146 skills · sorted by relevance
Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.
The English summary is being prepared. Showing the original description.
Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a harness repair improved later outcomes. Do not use for code-only audits, AGENTS-only audits, individual skill reliability reviews, or executing the task itself.
The English summary is being prepared. Showing the original description.
Audit and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions. Use when the user asks to diagnose conflicting instructions, excessive approval pauses, broad skill triggers, duplicate guidance, or broken instruction references, or to clean up that instruction set. Ordinary code review, Markdown editing, or application debugging alone does not trigger this workflow. Inspection stays read-only; apply changes when authorized.
The English summary is being prepared. Showing the original description.
Apply Andrej Karpathy-inspired coding-agent guidelines in Codex. Use when writing, reviewing, debugging, or refactoring code to surface assumptions, avoid overengineering, keep edits surgical, and define verifiable success criteria.
The English summary is being prepared. Showing the original description.
Mine AI coding-agent session transcripts into structured, gate-validated GPU-kernel optimization records for the wiki. Use when asked to turn vibe-coding sessions, Codex rollout logs, or Claude Code project transcripts into wiki records; to summarise what a kernel-optimization session achieved; to build or extend a session-trace store; or to re-run and validate one. Also use when asked how a session-derived record's number, snippet, or provenance was established.
The English summary is being prepared. Showing the original description.
Use when mining coding-agent session history, archived transcripts, memories, or repeated local work to discover recurring workflows that should become new Agent Skills.
The English summary is being prepared. Showing the original description.
Converts repeated AI coding-agent workflows into reusable skill packages with triggers, guardrails, examples, and verification checks. Use when a user wants to turn a prompt, checklist, AGENTS.md section, Claude/Codex workflow, or recurring agent task into a portable SKILL.md.
The English summary is being prepared. Showing the original description.
Use when acting as a project manager that delegates tasks to other coding-agent sessions (Claude Code, Codex, or Pi) - launch workers, assign them work, monitor progress, review their tool calls, and collect results
The English summary is being prepared. Showing the original description.
Designs provider runtimes for coding agents. Use when modeling model abstraction, streaming semantics, tool-call normalization, retries, or fallback routing.
The English summary is being prepared. Showing the original description.
Designs approval and sandbox policy for local coding agents: permission modes, isolation, network and destructive-command guards. Use when setting approvals. Not cloud sandboxes.
The English summary is being prepared. Showing the original description.
A digest of a week or more of the user's own coding-agent sessions (default 7 days): sessions per day and project, most-edited files and the lessons Cognee learned, written up as shipped, decided and still open.
The English summary is being prepared. Showing the original description.
A multi-day digest of the user's own coding-agent sessions — sessions per day and project, most-edited files, and every lesson Cognee distilled into the knowledge graph in that window. Use only when the user explicitly asks for a weekly digest, a retro, a recap or report of their recent sessions, or asks for the `cognee-digest` skill by name. Not for questions about code or the current task.
The English summary is being prepared. Showing the original description.
A standup or status update built from the coding-agent sessions Cognee recorded — prompts, tool calls, edited files, what was left open — per project. Use only when the user explicitly asks for a standup, a status update, a catch-up on their own recent sessions ("what did I work on yesterday / this week"), or asks for the `cognee-standup` skill by name. Not for questions about code, files or the current task.
The English summary is being prepared. Showing the original description.
A dated chronology of one topic across the user's recorded coding-agent sessions — the lessons the graph learned about it and the prompts that named it, oldest first. Use only when the user explicitly asks for the history or timeline of a topic across their sessions ("how did X evolve", "when did we first discuss X") or asks for the `cognee-timeline` skill by name. Not for questions about code or the current task.
The English summary is being prepared. Showing the original description.
A dated chronology of one topic across the user's recorded coding-agent sessions, oldest first: the lessons the graph learned about it and the prompts that named it. Default last 30 days; also all time or a date.
The English summary is being prepared. Showing the original description.
A standup or status update on the user's own recent work, from the coding-agent sessions Cognee recorded (prompts, edited files, what was left open) per project. Default last 24h; also today, yesterday, 48h or a date.
The English summary is being prepared. Showing the original description.
Authoritative reference for Pi (@earendil-works/pi-coding-agent): install, configure, run, and extend it. Use for the CLI and configuration, providers and models, extensions, skills, MCP, codemode, the SDK/RPC, security and trust, design philosophy, and the pi repository's internals and contribution rules.
The English summary is being prepared. Showing the original description.
Make AI coding-agent messages to humans clear and easy to follow. Use for every user-facing message in this repository, or when the user asks to simplify or rewrite an agent message.
The English summary is being prepared. Showing the original description.
Make AI coding-agent messages to humans clear and easy to follow. Use for every user-facing update, explanation, review, question, and handoff in this repository, or when the user asks to simplify or rewrite an agent message.
The English summary is being prepared. Showing the original description.
Run CodeBurn locally or as an MCP server so agents can inspect token usage, cost, model mix, project spend, and budget waste across coding tools.
The English summary is being prepared. Showing the original description.
Author, validate, test, and troubleshoot Copilot Studio agents through YAML-driven commands instead of clicking through the product UI.
The English summary is being prepared. Showing the original description.
Use when a coding-agent session store is added or its format drifts, to document its layout, roles, quirks. Not for recalling a session: use history-recall. Not for peer transfer: use history-sync.
The English summary is being prepared. Showing the original description.
Prompt engineering and task-specification skill for improving prompts, agent instructions, system messages, evaluation prompts, coding-agent tasks, multi-step workflows, and LLM output reliability. Use when rewriting vague prompts, adding constraints, reducing ambiguity, improving safety, creating reusable prompt templates, or converting goals into actionable agent instructions.
The English summary is being prepared. Showing the original description.
Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.
The English summary is being prepared. Showing the original description.