learn
Extract actionable learnings from this conversation and persist them where they will be found again.
library
Private skill distribution system. Use when the user wants to install, use, add, push, sync, list, or search for skills, agents, or prompts from the shared library catalog. Triggers on /library commands or mentions of library, skill distribution, or agentic management.
mcp-to-skill
Convert any MCP server into a Claude Skill with 90% context savings. Use this skill when converting an MCP server to a skill to reduce context usage and improve performance.
motonet
>-
nano-banana-image
>
netrauta
>-
pandoc-typst-pdf
>-
pdf-to-markdown
Convert a PDF book or document into clean, structured Markdown files split by chapter/section, with embedded images. Uses the Gemini Files API for high-quality conversion. Handles hyphenation repair, page-break paragraph joining, and blockquote formatting.
pi-session-logs
Search and analyze Pi agent session logs stored as JSONL files under ~/.pi/agent/sessions/, and query CCM (Claude Code Mux) proxy logs via journalctl. Use when investigating what Pi did in a past session, why a build or tool call failed, how Pi used interactive_shell, what CCM routed and at what latency, or reconstructing a full session transcript. Covers searching by text, timeline inspection, tool-call auditing, and correlating Pi session timestamps with CCM routing decisions.
power
>-
processing-scanned-receipts
Use when processing a batch of scanned receipt PDFs that need image extraction, OCR, structured plaintext generation, and descriptive renaming.
puuilo
>-
read-as-markdown
>-
secrets-scan
>-
sync-plugin-cache
>-
taloon
>-
tokmanni
>-
upstream-pr
>-
verkkokauppa
>-
youtube-frame-analysis
>
youtube-to-markdown
>-
YouTube Transcription
>-
zed-threads
Read and inspect Zed AI conversation threads stored in the local SQLite database. Use when the user asks to "show Zed threads", "read my Zed AI conversations", "inspect Zed chat history", "dump Zed thread", or wants to examine past Zed AI interactions.
asana
Manage Asana tasks and projects. Use when the user asks about "Asana tasks", "what's on my Asana board", "create an Asana task", "update Asana priority", "sync Asana", or any request to query, create, or modify tasks in Asana.
bauhaus
>-
browser-youtube-history
>-
claude-session-logs
Search and analyze Claude Code session logs stored as JSONL files under ~/.claude/. Use when investigating why an agent didn't reply, reconstructing what happened in a past session, finding a specific message across all sessions or agent histories, recalling when or how something was done previously, or diagnosing tool-call failures. Covers searching by text, timeline inspection, full transcript reconstruction, and tool-call auditing. For Pi agent sessions use pi-session-logs; when the ask spans "all sessions" or "all agents", use both.
commit-organizer
Organize a messy working tree into a series of cohesive conventional commits, ordered by modification time.
commit
Commit staged changes, or stage and commit each logical change from the conversation, with conventional commit messages.
context7
Fetch up-to-date library documentation using Context7. Use when the user asks to "fetch documentation from context7", "get library docs", "resolve a library ID", "use context7 MCP tools", or mentions context7 library documentation. Provides dynamic MCP tool invocation without loading all tool definitions into context.
opencode-marketplace
Reference guide for the opencode-marketplace CLI tool. Use this skill when users want to install, uninstall, update, list, or scan OpenCode plugins; manage plugin components (commands, agents, skills); work with plugin scopes (user/project); handle GitHub-based plugins; or need guidance on plugin structure and conventions.
dl-paper-code-blog
Craft long-form, Chinese blog posts that connect deep-learning papers with their code repositories using the auto-collected bundle (materials_manifest, paper_text, figures, repo_context, lsky cache). Use this skill whenever a user provides such a bundle and wants a TL;DR, method deep dive, experiment analysis, reproduction guide, and media assets.
lsky-uploader
Upload files to the self-hosted Lsky image bed (https://lsky.xueguo.us/api/v1), fetch the returned URLs/Markdown snippets, and manage albums or strategies via the REST API. Use this skill whenever you need to programmatically push screenshots/assets to Lsky and return shareable links inside Codex.
tox-paper-extractor
End-to-end OA literature pipeline for toxicity/peptide experimental data. Use to discover candidates (Europe PMC), download OA full text + supplementary (PDF/JATS XML/PMC OA packages), extract traceable raw records (tables/supp → raw_extractions.csv + raw_experimental_records.csv + extracted_tables), generate monitoring reports, and screen records for training readiness (units/aggregation/censoring).
bioinforw-data-plotting
Recommend and adapt scientific plotting templates from a local Bioinforw or NGplot catalog for research data visualization. Use when Codex needs to choose a chart type from `catalog_enriched.jsonl`, refresh `embedding_input.jsonl`, return top-k templates with Python/R code paths, map user columns to template-required columns, or turn a research plotting request into an executable plotting starting point.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
fly-sprites
Operate Fly.io Sprites with the `sprite` CLI. Use for Sprite lifecycle; remote commands, files, and package installation; exec sessions or wake-safe services; HTTP URLs and port forwarding; checkpoints and restores; or troubleshooting target selection, authentication, lifecycle, networking, and storage.
gob
Process manager for long-running background processes. Use when starting development servers, watching files, or running commands that need to continue in the background while agent continues working.
emacsclient
Use emacsclient to open files, inspect or debug a running Emacs, evaluate or reload Elisp, or manage windows.
herdr-subagents
Herdr subagent orchestration. Use when the user asks to delegate through Herdr for a read-only investigation or review, an implementation-and-review loop, or a sequential task queue.
martin-fowler-refactoring
Apply Martin Fowler's catalog to identify code smells and select systematic refactorings.
pair-programming
Human-navigated, agent-driven pair programming through small design increments and natural handoffs.
pi-sessions-duckdb
Inspect Pi session conversations and analyze session logs with DuckDB. Use when asked what happened in a session, to summarize or extract conversation fragments, to read user/assistant messages without tool traffic or thinking, to find debugging evidence, or to calculate session, message, and tool-use statistics from ~/.pi/agent/sessions/**.
safe-refactoring
Refactor code when the user wants behavior-preserving cleanup or raises a structural concern such as a large method, duplication, mixed responsibilities, awkward control flow, misplaced logic, or difficult naming—even when they are still exploring what to change. Use for extracting, moving, simplifying, reorganizing, renaming internals, and replacing implementations without changing behavior. Route behavior changes and bug fixes to test-driven-development; styling and declarative configuration use targeted verification instead.
story-splitting
Turn broad requirements, large stories, epics, features, initiatives, or backlog items into small end-to-end child stories without turning them into technical component tasks. Use when refining a backlog, decomposing epics, planning an MVP or walking skeleton, looking for vertical slices, reducing story size, applying SPIDR/Hamburger/capability slicing, avoiding scatter-gather/component stories, or deciding the first valuable story before implementation planning.
test-driven-development
Test-drive meaningful application-owned behavior when adding or changing domain rules, interactions, state transitions, authorization, calculations, persistence, API contracts, or fixing bugs—even when the user does not request TDD. Route behavior-preserving structural work to safe-refactoring. Styling, declarative metadata or configuration, generated code, dependency upgrades, mechanical wiring, and test-only maintenance fall outside this TDD process.
tidy-first-analysis
Command-only workflow for analyzing an intended code behavior change using Kent Beck's Tidy First principles and recommending small behavior-preserving tidyings before implementation. Use via /skill:tidy-first-analysis when comparing skill versus prompt-template approaches, or when explicitly asked to run a Tidy First analysis.
Architect
Architect or technical leader mode.
code-reviewer
Review code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.
commit-messager
Write clear and concise commit messages that accurately describe the changes made in the codebase
Page 1234 of 1665 · 83227 results