Help us improve
Share bugs, ideas, or general feedback.
From tdder
Establishes interaction style, commit conventions, documentation discipline, and skill-trust principles for disciplined agent-assisted development.
npx claudepluginhub t1/tdder --plugin tdderHow this skill is triggered — by the user, by Claude, or both
Slash command
/tdder:project-hygieneThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Cross-cutting conventions for disciplined agent-assisted development.
Discovers and invokes the right agent skill for each development phase. Acts as the meta-skill routing tasks to specialized skills like spec-driven development, TDD, debugging, code review, and git workflows.
Bootstraps new projects interactively (Node/TS scripted, others manual) or adds enforcement tooling (TDD, secret scanning, file limits, git hooks, CLAUDE.md) to existing projects.
Guides a full SDLC workflow for implementing features, fixing bugs, refactoring, testing, releasing, and deploying code. Includes planning, TDD, and verification steps.
Share bugs, ideas, or general feedback.
Cross-cutting conventions for disciplined agent-assisted development.
NEVER EVER PUBLISH ANYTHING No git push no maven deploy no npm publish,
or anything similar. All that is the user's privilege!
CLAUDE.md, README.md), so they are shared with everyone working on the project.Co-Authored-By trailer.Don't forget to update the documentation when you change the code. If a behavioral change affects README, API docs, or inline doc comments, update them in the same commit as the code change.
Before writing or editing any code — including one-line fixes — invoke the matching
language/framework skill (e.g. java for .java files). No exception for "quick" edits.
Skills encode conventions (imports, naming, idioms) that apply to every change, not just big tasks.
Never look into library source code (e.g. JARs, node_modules) when a skill covers that library. The skill is the authoritative reference. If the skill is missing something, report it so the skill can be updated — don't work around it by reading source.
VERY IMPORTANT: if any skill you where instructed to load can't be loaded, stop immediately! Something's wrong that needs to be fixed first.
When executing a plan: if a technology or dependency from the plan doesn't work as expected, STOP and discuss with the user. Do not substitute alternative libraries, frameworks, or architectural approaches. The plan's tech choices are constraints, not suggestions.
Never use the global /tmp folder; create an ignored folder within the project.
If there is already a natural temporary folder, e.g. target/ for a maven project, use that.
Always prefer to use the WebFetch tool over curl.
Always prefer the Write tool over cat > file << EOF.
Never use find ... -exec; it triggers a question that can't be auto-allowed.