Stats
Actions
Tags
From tdd-pipeline
Standard briefing for coding agents. Covers file rules, shell rules, quality bar, and directive to read CLAUDE.md for project-specific context.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tdd-pipeline:agent-briefingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read this entire document before writing any code.
Read this entire document before writing any code.
Write ONLY the files your role permits:
Do NOT modify build files or configuration files. Do NOT commit -- the orchestrator handles commits.
Check the project's CLAUDE.md for exact file paths
and patterns (e.g. src/{module}.py,
tests/test_{module}.py).
Complete ALL listed behaviors. Partial work will be rejected.
Every public function must have at least one test exercising it.
Read the project's CLAUDE.md for the test command. Run it exactly as specified.
Run commands exactly as shown. Do NOT append shell
syntax like 2>&1, ; echo "EXIT: $?", or pipe
redirections. The Bash tool already captures stdout,
stderr, and exit codes.
Read the project's CLAUDE.md for language-specific corrections, lint rules, and coding standards. If a language plugin has injected corrections (e.g. API changes or lint rules), they will appear there.
npx claudepluginhub kelp/kelp-claude-plugins --plugin tdd-pipelineCreates and improves CLAUDE.md files for project memory and agent configuration using TDD workflow with task tracking. Activates on 'create CLAUDE.md', 'setup project', 'configure agent'.
CLAUDE.md instruction quality: writing effective project instructions, diagnosing why Claude ignores rules, routing content to the right layer, and systematic improvement. Invoke whenever task involves any interaction with CLAUDE.md files — writing, reviewing, auditing, improving, or debugging instruction compliance.
Generates project-specific CLAUDE.md rules by detecting stack from package.json, Cargo.toml, pyproject.toml, go.mod, git log, and user-selecting categories like response format, library preference, code review stance. Use for new projects, repo onboarding, or establishing conventions.