New Client — Development skill for Claude Code
Onboard a client — scaffold a profile in the working project and seed its eval cases.
How to install New Client
Installs to ~/.claude/skills/hadicancatak-coder-gf-creative-team-new-client/SKILL.md
mkdir -p ~/.claude/skills/hadicancatak-coder-gf-creative-team-new-client && curl -fsSL https://raw.githubusercontent.com/hadicancatak-coder/GF-Creative-Team/HEAD/commands/new-client.md -o ~/.claude/skills/hadicancatak-coder-gf-creative-team-new-client/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What New Client does
Onboard a client — scaffold a profile in the working project and seed its eval cases.
Alternatives in Development
- GenericAgent — Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token co 6.1k ★
- Onboard — You are given the following context: $ARGUMENTS 5.8k ★
- Agent Instructions — This project uses bd (beads) for issue tracking 1.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Eval Author
Draft a new eval case (eval/cases/ .json) + scaffold its golden folder, golden_pending until captured on the V
Agtmls New Skill
Scaffold a new AgtMLS skill with its metadata and both eval cases.
Vault Gardener
Seed an empty vault or new topic with an interactive starter structure and initial notes. Use when a knowledge
Architect Prove
Run the prove stage. Writes at least ten eval cases including a refusal and an injection case, runs the harnes
Eval Cases
Grow an eval case set from the placeholder rows to a real 15-25 - harvest genuine cases out of the repository
Validate Starter
從 meta repo root 驗證 template/ starter seed 的結構完整性、文件一致性與 scaffold 輸出
Related Agents
Eval Skew Reviewer
Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew
Scaffold Inspect
Sets up inspect-ai evaluation configurations for all runs in a designed experiment. Reads experiment_summary.y
Fk Kernel Engineer
Writes and integrates GPU kernels (Triton, TileLang, CuTe DSL, CUDA C++, CUDA graphs, torch.compile) under can