Afegits recentment
Els últims skills afegits al catàleg. Descobreix les novetats!
beancount-close
bex-co
Close an accounting period in a local Beancount ledger by reconciling each active account through beancount-reconcile, checking assertions and recurring gaps, reviewing flags, then proposing a commit with the period reports. Use for month-end close or wrapping up the books. Surface incomplete work and require a passing check before a confirmed commit; never push. Skip closing a single account (a close directive; beancount-add) and ledgers hosted on Beancount.io.
beancount-ask
bex-co
Answer explicit requests for facts from a local Beancount ledger using shown, reproducible bea queries and reports for spending, trends, net worth, holdings, subscriptions and anomalies. Do not select this skill merely to gather preliminary inputs for buy/sell decisions or tax recommendations, even if ledger facts could help. Strictly read-only; figures come from executed queries. Skip ledgers hosted on Beancount.io, recording transactions (beancount-add), reconciliation, migration, ledger edits, option pricing or greeks, investment or tax advice, and general Beancount, BQL, or bea documentation questions (including what bea ask does).
beancount-add
bex-co
Record one-off entries the user describes in a local Beancount ledger through bea — a purchase, bill, paycheck, or transfer between their own accounts (including splits and pasted receipt text), opening or closing an account, a price, or a note. Propose the exact entries from existing accounts, check whether one is already recorded, and write only after confirmation with a passing check; it never changes existing entries. Skip bank or card export files (beancount-import), statements (beancount-reconcile), finance-app migrations, options trades (beancount-options), investment trades, dividends, splits, and vests (beancount-trade), month-end close, edits to existing entries, and ledgers hosted on Beancount.io.
beancount-accruals
bex-co
Prepare supported accrual and reversal drafts for a period from an explicitly stated schedule — basis, service interval, day-count, recognized-to-date, already-booked, required adjustment — posted only through the suite's propose/confirm/check flow with stable schedule identity. Skip recording one-off entries the user describes (beancount-add), explaining how a balance moved (beancount-roll-forward), tax or depreciation advice, automatic reversals, and ledgers hosted on Beancount.io.
elara
PIIIX-org
Connects AI agents to Elara — an open-source, self-hostable second brain and AI-navigable knowledge graph platform with synced code repositories. Use whenever interacting with Elara vaults, notes, knowledge graphs, codebase mappings, or when navigating projects via Elara MCP tools.
chapters
PIIIX-org
Connects AI agents to Chapters (now Elara) — an open-source, self-hostable second brain and AI-navigable knowledge graph platform with synced code repositories. Backward-compatibility proxy for the Elara skill.
anti-ui-slop
davepoon
Stop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Codex, Claude Code, Cursor, Copilot, and other coding agents.
ai-search-visibility-audit
davepoon
"Audit whether a website can be found, crawled, and cited by AI answer engines such as ChatGPT Search, Perplexity, Google AI Overviews, and Microsoft Copilot. Use when someone asks why their brand is missing from AI answers, whether AI crawlers can read their site, how to get cited by ChatGPT or Perplexity, or asks for a GEO or AEO (generative / answer engine optimization) review. Produces a citation baseline across buyer-intent prompts, a crawler-access check, a citability review of named pages, and a ranked fix list. Not for keyword rank tracking, paid search, or pages behind a login."
agentwhy-session-audit
davepoon
Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.
agenttrace-session-audit
davepoon
Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.
agent-memory-discipline
davepoon
"Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service."
agent-analytics
davepoon
"Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track."
ad-angle-research
davepoon
Pull the ads a competitor is running right now on Meta (Facebook/Instagram) and Google, then extract the hooks, offers, CTAs and landing pages worth modelling. Use when writing ad copy, planning creative tests, choosing a landing page angle, or when the user asks "what is X advertising", "what ads does X run", "find competitor ad hooks". Reads live Ad Library and Ads Transparency data through the Tracetify MCP; falls back to a manual Ad Library walkthrough when the connector is absent.
work-pipeline
davepoon
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
sdd-pipeline references
davepoon
references/work-activity-log.md Activity Log 규칙
qa-find-bugs-mobile
bex-co
Hunt bugs in the running Beancount mobile app using local Expo MCP on the iPhone 17e simulator, sign in with QA_EMAIL and QA_PASSWORD, reproduce failures, trace root causes, and deduplicate findings. Use for native mobile QA. Skip browser-only dashboard QA, ordinary code review, and store releases.
beancount-roll-forward
bex-co
Explain how one balance-sheet account moved over a period — opening balance, each signed movement, closing balance — with shown, reproducible bea queries for prepaid, loan, and brokerage accounts. Strictly read-only; the closing is computed independently and any gap is reported, never plugged. Skip ledgers hosted on Beancount.io, recording entries (beancount-add), explanations of one transaction (beancount-ask), reconciliation against a statement (beancount-reconcile), investment or tax advice, and general Beancount or BQL questions.
beancount-init
bex-co
Scaffold a new local Beancount ledger with bea init and validation, with optional Fava browser setup when requested. Use for setting up a new ledger or initializing a bookkeeping repository. Skip importing history (beancount-migrate), bank exports, edits to a populated ledger, or ledgers hosted on Beancount.io.
apify-product-lookup
davepoon
"Fetch a real product's current price, stock, rating, or images from retailer pages over the Apify MCP server, and return them as typed fields rather than prose. Use when someone asks what a product costs right now, whether it is in stock, how it is rated, to compare a product across retailers, or to check a product URL they pasted. Also use when an agent would otherwise answer a product question from training data. Not for managing your own store's catalog, not for payments, and not for questions answerable without live retailer data."
open
davepoon
Boot the session, load context from the vault, and surface what matters
close
davepoon
Commit the session to durable vault memory and prepare a clean resume point
work-status
davepoon
Shows WORK progress and TASK status. Use when the user asks about WORK list, WORK progress, TASK status, or pipeline status (e.g., "WORK list", "WORK-01 progress", "show status").
uctm-init
davepoon
Initialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in .claude/settings.local.json. Use when the user says "uctm init", "initialize uctm", "uctm 초기화", or "초기화".
security-audit
davepoon
Deep security audit covering OWASP Top 10, authentication, authorization, data protection, dependency vulnerabilities, and secrets scanning. Delegates to the Centinela (QA) agent.