377 skills · sorted by relevance
Create external Paperclip plugins using command-line tools. Scaffold a package, install it into a local Paperclip instance, rebuild as you edit, and check types, tests, and builds before reporting the plugin’s status.
Create Paperclip tasks, add progress comments, update statuses, and list assignments from Hermes. A helper uses API credentials with restricted permissions to keep task creation and updates within approved work boundaries.
Track pull requests opened by a Paperclip instance, explain their purpose, and assess whether their latest changes are ready to merge. Dispatch preparation work for unresolved problems and publish an evidence-based report without merging anything.
Prepare Paperclip changes for a pull request by organizing commits, updating the branch, writing the description, addressing automated review feedback, and checking tests and CI before reporting the result for handoff.
Use an assigned Slack bot to read shared conversations, search accessible discussions, summarize with source links, and send messages or files. It connects Slack collaboration with Paperclip tasks and routines while respecting channel access and delivery status.
Manage an AI-agent company in Paperclip through conversation. Set up the company, hire and configure agents, handle approvals, track tasks and spending, and review work products, with summaries and links to the relevant web pages.
Build or modify adapters that connect Paperclip to AI agent runtimes. Covers server execution, configuration forms, terminal output, session persistence, and environment checks for CLI agents, HTTP endpoints, and custom processes.
Prepare and submit requests to add agents in Paperclip. Check hiring permissions, compare existing configurations, and define the role, instructions, reporting line, and runtime settings, then handle approval and follow-up for linked tasks.
Turn bundled Paperclip issues, comments, and documents into readable wiki updates covering project purpose, current progress, decisions, risks, and next actions, while preserving existing knowledge and citing the supporting activity.
Select, inspect, validate, and report Paperclip evaluations for Runner protocol behavior or complete product workflows. Interpret results with evidence, source revisions, costs, and failure categories, and refresh reports from retained evidence without new provider calls.
Start and repair isolated Paperclip development workspaces through managed services. Restore a full database clone when needed, then verify login, populated data, health, service visibility, and whether the process using the port belongs to the intended workspace.
Research MCP connections, which let agents use external tools, and vendor integrations for Paperclip. Produce an evidence-backed planning pull request, obtain human approval for its exact revision, then implement and verify each approved connection separately.
Build and update Paperclip interfaces using shared rules for colors, typography, status indicators, layouts, and interactions. Reuse existing components and keep the component catalog and showcase page aligned with new or changed interface elements.
Turn an idea, post, or task into a skill for the Paperclip catalog. Search for existing skills first, then reference, adapt, or author one, add worked examples where applicable, validate the catalog, and prepare a pull request.
Create, implement, or review Paperclip capsule visuals that represent agents and their status. Apply the rules for each visual type, document settings for reproducible assets, and provide static alternatives for animated effects.
Write or revise a Paperclip plan that states the intended outcome, constraints, approach, and success checks. Capture unresolved decisions, maintain the saved plan, and request approval when the work requires it.
Tidy a Paperclip Mine inbox by scanning entries and grouping archive candidates by work status and inactivity. Present checkbox confirmations, then archive only accepted selections, with undo details and no changes to the underlying tasks, branches, or workspaces.
Coordinate bounded test runs for one Terminal-Bench task through Paperclip. Record evidence, diagnose failures, and manage approval for product fixes while keeping reruns in the same isolated working copy.
Coordinate a complete Paperclip release, from candidate verification and canary testing to stable npm publication and GitHub Release creation. Track release notes, Docker smoke tests, announcement follow-up, and linked content cases when Cases are enabled.
Guide a first task in Paperclip by clarifying goals, constraints, and completion criteria. Prepare a plan or one task proposal, then wait for approval before creating execution tasks or carrying out the agreed work.
Coordinate Paperclip vulnerability response from confidential report review and private fixes to local testing, CVE identifier requests, advisory publication, and immediate security releases, with human assistance for reporter communication.
Guide development of new interaction cards in Paperclip issue threads, such as approvals or structured questions. Covers shared data definitions, server behavior, interface states, CLI and MCP support, plugin helpers, documentation, and tests.
Review stalled, blocked, or pending-review issues in Paperclip and choose one concrete next action for each. Clarify ownership and status, then resume work, reassign it, resolve blockers, request a decision, or close the issue.
Turn an authorized plan into Paperclip work by deciding which tasks need separate owners, defining clear deliverables, and recording real dependencies so independent work can start and dependent work waits.