Menu
O SkillsMP coletou 29 skills de comisai/comis. Abra uma skill para revisar a origem e os detalhes.
Mostrando 29 de 29 skills coletadas.
Create new Comis skills, modify and improve existing skills, and validate them against the platform's manifest schema. Use this skill whenever the user wants to create a skill from scratch, turn a workflow into a reusable skill, update or fix an existing…
Idioma do texto original: inglês
MANDATORY: Conduct systematic, multi-angle web research before answering any request to understand or explain a topic properly, deeply, thoroughly, comprehensively, or beyond a short paragraph, even when general knowledge could produce an answer. Also use for…
Idioma do texto original: inglês
How to use the artifact-to-action tools (mcp:artifact-action-sim/*) to turn an artifact into a provenance-bound staged action, obtain exact authorization, commit once, and verify durable state.
Idioma do texto original: inglês
How to use the personal operations tools (mcp:personal-ops-sim/*) for an evidence-grounded daily review of inbox, calendar, tasks, decisions, drafts, and follow-ups.
Idioma do texto original: inglês
Use when a task is more than a single step — a read/research fan-out, spawning sub-agents, running a DAG, scheduling your own work, or messaging your channel. Teaches when to route work through `orchestrate(script)`, how to fan out with capability…
Idioma do texto original: inglês
Drive the Claude Code CLI interactively in a terminal session to build, fix, or extend software — launch it in a NAMED project folder, give it the task, handle its interactive prompts via keystrokes, detect completion, and verify the result. Use whenever the…
Idioma do texto original: inglês
Drive the OpenAI Codex CLI interactively in a terminal session to build, fix, or extend software — launch it in a NAMED project folder, give it the task, detect completion, and verify. Use this when the user explicitly wants to use Codex (the OpenAI coding…
Idioma do texto original: inglês
Implement a design document end-to-end in a target repo by driving Claude Code through the GSD workflow — define a GSD milestone from the doc, then run /gsd-autonomous (TDD, skip-discuss) to build all phases unattended. Use when the operator hands you a…
Idioma do texto original: inglês
How to operate the threat-hunting console tools (mcp:th-sim/*) to triage a security alert and resolve an investigation. Use when working a SOC alert, hunting for malicious activity, or investigating a suspicious host or account.
Idioma do texto original: inglês
MANDATORY: For requests asking whether a skill or specialized capability exists, load this skill and run its catalog workflow before answering. This includes elliptical follow-ups such as 'find something that does' when the preceding turn names the task. Do…
Idioma do texto original: inglês
Generate data visualizations and charts from user data. Supports 26 chart types including line, bar, pie, scatter, treemap, sankey, radar, funnel, maps, org charts, mind maps, network graphs, and more. Use this skill whenever the user wants to visualize data,…
Idioma do texto original: inglês
Generate images using structured prompts and optional reference images. Supports character design, scenes, product visualization, and any visual content creation. Use this skill when the user requests to generate, create, imagine, draw, or visualize images,…
Idioma do texto original: inglês
Investigate and troubleshoot daemon logs at ~/.comis/logs/. Covers NDJSON log format, Pino level codes, field dictionary, and staged analysis strategies for efficient troubleshooting of large log files. Use this skill whenever the user asks about logs,…
Idioma do texto original: inglês
Convert text content into two-host conversational podcast audio. Transforms articles, reports, documentation, or any written content into natural dialogue between male and female hosts, then synthesizes speech audio. Use this skill when the user requests to…
Idioma do texto original: inglês
Generate videos using structured prompts and optional reference images. Supports scene generation with camera, dialogue, and audio specifications. Use this skill when the user requests to generate, create, or produce videos, clips, animations, or motion…
Idioma do texto original: inglês
How to operate the package-delivery tools (mcp:depot-sim/*) to deliver a package to someone in an office building. Use when asked to deliver a package, find a person's office, or navigate a building to drop something off.
Idioma do texto original: inglês
How to operate the ICU clinical decision-support tools (mcp:icu-sim/*) to assess one ICU patient and finalize a diagnosis. Use when supporting an ICU team at the bedside, building a differential, or deciding on a working/final diagnosis for a critically ill…
Idioma do texto original: inglês
How to operate the autonomous research-lab bench tools (mcp:lab-sim/*) to run a research campaign on simulated robotics toward a target. Use when designing or queuing lab experiments, optimizing an assay, or running protocols on the simulated bench.
Idioma do texto original: inglês
How to operate the wildland-fire incident-command tools (mcp:fire-sim/*) to size up a fire, set a suppression plan, assign resources, and bring the incident to containment. Use when acting as planning chief / incident commander on a wildland fire.
Idioma do texto original: inglês
How to operate the AML investigation console tools (mcp:aml-sim/*) to triage a financial-crime referral and resolve a case. Use when working an anti-money-laundering alert, investigating suspicious transactions, or deciding whether to file a SAR.
Idioma do texto original: inglês
How to operate the content-moderation console tools (mcp:mod-sim/*) to work a trust & safety queue and resolve each item. Use when moderating reported content, reviewing a report queue, or deciding whether an item violates policy.
Idioma do texto original: inglês
How to operate the contract-negotiation desk tools (mcp:nego-sim/*) to negotiate a commercial contract with a counterparty and close on the best terms you can. Use when negotiating a deal, countering an offer, or deciding whether to accept, counter, or walk…
Idioma do texto original: inglês
How to operate the customer-success portfolio console tools (mcp:cs-sim/*) to run a quarterly review of an account portfolio — assessing churn risk, proposing plays, and forecasting renewals. Use when reviewing a book of accounts, deciding which accounts are…
Idioma do texto original: inglês
How to operate the balancing-authority operator console (mcp:grid-sim/*) to keep a control area's generation and load in balance across a dispatch interval. Use when running a power grid control area, balancing generation against load, managing reserves, or…
Idioma do texto original: inglês
How to operate the relief-logistics coordination tools (mcp:relief-sim/*) to route relief supplies across a crisis and confirm aid reaches the affected people. Use when coordinating a disaster response, dispatching convoys, or allocating relief supplies.
Idioma do texto original: inglês
How to operate the algorithmic market-making desk tools (mcp:mm-sim/*) to run a trading book through an episode and settle it for a graded result. Use when making markets, quoting two-sided prices, managing trading inventory, or running a market-making…
Idioma do texto original: inglês
How to operate the precision-apiary console tools (mcp:apiary-sim/*) to manage a bee yard through one season — inspecting hives, reading the forage and honey-flow, and acting (treat, place, harvest) up to closing the season. Use when managing an apiary,…
Idioma do texto original: inglês
How to operate the adaptive tutoring console tools (mcp:tutor-sim/*) to diagnose one student's misconception, remediate it, and confirm mastery. Use when tutoring a single student, diagnosing a learning gap, or running a 1:1 remediation session.
Idioma do texto original: inglês
Stub for tests
Idioma do texto original: inglês