custom-workflow
Observe repeated workflows, compose existing skills, write new skills, record project memory, and build reusable agents for the team.
Before you start
Choose your system and agent, then run the command in your terminal. After installation, send the prompts below to your agent.
curl -sSL https://paperskills.com/scripts/paperskills-install.sh | bash -s -- \
--tool codex \
--skills sa.autoskill,cs.customize,cs.skill-creator,air.research-manager,cs.learn \
--registry https://paperskills.com/api/registryStep 1 · sa.autoskill
Task for your agent
Use autoskill or manual review to summarize the last five similar tasks: triggers, inputs, judgment rules, deliverables, and existing skill coverage.Expected outputs
Step 2 · cs.skill-creator
Task for your agent
Use skill-creator to write a new SKILL.md for gaps, or compose multiple existing skills into a recipe with test examples.Expected outputs
Step 3 · air.research-manager
Task for your agent
Use research-manager at session close to record decisions, experiments, failed paths, and key evidence so new teammates can pick up the project context.Expected outputs
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
View skillCreate, configure, and maintain custom agent profiles and author new skills via the `repl` tool. Use when the user wants to create an agent profile, build a custom agent, modify agent capabilities, attach or detach skills/connectors on a profile, author a skill, or inspect which connectors and tools are available. Also use whenever you need the `host.agents.*` or `host.skills.*` Python SDK.
View skillCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
View skillRecords research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
View skillUse this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: - Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") - Terse concept names implying "help me understand this": "Galois theory," "transformers, from scratch" - Confusion signals: "won't stick," "keep mixing these up," "not getting it" - Learning-path questions: prerequisites, sequencing, what to study before X - Conceptual questions about mechanisms, causes, or dynamics Don't trigger for: - Tasks: coding, writing, calculation, translation, factual lookup, news updates - Personal troubleshooting; resource/textbook recommendations - Claude's evaluative verdict: opinion prompts ("do you think X", "settle this", "honest take", "is X dead / still taken seriously") and interpretive takes ("was X really as harsh as people say")
View skill