Finance
Personal finance, budgeting, financial tools
dialectic
by beingcognitive
Harden a plan/design/algorithm/decision via a thesis→antithesis→synthesis loop: each round, two independent reviewers (a different model + a freshly-spawned subagent) critique the current draft; fold in only findings the draft doesn't already resolve, adjudicating reviewer disagreements by evidence; stop after two consecutive clean rounds (cap 10, usually 3–5). Independence is the engine — a different model and an isolated perspective expose blind spots one model can't see in itself. Use when the user says "dialectic" or "정반합". NOT for trivial or no-real-tension changes.
pr-summary
by Hallmanac
Generate a pull-request title and description from the commits on the current branch. Primary use is a build session's own closing PR SUMMARY block, which the Hall9k daemon puts verbatim into the pull request it opens; the second use is replacing an already-open PR's body. A repo that ships its own PR-description rule wins for the prose. Output is text only; it never opens the PR.
INVOGUE COLLAB HQ — Cowork Setup & Deployment Guide
by invogueai
Campaign budget tracked in real-time, warning at 80%, blocked at 100%
beancount-accounting
by icealtria
This skill should be used when the user asks to "add a transaction", "create a beancount entry", "record an expense", "balance my accounts", "query my finances", "check account balances", "categorize spending", "write beancount", "edit .beancount files", "run a BQL query", "reconcile accounts", or mentions beancount, double-entry accounting, or ledger files. Provides comprehensive beancount syntax, directives, and query language expertise.
product-lifecycle-plays
by HMS091
"Map a product's lifecycle stage and choose between extension, replacement, and retirement plays. Use when a product is maturing or declining and the next move isn't obvious."
gzs-agent-context-diet
by tvproductions
Reduce always-loaded agent instruction weight while preserving every binding invariant through progressive disclosure and precise context pointers. Use when AGENTS.md, CLAUDE.md, repository rules, or skill descriptions have accumulated duplicated rationale or exceed an enforced context budget.
researcher-canada-hunt
by robertsben333-cmyk
The unpriced-information hunt, run over the Canadian market — TSX, TSX Venture, CSE and NEO. Seals what the market has priced into each company reporting into the next Toronto session, sends one hunter per name to find what is not in that price, and sums their signed finding sizes into one number per company so the day's names can be ranked. Research only, no orders. Use when asked to run the Canada researcher, run stage CA, rank the day's Canadian earnings names, or hunt Toronto, TSX or TSXV prints.
aaa-discovery
by Automation-Architecture
Walks the operator through the Automation Architecture (AAA) Discovery Phase for a new client engagement — a 15-step sequence that produces a fully scoped, ticketed, and client-informed project before any engineer writes code. Trigger this skill whenever a new client project is starting, when the operator says "kick off discovery", "start a new client", "new client engagement", "spin up a new project", "let's begin discovery", or invokes /aaa-discovery. Also trigger when a sales call transcript has just been read and the next step is to start scoping the work, or when the operator references "the 15 steps", "the AAA discovery flow", or "the canonical sequence". This skill orchestrates other skills (grill-me, to-prd, aaa-client-init) and agents (cto-technical-architect, board-nanny) — invoke it as the entry point so the steps run in the right order, with the right artifacts, in the right places.
category-inference
by Tzeusy
Assigns spending categories to uncategorized transactions using aggregate GROUP BY queries. Writes to the inferred_category overlay field, preserving explicit category values. Memory-backed for auto-applying known merchant→category mappings on future runs. Should run after merchant normalization.
slice-delivery
by ujjaval-verma
Tracker-agnostic vertical-slice delivery discipline. Use when the work is framed in slice terms or per-slice execution is delegated here. Triggers on "slice", "tracer bullet", "deep module", "refactor scan", "Ralph", "definition of done".
openclaw-workspace
by travererogenous649
Use when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and memory files. Covers workspace auditing, token budget analysis, new agent workspace setup from scratch, memory distillation, and cross-file consistency reviews.
refused-forecast
by eliquid
Diagnose a forecast the tool refused, repaired, or never returned. Use when a run dies with "returned an unusable forecast", when a model command hangs with no output, or when stored quantiles look mislabelled.
routine-abstraction-improver
by bex-co
Autonomous maintenance routine that flattens over-engineered
hand-off
by eliquid
Package this folder for someone else and check what you are actually sending them. Use before running share.sh, before publishing a release, or whenever a copy of the project leaves this machine.
waves-llm
by wavespestcontrolfl
Use when adding or modifying ANY LLM call site — model tiers, the DEEP helper, the ROUTES map, cross-provider fallbacks, or model env vars.
Deal Flow
by Atrium-Hermes
Weekly funding round tracker across configurable verticals
statiker
by Gunther-Schulz
Conducts a development task from investigation through verified implementation — a free design loop held by five forcing points (recorded decisions with bases, dispatchable-design stop rule, a fresh-context attack on each locked design, no-design implementation, isolated executed verify). Successor to clippy; use only when the operator explicitly invokes statiker or requests a statiker run.
vercel-optimize
by 011matthias
"Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests."
acquisition-channel-advisor
by HMS091
Evaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel.
unit-economics
by sallzzbr
"Compute e-commerce unit economics and ad-budget scenarios. Use when the user wants margins, breakeven CAC, target ROAS or to simulate an ad budget — unit economics, margem por pedido, CAC máximo, ROAS alvo, cenário de verba, quanto posso pagar por venda."
dse-loop
by middle-chunjie
"Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning."
bullshit-master
by ddddddebug
Transform casual, vague, or informal text into professional, polished, and context-aware expressions. Use when users ask to rewrite, polish, optimize, or improve writing.
balance
by Fibrous-Finance
Check wallet balances (native and ERC-20 tokens) on Base, Citrea, HyperEVM, or Monad.
plotext-financial-chart
by terrylica
ASCII financial line charts for markdown using plotext dot marker. TRIGGERS - financial chart, line chart, plotext