Teams lose time when prior decisions and fixes are buried in old chats. This skill searches archived conversations and returns concise, sourced guidance.

AI agents need a structured way to find services, post work, and manage paid delivery. ClawLabor provides marketplace workflows for discovery, escrow-backed orders, tasks, events, and account operations.

Generic AI edits often flatten voice and add unsupported polish. Dittobot rewrites user-provided text while preserving facts, stance, rhythm, and constraints.

Artist files can become inconsistent across context, songs, and releases. This skill organizes and updates one existing artist workspace using defined source-of-truth files.

A missing workspace can make an active artist roster appear empty. This skill checks local identity files and uses live Recoup roster discovery when needed.

Manual artist onboarding leaves roster records and workspace files incomplete. This skill creates the artist, matches Spotify data, researches profiles, and scaffolds catalog documents.

Shell-built email payloads can break quoting and deliver empty messages. This helper validates content, serializes it safely, previews requests, and reports delivery failures.

Label knowledge, roster data, and recurring work often become fragmented across tools. This skill builds a structured workspace connected to Recoup workflows.

Recoup data and connected services require precise authentication, identifiers, and endpoint schemas. This skill guides reliable retrieval and approved external actions.

Teams need polished documents that reviewers can open and comment on. This skill helps Claude, Codex, and Claude Code publish p11 review links.

Reviewer comments can be hard to turn into a clean published revision. This skill finds the p11 target, applies clear decisions, and shares a new version.

Review threads can stall when questions, unclear requests, or conflicting comments lack an answer. This skill inspects visible p11 comments and posts concise replies through the p11 CLI.

Publishing a skill across agent marketplaces requires consistent metadata, clean source links, and platform-specific steps. This skill guides safe packaging, uGig publishing, sh1pt promotion, and follow-up marketplace submissions.

Manual LinkedIn Easy Apply searches can be repetitive and inconsistent. This skill guides agents through a controlled Puppeteer workflow with filters, resume checks, and skip rules.

Dice Easy Apply runs can be repetitive and error-prone when resumes, filters, and skip rules are managed manually. This skill provides a guarded workflow for remote searches, verified uploads, dry runs, and concise application reports.

Research tasks need current sources and clean page text. This skill routes Claude, Codex, and Claude Code requests through Tavily and Exa using the belt CLI.

Finding current web information can be slow when an assistant has no search path. This skill sends queries to Qryma and returns structured or readable results.

Creating a useful Agent Skill requires clear scope, discoverable descriptions, and valid structure. This skill guides authors through SKILL.md, examples, testing, and troubleshooting.

PyTorch docstrings require precise reStructuredText, tensor notation, and project conventions. This skill guides consistent signatures, arguments, cross-references, formulas, warnings, and examples.

Legacy PyTorch dispatch macros require careful argument and type-group changes. This skill converts them to AT_DISPATCH_V2 with the required include, wrappers, and explicit types.