Afegits recentment
Els últims skills afegits al catàleg. Descobreix les novetats!
agonara-api-access
igor1309
Connect any agent to an Agonara instance over its HTTP API — health check, password login and the agonara_session cookie, whoami, the X-Agonara-CSRF token and idempotency keys for safe mutations, and reading the accepted/rejected/fault envelope. Use when an agent needs to authenticate to Agonara, hold a session, send a state-changing request, or interpret an Agonara API response. The shared foundation every Agonara role skill builds on.
agonara-admin
igor1309
"Operate an Agonara private instance as an Admin through its HTTP API: bootstrap the first Admin, create and disable identities, bind local-password credentials, grant or revoke instance Admin authority while preserving the last-admin invariant, inspect operational access and audit events, and perform exceptional program-membership recovery or revocation. Use when an agent is doing instance administration, identity/credential administration, Admin authority transfer, access diagnosis, or recovery-level membership operations. Admin is not curation or learning and does not grant program participation."
agonara-coach
igor1309
Tutor a student against an Agonara instance — the explanation/tutoring front of the student assistant. Explain a concept at the depth the student asks for, take it deeper on request, diagnose why a weak area is weak from the evidence behind it before re-teaching, teach prerequisites first when the base is shaky, and teach the discriminating feature of confusable concepts. Grounds every explanation in accepted materials, never in your own knowledge unstated. Owns explanation craft only; the API reads, the assessment-integrity boundary, and the MCQ item-quality bar stay with agonara-student, practice with the drill skills. Use when the task is to tutor — explain or help a student understand a topic — rather than to take a check or do API work.
triage
agbossjs
Conveyor stage 1 → status Triage. Takes a requirement (or an existing issue), clarifies its business side through quizzes — why, what it does, what it does NOT do, constraints, business acceptance criteria (AC1…) — and creates or updates GitHub issues, splitting into a parent with sub-issues when useful. Use whenever the user brings a new requirement, idea, request, bug report or an issue number/URL and wants it clarified, triaged, "заведи тикет", "разбери задачу" — before any technical spec or code.
spec-session
agbossjs
Conveyor stage 2 → status Backlog. For issues in Triage, decides the technical side through quizzes and writes into the issue a detailed spec, an implementation plan, acceptance criteria split into automated (tests) and manual (plain-language instructions for a human — where to go, what to do, what to see), test cases, wiki pages to update and dependencies. Use after triage, or whenever the user says "spec", "спека", "план имплементации", "распиши тикет", or wants issues ready for autonomous implementation.
implement
agbossjs
Conveyor stage 3 → status In progress, and Test after merge. Implements Backlog issues — in parallel where they are independent (git worktrees with sub-agents, or separate Claude Code on the web sessions), in dependency order otherwise — each as its own branch and PR into main with tests, green gate, self-review, Wiki update and a manual-test handoff. Never moves anything to Done. Use after spec-session, or when the user says "implement", "имплементируй", "запусти", "go", or names Backlog issues to build.
framework-review
agbossjs
Architecture review of the framework itself (DI, components, graph DSL, CLI) for extensibility and API quality in a world where code is written by agents, not by hand. Scores 17 axes, runs empirical probes (agent writes code, misconfiguration matrix, CLI contract, generators), verifies every finding, writes a report with an improvement proposal per finding and can file it as an epic. Use when the user asks for a framework / architecture / API / CLI review, "оцени архитектуру", "ревью фреймворка", or wants to compare against a previous review.
setup
jinwon-int
Install and configure the Telegram Skill Bot. Use when users ask to install, set up, or configure the bot. Supports multi-language installation guidance (English, Chinese, Japanese, Spanish, French, German). Handles system requirement checks, bot token collection, user whitelist configuration, proxy setup, virtual environment creation, dependency installation, and .env file generation.
typesafe-ai
jinwon-int
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.
gh-pr-flow
jinwon-int
Validate, independently review, and normally squash-merge protected GitHub pull requests. Use when a PR must pass exact-head, green-check, author/reviewer separation, or required-review gates; when a jinon86- or seoseo-ai-authored PR needs approval from the other relay-held account; or when landing changes without weakening branch protection.
ccc-wiki-record
jinwon-int
Record durable operating knowledge in the Seoyoon Family Wiki through the wiki-agent PR-first workflow. Use for decisions, runbooks, node facts, incidents, task memory, or operating-log entries that must survive the current session without storing raw secrets.
ccc-security-audit
jinwon-int
Run and interpret the read-only ccc-node security audit for permissions, execution policy, scanner integrity, redaction, spool/cache safety, and collected fleet evidence. Use when asked to audit security, check owner-only storage, inspect policy drift, or assess a node without making repairs.
ccc-node-status
jinwon-int
Inspect the current ccc-node source, serving bridge, provider readiness, workload, scheduler, and recent body-free diagnostics. Use for node status checks, bridge health questions, deployment preflight, or verifying that a node remained healthy after a scoped change.
ccc-doctor
jinwon-int
Diagnose ccc-node harness, provider, bridge, memory, and managed-asset drift with the provider-aware doctor. Use when the operator asks for a health check, doctor report, readiness diagnosis, drift classification, or a preview of repairable ccc-node configuration.
ccc-agent-cron
jinwon-int
Inspect, validate, preview, and safely manage ccc-node agent-cron task definitions and execution boundaries. Use when the operator asks about scheduled agent work, due tasks, locks, retries, adding or changing a task, or previewing a scheduler tick.
wiki-record
jinwon-int
Use when you need to durably record a decision, runbook, node fact, incident, or operating-log entry in the Seoyoon Family Wiki. PR-first flow (wiki-agent write-path -> edit in the worktree -> wiki-agent pr); handles TM-/ND-/LOG- section IDs, the worktree path, and the no-raw-secrets rule.
staleness-threshold-empirical-calibration
jinwon-int
Choose a threshold for a staleness/freshness check so it neither sits dead nor invents a signal — confirm what the metric actually measures, use the corpus distribution to detect dead thresholds, and derive the number itself from the governing convention or policy. Use when adding a check like "flag if unchanged for >N days", when an existing freshness check never fires, or when a reviewer asks why N was chosen.
skillsuggest
jinwon-int
Use when asked to find automatable routines, improve an existing skill, review skill candidates, or list and roll back autosave-installed skills. Detects repeated procedures, reviews create/patch/support-file skill proposals (human-in-the-loop), and audits autosave auto-mode changes.
self-update
jinwon-int
Use when asked to update/upgrade this node's ccc-node harness (~/.claude) to GitHub latest or check harness drift across the fleet. Read-only drift check and diff; applying needs explicit OK, backs up, runs setup.sh, validates, rolls back on failure. Not for the bridge (bridge/start.sh --upgrade).
schema-change-mixed-data-validation
jinwon-int
Validate data integrity across a schema change (added/removed/retyped fields) by pinning the changeover point from the source commit, segmenting records before and after it, and running a read-only field-presence checklist — so a field missing merely because a row predates the change is never misread as a failure. Use when analyzing logs, audit records, or tables that span a format change.
Check Kafka Topics
OmniNode-ai
Kafka topic existence, partition counts, and wildcard pattern matching
Check Infrastructure
OmniNode-ai
Infrastructure component connectivity and health checks for Kafka, PostgreSQL, and Qdrant
Check Database Health
OmniNode-ai
PostgreSQL database health via omninode-runtime HTTP health endpoint
url-state
BerriAI
Read or write dashboard URL query state (tabs, filters, pagination, deep links, demo flags) with nuqs instead of raw history or URLSearchParams