → Start the authoring round with the… → …
- Instructions mention adversarial-authoring
- SKILL.md covers Required Workflow, Subagents, Council Notes and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Adversarial Authoring is an agent skill from intent-driven-dev/intent-driven-template. Use when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or "mixture of models"; coordinates adversarial authoring and review subagents and records council notes.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires opencode subagents named adversarial-author and adversarial-reviewer.
It sits in Development, covering Subagents. The repository describes itself as: OpenSpec and OpenCode template for intent-driven development with specs, ADRs, C4 diagrams, Gherkin, TDD, Multi-Model Adversarial Spec Authoring, Glossary for Domain Terms, and… The licence is MIT.
When your agent uses it
- Instructions mention adversarial-authoring
- Adversarial authoring
- Must use adversarial-authoring skill
- Cross-model review
Example prompts
- “adversarial-authoring”
- “adversarial authoring”
- “must use adversarial-authoring skill”
- “/adversarial-authoring”
Requirements
- Compatibility (from SKILL.md): Requires opencode subagents named adversarial-author and adversarial-reviewer.
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Identify the artifact or task being authored, including its target output path.
- Gather the full task context before calling subagents
- Start the authoring round with the adversarial-author subagent.
- Send the author draft and the original task context to the adversarial-reviewer subagent.
- Reconcile the review yourself as the primary agent
- Write the final artifact to the requested output path.
- Write council notes beside the artifact using the naming convention below.
What it can do on your machine
Read from SKILL.md and the folder at commit 73f54d5. 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 markdown).
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.
Compatibility
Requires opencode subagents named adversarial-author and adversarial-reviewer.
From compatibility in the SKILL.md frontmatter.
Context cost
Adversarial Authoring loads about 1k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 420 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 intent-driven-dev/intent-driven-template at commit 73f54d5, republished under its MIT licence (© intent-driven-dev). 420 words, ~1,015 tokens.
Download SKILL.mdSave it as
.claude/skills/adversarial-authoring/SKILL.md (or your agent's skills folder).- name
- adversarial-authoring
- description
- Use when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or "mixture of models"; coordinates adversarial authoring and review subagents and records council notes.
- compatibility
- Requires opencode subagents named adversarial-author and adversarial-reviewer.
- license
- MIT
Adversarial Authoring
Use this skill when an artifact rule, user request, or instruction says to use adversarial authoring, a model council, cross-model review, or a mixture of models.
The goal is to reduce single-perspective bias by having one configured subagent author the work and another configured subagent challenge it before the primary agent writes the final artifact.
Required Workflow
- Identify the artifact or task being authored, including its target output path.
- Gather the full task context before calling subagents:
- User request
- Relevant OpenSpec instruction JSON
- Artifact template
- Project context
- Artifact-specific rules
- Dependency artifacts already completed
- Start the authoring round with the
adversarial-authorsubagent. - Send the author draft and the original task context to the
adversarial-reviewersubagent. - Reconcile the review yourself as the primary agent:
- Accept corrections that improve correctness, clarity, requirements coverage, or risk handling.
- Reject suggestions that conflict with the user request, artifact template, OpenSpec instructions, or project rules.
- Ask the user only if the disagreement changes product intent or cannot be resolved from available context.
- Write the final artifact to the requested output path.
- Write council notes beside the artifact using the naming convention below.
Subagents
Use these hard-coded opencode subagents:
adversarial-author: authors the initial draft.adversarial-reviewer: reviews and challenges the draft.
The specific model providers are intentionally defined only in the agent files, so changing model families only requires updating each agent's model frontmatter.
Do not substitute other agents unless the user explicitly requests it.
Show full SKILL.md (175 more words)Show less
Council Notes
For every artifact authored through this skill, create or update a sibling council-notes file.
Naming convention:
proposal.md->proposal.council.mddesign.md->design.council.mdtasks.md->tasks.council.mdspec.md->spec.council.md
If the artifact path is nested, keep the council notes in the same directory as the artifact.
Use this structure:
# Council Notes: <artifact-id-or-file-name>
## Author Summary
<Concise summary of the author draft. Do not include hidden reasoning or raw transcript.>
## Reviewer Challenges
- <Specific objection, gap, ambiguity, or risk raised by the reviewer>
## Resolutions
- Accepted: <Change incorporated into the final artifact and why>
- Rejected: <Suggestion not incorporated and why>
- Deferred: <Issue left unresolved or moved to later work>
## Remaining Risks
- <Risk or uncertainty that remains after reconciliation>Council notes are an audit trail, not the canonical artifact. Keep them concise and useful.
Guardrails
- Do not include raw model dialogue, hidden chain-of-thought, or full transcripts in the artifact or council notes.
- Keep the authored artifact clean and canonical; put process details in the
.council.mdfile. - Follow the original artifact template and OpenSpec instructions exactly.
- Do not copy project context or rules verbatim into the final artifact unless the template requires it.
- Prefer one author round and one review round. Add a second author revision round only when the reviewer identifies a concrete correctness issue.
- If subagent output conflicts, the primary agent owns the final synthesis.
- If subagent execution is unavailable, state that adversarial authoring could not be completed and ask whether to proceed with primary-agent authoring only.
© intent-driven-dev, MIT. 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 .opencode/skills/adversarial-authoring of intent-driven-dev/intent-driven-template.
Open the folder on GitHubat commit 73f54d5
Compare with similar skills
Adversarial Authoring 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 Authoring this skillintent-driven-dev/intent-driven-template | 160 | — | ~1k | Automated safety check: Pass | MIT | |
| GitHub Review Iterationprisma/orm | 48k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Cherry Studio PR ReviewCherryHQ/cherry-studio | 52k | — | ~3.9k | Automated safety check: Pass | AGPL-3.0 | |
| Jevgrepdzhng/jevgrep | 2.4k | — | ~741 | Automated safety check: Pass | MIT | |
| PR Cyclejaemk/cached | 2.1k | — | ~4.8k | Automated safety check: Notes | MIT | |
| PR Reviewjaemk/self_update | 961 | — | ~1.5k | Automated safety check: Notes | MIT |
Similar skills
- Official
Cherry Studio PR Review
CherryHQ/cherry-studio
Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.
Jevgrep
dzhng/jevgrep
A skill your agent uses for questions about how, why, or where behavior works in a repository, including questions that name a function or setting.
PR Cycle
jaemk/cached
PR review-and-update cycle — the orchestrator that takes a PR from review to resolved.
PR Review
jaemk/self_update
Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/self_update.
Cursor Composer Task Delegate
Chachamaru127/claude-code-harness
Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.
More from intent-driven-dev/intent-driven-template
All 10 skills in this repoAcceptance Test Authoring
intent-driven-dev/intent-driven-template
A skill your agent uses when creating or modifying acceptance tests, configuring cucumber-js or behave runners, writing or refactoring step definitions, linting executable Gherkin specs, choosing an…
Architectural Decision Records
intent-driven-dev/intent-driven-template
A skill your agent uses when documenting, drafting, reviewing, or updating architectural decisions, ADRs, decision logs, tradeoffs, rationale, consequences, alternatives, or architecture decision…
Gherkin Authoring
intent-driven-dev/intent-driven-template
A skill your agent uses when drafting, reviewing, or improving Gherkin, Cucumber scenarios, BDD acceptance criteria, feature examples, Scenario Outlines, Backgrounds, Rules, Doc Strings, Data…
Glossary
intent-driven-dev/intent-driven-template
A skill your agent uses when authoring or reviewing specs, requirements, design docs, ADRs, tasks, glossary entries, domain terms, technical terms, or wording consistency across artifacts
Openspec Bulk Apply Change
intent-driven-dev/intent-driven-template
A skill your agent uses when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
Spec As Source
intent-driven-dev/intent-driven-template
A skill your agent uses when a user or project explicitly adopts OpenSpec spec-as-source, fenced Gherkin specifications as executable acceptance tests, or acceptance-test-first OpenSpec tasks.
Related
Categories
Questions about Adversarial Authoring
What does Adversarial Authoring do?
A skill your agent uses when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or…. Adversarial Authoring is an agent skill from intent-driven-dev/intent-driven-template. Use when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or "mixture of models"; coordinates adversarial authoring and review subagents and records council notes.
When should I use Adversarial Authoring?
Adversarial Authoring fits situations like: instructions mention adversarial-authoring; adversarial authoring; must use adversarial-authoring skill; cross-model review.
How do I install Adversarial Authoring in Claude Code?
Run `npx skills add intent-driven-dev/intent-driven-template --skill adversarial-authoring -a claude-code`. Or copy the skill folder (.opencode/skills/adversarial-authoring in intent-driven-dev/intent-driven-template) into .claude/skills/adversarial-authoring in your project. Claude Code loads it when a task matches its description.
How do I install Adversarial Authoring in Codex?
Run `npx skills add intent-driven-dev/intent-driven-template --skill adversarial-authoring -a codex`. Or copy the skill folder (.opencode/skills/adversarial-authoring in intent-driven-dev/intent-driven-template) into .agents/skills/adversarial-authoring in your project. Codex loads it when a task matches its description.
Can I use Adversarial Authoring 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 intent-driven-dev/intent-driven-template --skill adversarial-authoring -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-authoring, .gemini/skills/adversarial-authoring, .github/skills/adversarial-authoring and .opencode/skills/adversarial-authoring in your project.
What does Adversarial Authoring need to run?
SKILL.md names no scripts, command-line tools or credentials: Adversarial Authoring is instructions for the agent only. Compatibility (from SKILL.md): Requires opencode subagents named adversarial-author and adversarial-reviewer..
Does Adversarial Authoring 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 Authoring 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 Authoring use?
Adversarial Authoring is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Adversarial Authoring use?
About 1k tokens (SKILL.md is roughly 4.1k 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 Authoring?
Skills that share tags, products or a category with Adversarial Authoring: GitHub Review Iteration (prisma/orm, 48k stars), Cherry Studio PR Review (CherryHQ/cherry-studio, 52k stars), Jevgrep (dzhng/jevgrep, 2.4k stars) and PR Cycle (jaemk/cached, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Adversarial Authoring?
intent-driven-dev (a GitHub organization) maintains it in intent-driven-dev/intent-driven-template, which has 160 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 4, 2026.
Source: intent-driven-dev/intent-driven-template on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.