keypoint-orchestrator
Orchestrate normal keypoint testing with bounded concurrency.
Skill by NetX-lab
Chalk Labs
Need help deploying keypoint-orchestrator?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/netx-lab-keypoint-orchestrator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/keypoint-orchestrator
What's inside
- Skill name
keypoint-orchestrator- Description
- Orchestrate normal keypoint testing with bounded concurrency.
- License
- MIT
- Instructions
- 52 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- SKILL.md
- fixed_batch_concurrency_pattern.md · references/
- minimal_context_principle.md · references/
- check_keypoint_count.py · scripts/
- validate_artifacts.py · scripts/
SKILL.md (first lines)
# Keypoint Orchestrator
Use this skill when `games/{game_name}/keypoints.md` exists and a normal
evaluation run must execute one isolated worker per keypoint.
## Inputs
- `game_name`
- `run_id`
- `game_url`
- `max_concurrent`
- `screenshot_mode`
- `screenshot_interval`
## Contract
Each keypoint worker writes artifacts under:
```text
runs/{game_name}/{run_id}/keypoint_{id}/
```
Required files per keypoint:
- `result.json`
- `test_config.json`
- `test_script.mjs` or `test_script.js`
- `test_result.json`
The orchestrator should collect all completed keypoint results and write:
- `runs/{game_name}/{run_id}/summary.json`
- `runs/{game_name}/{run_id}/summary.md`
## Validation
Use the bundled validators:
```bash
python3 skills/keypoint-orchestrator/scripts/check_keypoint_count.py \
--keypoints-file "games/${GAME_NAME}/keypoints.md" \
--min-count 30
python3 skills/keypoint-orchestrator/scripts/validate_artifacts.py \
--run-root "runs/${GAME_NAME}/${RUN_ID}" \
--test-mode normal
```
Validation failure means the run is incomplete and must not be reported as a
successful evaluation.From NetX-lab/GameGen-Verifier, MIT.
More from NetX-lab/GameGen-Verifier
- 0.519score
game-gen-with-data
NetX-lab
Generate a runnable TypeScript game from a game description file, plus data.md and a state injection API for evaluation.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
auto-eval
NetX-lab
Run the full game-gen-eval pipeline in normal mode (state injection + visual interaction verification) from a generated game.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
distill-verified-keypoints
NetX-lab
Extract discrete, verifiable, specification-first keypoints from a game description for subsequent evaluation of game logic correctness.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
analyze-game-implementation
NetX-lab
Analyze game source code and write a concise implementation summary for downstream testing.
SkillCFreshness: C★ 3Claude Code +9 - 0.511score
generative-state-construction
NetX-lab
Convert fuzzy keypoint text into concrete short interaction data for executable verification.
SkillCFreshness: C★ 3Claude Code +9 - 0.511score
short-interaction-verification
NetX-lab
Execute Playwright verification for one concrete short interaction and write result artifacts.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
cross-verification
NetX-lab
Recheck an existing normal keypoint evaluation artifact without rerunning the game.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
recheck-orchestrator
NetX-lab
Run cross-verification on an existing evaluation run and generate recheck_summary.md plus recheck_comparison.json.
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 7, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/NetX-lab/GameGen-Verifier
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from NetX-lab
- 0.519score
game-gen-with-data
NetX-lab
Generate a runnable TypeScript game from a game description file, plus data.md and a state injection API for evaluation.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
auto-eval
NetX-lab
Run the full game-gen-eval pipeline in normal mode (state injection + visual interaction verification) from a generated game.
SkillCFreshness: C★ 3Claude Code +9 - 0.519score
distill-verified-keypoints
NetX-lab
Extract discrete, verifiable, specification-first keypoints from a game description for subsequent evaluation of game logic correctness.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
analyze-game-implementation
NetX-lab
Analyze game source code and write a concise implementation summary for downstream testing.
SkillCFreshness: C★ 3Claude Code +9 - 0.511score
generative-state-construction
NetX-lab
Convert fuzzy keypoint text into concrete short interaction data for executable verification.
SkillCFreshness: C★ 3Claude Code +9 - 0.511score
short-interaction-verification
NetX-lab
Execute Playwright verification for one concrete short interaction and write result artifacts.
SkillCFreshness: C★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get keypoint-orchestrator running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
keypoint-orchestrator skill. Agent Mart. https://agentmart.dev/skills/netx-lab-keypoint-orchestrator (last updated 2026-10-24)