DanielXing
Community@xz1220 · China
peace and love
Agent Skills by DanielXing
Showing 34 vetted skills indexed across 1 GitHub repositories.
cancel
Cancel active oh-my-kimi workflow modes with scoped cleanup and termination.
pipeline
Orchestrate multi-stage agent workflows with resumable state persisted to JSON.
autoresearch
Run iterative improvement loops with JSON evaluation and decision logs.
deep-dive
Run a 3-lane causal trace and deep-interview to crystallize requirements from evidence.
trace
Generates competing hypotheses and evaluates evidence to explain observed outcomes.
skill
Manage local Kimi Agent Skills across built-in, user, and project scopes.
ask
Generate structured second opinions from local Claude or Gemini CLIs.
verify
Verify functional changes with concrete evidence and explicit pass/fail results.
deep-interview
Convert ambiguous ideas into approval-ready specifications via Socratic clarification and ambiguity scoring.
plan
Convert vague requests into structured project plans with quality gates.
ultraqa
Run a cycle-limited QA loop that verifies goals, diagnoses failures, and applies fixes.
ultrawork
Execute independent tasks in parallel with acceptance criteria and evidence collection.
doctor
Diagnoses and repairs oh-my-kimi installation issues including hooks and config.
code-review
Generate severity-rated code reviews with file:line findings and approval decisions.
setup
Install, refresh, and verify oh-my-kimi on local Kimi CLI setups.
ralph
Run a persistent iteration loop with tests, build, lint, and architect validation until completion.
wiki
Maintain a persistent markdown knowledge base with keyword-based wiki page retrieval.
release
Analyze version sources and CI rules to orchestrate repository releases.
visual-ralph
Transform approved visual references into pixel-verified UI code iterations.
deepinit
Generate hierarchical AGENTS.md documentation with parent references across repository directories.
skillify
Extracts chat workflows into reusable oh-my-kimi Skill drafts with YAML frontmatter and triggers.
ai-slop-cleaner
Reduces AI-generated code clutter through disciplined cleanup with regression tests.
team
Coordinate multiple agents through a phased plan-execute-verify-fix pipeline.
visual-verdict
Compare UI screenshots against reference images and output JSON visual QA verdicts.