Loading...
Loading...
Found 8,144 Skills
Generate AGENTS.md file and docs/ knowledge base skeleton in the project root directory, and establish a document governance system for agent-first repositories. Manually triggered, writes the template after checking for existence.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Build and use the verification infrastructure coding agents need to prove their work. Use when: a repo has no bootable dev environment, no real-surface tests, or no interaction layer an agent can use; auditing or grading a repo's agent-readiness; verifying changes work end to end on real surfaces; or when harness gaps block reliable agent output.
Create and manage a Notion-based tweet performance tracking system for "poor man's reinforcement learning"
Implement reviewer feedback on a Canva design. Reads all comment threads, synthesises what reviewers want, makes the clear-cut changes directly, and flags anything that needs a human decision. Use when the user asks to "implement feedback on my deck", "address comments on a design", "apply review feedback", "fix the comments on my presentation", or "implement the feedback".
Orchestrates a continuous journey-builder → refine → restart loop. Runs journey-builder and refine-journey sequentially, improving the skill each iteration. Loops until all spec requirements are covered by journeys and the score reaches 95%.
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
Automatically create a PR to register insights, conventions, and best practices obtained from the current project as rules in the TBSten/skills repository. It runs the entire end-to-end process: collecting insights from the project's CLAUDE.md, .claude/rules/ directory and codebase, packaging them as reusable Claude Code rules, and creating the PR. Rules are files stored in .claude/rules/, and unlike skills, they do not require frontmatter. RULE.md serves as the main rule body, while detailed documentation (<rule-name>.md / <rule-name>.ja.md) is placed directly under the rules/ directory. Use when the user requests: "Register insights as rules", "contribute rule", "Share this rule", "Register as a rule", "Compile rules into a PR", "Turn this convention into a rule", "Turn best practices into rules". gh CLI and git must be installed.
Monitor background processes from Claude Code using sentinel files, heartbeat liveness, and subagent polling. Best practices and anti-patterns for autonomous loops that need to kick off work, detect completion/failure/hang/timeout, and resume the main context without wasting tokens. TRIGGERS - monitor background process, sentinel file, heartbeat monitoring, process supervision, agentic loop monitor, background task health, detect hung process, poll for completion, watchdog pattern, process liveness, monitor long-running task, agent poll loop, circuit breaker pattern.
Run Codex code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Task-based multi-agent coordination (includes Issue Remediation Loop)
Execution plan generation and management — Plan lifecycle as repository artifact