youdede-toolkit

169 coding-agent skills with 575 declared refusal boundaries.

169 skills

Plan, enforce, and independently verify accessible interface behavior from source evidence.

4 skills · 2 agents · hooks

Install a guarded read-only MCP baseline with declared authority and independent trust-boundary review.

2 skills · 1 agent · 3 MCP servers · hooks

Prepare bounded code changes, obtain independent review, and prevent oversized unreviewable commits.

3 skills · 1 command · 1 agent · hooks

Deliver bounded incremental changes, prepare review evidence, and prevent unreviewable diffs.

2 skills · 1 command · 1 agent · hooks

Build an evidence-backed release decision and stop publication from unsafe repository state.

1 skill · 1 command · 2 agents · hooks

Design agent integrations, review their trust boundary, and block obvious data-exposure paths.

2 skills · 2 agents · hooks

Persist bounded hash-chained checkpoints, restore cited context, and verify continuity across sessions.

1 skill · 2 commands · 1 agent · hooks

Review schema and migration changes with deterministic safety checks and independent risk analysis.

2 skills · 1 agent · hooks

Collect bounded GitHub evidence in read-only mode and turn failing CI evidence into a traceable diagnosis.

1 skill · 1 command · 1 agent · 1 MCP server

Exercise an unauthenticated local interface in an isolated browser, preserve journey-level evidence, and review the change for web performance risks.

1 skill · 1 agent · 1 MCP server

Plan a staged infrastructure change and independently review lifecycle, blast-radius, and recovery evidence.

1 skill · 2 agents

Review mobile release evidence, accessibility, and reliability. Guards stop fastlane-action, EAS, Xcode, and Gradle uploads from a dirty tree or bad versions; custom lanes pass.

1 skill · 1 agent · hooks