Workflow Review
nabeelhyatt/coworkpowers
Run parallel multi-agent review on completed knowledge work.
Adversarial review skill. An agent skill from blueberrycongee/termcanvas.
Install Challenge
$ npx skills add blueberrycongee/termcanvas --skill challenge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install blueberrycongee/termcanvas challenge --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/blueberrycongee/termcanvas.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills/challenge .claude/skills/challenge && 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 "challenge" agent skill from https://github.com/blueberrycongee/termcanvas/tree/main/skills/skills/challenge into .claude/skills/challenge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "challenge", 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/blueberrycongee/termcanvas/tree/main/skills/skills/challengeType 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 blueberrycongee/termcanvas --skill challenge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install blueberrycongee/termcanvas challenge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/blueberrycongee/termcanvas.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skills/challenge .agents/skills/challenge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "challenge" agent skill from https://github.com/blueberrycongee/termcanvas/tree/main/skills/skills/challenge into .agents/skills/challenge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "challenge", 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 blueberrycongee/termcanvas --skill challenge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install blueberrycongee/termcanvas challenge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/blueberrycongee/termcanvas.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skills/challenge .cursor/skills/challenge && 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 "challenge" agent skill from https://github.com/blueberrycongee/termcanvas/tree/main/skills/skills/challenge into .cursor/skills/challenge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "challenge", 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/blueberrycongee/termcanvas.git --path skills/skills/challenge--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 blueberrycongee/termcanvas --skill challenge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install blueberrycongee/termcanvas challenge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/blueberrycongee/termcanvas.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skills/challenge .gemini/skills/challenge && 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 "challenge" agent skill from https://github.com/blueberrycongee/termcanvas/tree/main/skills/skills/challenge into .gemini/skills/challenge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "challenge", 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 blueberrycongee/termcanvas challengeInstalls 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 blueberrycongee/termcanvas --skill challenge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/blueberrycongee/termcanvas.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skills/challenge .github/skills/challenge && 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 "challenge" agent skill from https://github.com/blueberrycongee/termcanvas/tree/main/skills/skills/challenge into .github/skills/challenge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "challenge", 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 blueberrycongee/termcanvas --skill challenge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install blueberrycongee/termcanvas challenge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/blueberrycongee/termcanvas.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skills/challenge .opencode/skills/challenge && 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 "challenge" agent skill from https://github.com/blueberrycongee/termcanvas/tree/main/skills/skills/challenge into .opencode/skills/challenge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "challenge", 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
challenge- GitHub stars
- 406
- Token cost
- ~1.5k tokens
- SKILL.md length
- 790 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Adversarial review skill. An agent skill from blueberrycongee/termcanvas.
- Works in 5 steps: Extract → Spawn 4 workers → Watch → …
- The user wants to stress-test an idea
- SKILL.md covers When to use, Step 1: Extract, Step 2: Spawn 4 workers and Step 3: Watch, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Challenge is an agent skill from blueberrycongee/termcanvas. Adversarial review skill. Use when the user wants to stress-test an idea, argument, proposal, or opinion from multiple independent angles. Spawns parallel Hydra workers with orthogonal analytical methodologies.
Its SKILL.md is about 1.5k 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, covering Load testing. The repository describes itself as: An infinite canvas desktop app for visually managing terminals. The licence is MIT.
When your agent uses it
- The user wants to stress-test an idea
- Opinion from multiple independent angles
Example prompts
- “/challenge”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit fa25981. 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 json).
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
Challenge loads about 1.5k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 790 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 blueberrycongee/termcanvas at commit fa25981, republished under its MIT licence (© blueberrycongee). 790 words, ~1,496 tokens.
Download SKILL.mdSave it as
.claude/skills/challenge/SKILL.md (or your agent's skills folder).- name
- challenge
- description
- Adversarial review skill. Use when the user wants to stress-test an idea, argument, proposal, or opinion from multiple independent angles. Spawns parallel Hydra workers with orthogonal analytical methodologies.
Challenge
Multi-angle adversarial review via isolated Hydra workers. Each worker attacks the same input using a different analytical method, with no visibility into the others' reasoning.
When to use
- User says "challenge this", "stress-test this", "poke holes in this", "what am I missing", "argue against this", or similar
- User has been discussing a topic and wants independent critical review
- Any argument, proposal, opinion, decision, or design that needs pressure-testing
Step 1: Extract
Summarize the argument/proposal/opinion from the current conversation into a neutral, complete brief. Include:
- The core claim or proposal
- Key supporting reasons the user or you have discussed
- Any constraints or context that are relevant
Do NOT editorialize or signal which parts you think are weak. The summary must be fair — biased summaries defeat the purpose.
Step 2: Spawn 4 workers
Use hydra spawn to launch 4 parallel workers. Each worker receives the
same summary but a different methodology prompt. Inherit the current
terminal's provider via --worker-type.
Worker prompts
Each worker prompt must include, in this order:
- The mandatory preamble below (verbatim)
- The full summary from Step 1
- The methodology instructions below (one per worker)
- Instruction to write findings to
result.jsonatomically
Mandatory preamble (prepend to every worker prompt verbatim)
SCOPE RULE — strictly enforced. Your analysis MUST extend beyond the immediate input. The input is your starting point, not your boundary. You are required to:
- Follow every chain. When you find something, do not note it and move on. Ask "what does this lead to?" and trace it at least 2-3 links further. Each link must be a concrete step, not a vague worry.
- Search outward. For every finding, actively look for evidence from outside the input's immediate context — other fields, other systems, historical precedents, known failure cases, research, prior art. If you cannot name a specific external reference, you have not searched wide enough.
- Refuse shallow answers. If a finding can be stated in one sentence with no chain and no external reference, it is not finished. Deepen it or discard it.
A review that stays inside the input's own frame is a failure. You will be evaluated on depth of chains and breadth of external evidence.
Worker 1 — Counterexample
Find concrete cases where this fails, backfires, or produces the opposite of what is intended. Each case must be specific enough to verify or reproduce — no abstract objections. Prioritize the most damaging cases first.
Worker 2 — Hidden Assumptions
Surface everything this takes for granted — every unstated dependency, every "this just works" that is not actually guaranteed. Assumptions form chains; each one rests on deeper ones. Trace each chain until you hit bedrock. An assumption is fragile if reasonable people could disagree with it, if it depends on conditions that may change, or if the whole thing collapses without it. Rank from most fragile to most solid.
Show full SKILL.md (315 more words)Show less
Worker 3 — Mechanism & Second-Order Effects
Challenge the mechanism — the chain of steps by which this is supposed to achieve its goal. Map the full chain from action to intended outcome. For each link: is it proven or assumed? Could the same input produce a different output? Are there missing steps? Then keep going past the intended outcome — what second and third-order effects emerge? What feedback loops are created? What does this look like after the system evolves?
Worker 4 — Boundary & Context Shift
Find where this stops being valid. Push along every dimension that matters until something breaks. Do not just find the breaking point — follow the chain past it: graceful degradation or catastrophic failure? When one boundary breaks, what else breaks with it? Then shift context entirely: would this still hold if the surrounding conditions, the actors, or the constraints were fundamentally different?
Result contract
Each worker writes result.json:
{
"success": true,
"summary": "<one-paragraph synthesis of the most critical findings>",
"findings": [
{
"point": "<the specific challenge>",
"severity": "critical | significant | minor",
"reasoning": "<why this matters>"
}
],
"outputs": [],
"evidence": [],
"next_action": { "type": "complete", "reason": "Challenge review complete" }
}Write to result.json.tmp first, then atomically rename it to result.json
only after the JSON is complete.
Step 3: Watch
For each spawned worker, run hydra watch --agent <agentId>. This polls
the worker's assignment run result until it reaches a terminal state (completed,
failed, or terminal dead).
Run all 4 watches in parallel (background bash commands or concurrent tool calls). Do not proceed until all 4 complete.
Step 4: Synthesize
Collect all 4 result files. Present to the user:
- Critical challenges first — anything rated "critical" from any worker, grouped by theme rather than by methodology
- Significant challenges — grouped the same way
- Minor observations — briefly listed
Do NOT defend the original argument while presenting challenges. Present them neutrally. Let the user decide what to address.
Step 5: Converge
After presenting, help the user:
- Decide which challenges are real threats vs acceptable risks
- Strengthen the original argument/proposal where needed
- Identify any challenges that change the conclusion entirely
This step is collaborative — you are no longer adversarial.
© blueberrycongee, 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 skills/skills/challenge of blueberrycongee/termcanvas.
Open the folder on GitHubat commit fa25981
Compare with similar skills
Challenge 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 |
|---|---|---|---|---|---|---|
| Challenge this skillblueberrycongee/termcanvas | 406 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Workflow Reviewnabeelhyatt/coworkpowers | 114 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Ask Colleaguenickwinder/synthteam | 103 | — | ~1.4k | Automated safety check: Pass | None | |
| Plan Interrogaterohitg00/pro-workflow | 2.9k | — | ~855 | Automated safety check: Pass | None | |
| Plan ReviewMathews-Tom/armory | 328 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Grillingpietheinstrengholt/rssmonster | 564 | 32 repos | ~510 | Automated safety check: Pass | MIT |
Similar skills
Ask Colleague
nickwinder/synthteam
Consult a distilled persona of a colleague for their likely take, critique, or pushback on an idea — locally, without involving them.
Plan Interrogate
rohitg00/pro-workflow
Stress-test a plan by walking its decision tree one question at a time.
Plan Review
Mathews-Tom/armory
Pre-implementation plan audit stress-testing scope, assumptions, risks, and failure modes before code is written.
Grilling
pietheinstrengholt/rssmonster
Grill the user relentlessly about a plan, decision, or idea.
- Official
Microbenchmarking
dotnet/skills
Activate this skill when BenchmarkDotNet (BDN) is involved in the task — creating, running, configuring, or reviewing BDN benchmarks.
More from blueberrycongee/termcanvas
Code Review
blueberrycongee/termcanvas
Structured code review skill. An agent skill from blueberrycongee/termcanvas.
Hydra
blueberrycongee/termcanvas
A skill your agent uses when a task should run through Hydra's Lead-driven workflow for multi-agent orchestration, or when an existing workflow must be inspected or cleaned up.
QA
blueberrycongee/termcanvas
QA testing skill with real browser automation. An agent skill from blueberrycongee/termcanvas.
Investigate
blueberrycongee/termcanvas
Systematic debugging skill. An agent skill from blueberrycongee/termcanvas.
Security Audit
blueberrycongee/termcanvas
Security audit skill. An agent skill from blueberrycongee/termcanvas.
Using Termcanvas
blueberrycongee/termcanvas
A skill your agent uses when starting work in a TermCanvas-managed repo to route between direct work, Hydra, or a narrow TermCanvas skill.
Related
Categories
Questions about Challenge
What does Challenge do?
Adversarial review skill. An agent skill from blueberrycongee/termcanvas. Challenge is an agent skill from blueberrycongee/termcanvas. Adversarial review skill.
When should I use Challenge?
Challenge fits situations like: the user wants to stress-test an idea; opinion from multiple independent angles.
How do I install Challenge in Claude Code?
Run `npx skills add blueberrycongee/termcanvas --skill challenge -a claude-code`. Or copy the skill folder (skills/skills/challenge in blueberrycongee/termcanvas) into .claude/skills/challenge in your project. Claude Code loads it when a task matches its description.
How do I install Challenge in Codex?
Run `npx skills add blueberrycongee/termcanvas --skill challenge -a codex`. Or copy the skill folder (skills/skills/challenge in blueberrycongee/termcanvas) into .agents/skills/challenge in your project. Codex loads it when a task matches its description.
Can I use Challenge 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 blueberrycongee/termcanvas --skill challenge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/challenge, .gemini/skills/challenge, .github/skills/challenge and .opencode/skills/challenge in your project.
What does Challenge need to run?
SKILL.md names no scripts, command-line tools or credentials: Challenge is instructions for the agent only.
Does Challenge 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 Challenge 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 Challenge use?
Challenge is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Challenge use?
About 1.5k tokens (SKILL.md is roughly 6k 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 Challenge?
Skills that share tags, products or a category with Challenge: Workflow Review (nabeelhyatt/coworkpowers, 114 stars), Ask Colleague (nickwinder/synthteam, 103 stars), Plan Interrogate (rohitg00/pro-workflow, 2.9k stars) and Plan Review (Mathews-Tom/armory, 328 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Challenge?
blueberrycongee (a GitHub user) maintains it in blueberrycongee/termcanvas, which has 406 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on May 31, 2026.
Source: blueberrycongee/termcanvas on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.