Skills & Agent Building
5,949 results
- ResearchehnruizInvestigate a question against primary sources and capture the findings as one cited Markdown note. Use when the user wants a topic researched, a vendor's docs or API facts gathered, a library's or tool's real behavior confirmed, or reading legwork delegated while the main session keeps working.
- ResearchergasseraneResearcher — Evidence Synthesis Specialist. Use when a complex MEL/SRHR task requires deep evidence synthesis before planning begins. Triggered by Ann between PHASE 1 and PHASE 2 for COMPLEX tasks. For a standalone rapid evidence assessment or lighter literature review, use /evidence-synthesis; reserve this skill for the deep COMPLEX-tier Evidence Brief Ane invokes directly when she needs that…
- Resume From DiskStepenkoAnatoliResumes a Fetchproof project after an interruption - a reset sandbox, a cut turn, a new agent - by reading where it stands from disk (doctor, handoff, preflight, git status, the last commit report, docs/ARCHITECTURE.md) instead of starting over and paying for collected pages twice.
- Ruby AntipatternsemgiezetForbidden Ruby/Rails patterns — eval with user input, YAML.load, mass assignment without permit, shell injection. Applies when editing Ruby files.
- Run Tarot ReadingwhoamimiRuns an interactive tarot reading in which the user picks their own cards from a shuffled 78-card deck, then gives a woven interpretation, for three-card spreads, single daily pulls, clarifiers and larger spreads. Use when the user mentions tarot, asks to draw or pull cards, or asks an open reflective question in a divination-flavoured way, even without saying "tarot".
- Rust AntipatternsemgiezetForbidden Rust patterns — unsafe without safety comment, unwrap in library code, unchecked integer arithmetic. Applies when editing Rust files.
- Self Improving Agentgrail-computerMeta-skill for making the agent self-improving. Covers updating AGENTS.md, creating new skills from repeated workflows, and deciding what to systematize. Invoke after completing tasks, when noticing repeated friction, or at session end.
- Skill Autox-mckayAutonomous skill development workflow - create, evaluate, and improve skills automatically until quality goals are met
- Skill RouterStepenkoAnatoliPicks which skill to use next from facts on disk - this machine's role (doctor), whether the corpus arrived (handoff), the research gate (preflight) and the brief - and never sends a builder to a skill that collects evidence.
- Skills LibrarylindblomstefanGet guided AI skill recommendations for your repo or team.
- Source IntelligenceNightVision SecurityGuide for agents to help users extract OpenAPI specs from source code using NightVision Source Intelligence. Use when running openapi extract (also spelled swagger extract), identifying framework support, troubleshooting extraction, handling unresolved variables, comparing API specs, or understanding Code Traceback.
- SuggestjohntrandallPropose edits to a note as tracked suggestions the human reviews in Obsidian's Track Changes panel: each change a signed suggestion with a short reason, never a direct edit.
- SupervisorehnruizRoute a multi-step task across cheaper subagents while the main session keeps the plan, the judgment calls and the verification. Use at the start of any task with more than one step, before spawning a subagent, when picking a model for a subtask, when a subagent fails, or when the user mentions cost, tokens or model choice.
- Task BriefZazaGdevUse every time the manager hands a task to a project lead. Turns the user's rough, often voice-dictated request into a short task brief that adds missing facts, never invented requirements, and marks every guess. Do not send a TASK message without it, except in a model comparison, which uses the compare-models skill instead.
- Task RouteremgiezetMaintain a project's instruction hierarchy — a small CLAUDE.md routing table plus task-scoped playbooks and path-scoped rules — so agents load only what the task needs. Use when a CLAUDE.md has grown too large, agents ignore or contradict instructions, token cost per task is rising, or when adding a playbook, rule file, or router row to a project.
- Tavs SetupcstelmachTAVS setup, configuration, and profile management assistant. Three workflows: (1) Interactive setup wizard for first-time configuration — detects terminal and agent, asks targeted questions, applies settings. (2) Targeted config changes — modify individual settings with backup, preview, and verification. Supports both CLI aliases and raw variables.
- Team Ceo ViewplasmindsUse when a team-* skill (team-refactor, team-council, team-council-plan, team-kickoff, team-review) reaches a CEO gate and the human must approve, decline, or choose between options. Also when the user asks for a visual, HTML, or browser view of a decision, backlog, or plan, or wants to share a team-review gate with the owner of the branch it reviewed.
- Team Council PlanplasmindsUse when a council decision is recorded under `.council/decisions/` and the next step is planning how to carry it out, or when the user asks to plan the council's decision. Not for planning work the council never decided.
- Team ProtocolplasmindsUse when running any team-* skill (team-council, team-council-plan, team-kickoff, team-refactor, team-review) — dispatching its role agents, settling what they disagree on, or handing off at a CEO gate.
- Tech Talk OutlinesamberTurns an accepted conference talk abstract into a rehearsable outline - the one-sentence takeaway, a narrative arc, a minute-by-minute time budget, demo placement, and a slide skeleton with cut checkpoints.
- Ticket DigestehnruizTurn a batch of tickets created or updated in a time window into one short, paste-ready message, one line per ticket, flagging the ones that need a decision. Use when the user asks what they filed today or this week, wants a recap or roundup for a product owner or team channel, or after filing three or more tickets in one sitting.
- Ticket TrimehnruizShorten an existing ticket that is too long or too technical, moving the engineering detail into a Technical notes comment so nothing is lost. Use when the user gives a ticket key or link and asks to trim, condense, simplify or clean it up, or says a product owner or analyst found it hard to read.
- UvPovertyActionThis skill should be used when working with Python projects that use uv for package and project management. Use this skill for running Python scripts and CLI tools with `uv run`, managing dependencies, creating projects, handling virtual environments, and executing commands within isolated project environments. Essential for projects with pyproject.toml files.
- Valuehugmouseskill does absolutely nothing, as well as the agent that uses it.