金融
个人理财、预算与财务工具
altitude-horizon-framework
TurboSnails
Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.
evaluating-trade-offs
liqiongyu
"Evaluate trade-offs and produce a Trade-off Evaluation Pack (trade-off brief, options+criteria matrix, all-in cost/opportunity cost table, impact ranges, recommendation, stop/continue triggers). Use for tradeoff/trade-off, pros and cons, cost-benefit, opportunity cost, build vs buy, ship fast vs ship better, continue vs stop (sunk costs). Category: Leadership."
finance-engineer
violetio
Financial systems and cost engineering
cap-table
jforksy
Equity tracking, dilution analysis, option pool modeling, and cap table management
marketing-ideas
fefogarcia
"When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 139 proven marketing approaches organized by category."
invoice-organizer
ashleytower
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Accounts Reconciler
jmsktm
Automate account reconciliation by matching transactions, identifying discrepancies, and generating variance reports
Business Plan Writer
jmsktm
Create comprehensive business plans, financial projections, and strategic documents for funding or planning
Construction Estimator
jmsktm
Construction cost estimation, project budgeting, material takeoffs, and bid preparation for contractors and builders
octoclaw
guanbear
OctoClaw is the TypeScript-first policy, delegation, status, and operator layer for OpenClaw. Use it when a turn should be routed through reply/delegate policy, WorkContract-backed delegation, runtime status, IM delivery, or feedback-loop tooling.
business-model
TurboSnails
"Generate a Business Model Canvas with all 9 building blocks. Use when creating a business model, documenting how a business creates value, or analyzing an existing business model."
vn-payroll
arisng
Calculates Net Income, Personal Income Tax (PIT), and Social Insurance (BHXH) based on Vietnam's progressive tax brackets.
phase-5-execute
cuioss
Execute phase skill for plan management. Manifest-driven task runner that executes tasks from TASK-*.json files sequentially and runs the per-deliverable plus end-of-phase verification sweep from manifest.phase_5.verification_steps.
architect
parsoFish
Interactive ideation session that turns ideas into a PLAN.md the operator reviews before any manifest is queued.
journey-sync
parsoFish
Keep the story suite (tests/stories/) in sync with forge-ui changes. Use whenever a change touches forge-ui load-bearing state (data-* attributes, routes, surfaces, flows/agents/skills/KB affordances), when adding or retiring a Studio capability, or before closing any session that modified forge-ui. The stories are BOTH the demo and the UI regression gate — a UI change without a story update either breaks the gate or silently rots the demo.
marketing-psychology
futuregerald
"When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application."
claude-hook-review
jcdendrite
Review and audit of Claude Code hooks (.claude/hooks/.sh and settings.json hook entries). TRIGGER when: reviewing a .claude/hooks/.sh script or settings.json hook entry, or designing a new hook. DO NOT TRIGGER when: editing permissions.allow rules (use review-permissions) or non-Claude hook systems.
recipe-agentfile-hygiene
cuioss
Domain-invariant cognitive sweep recipe that classifies every CLAUDE.md/AGENTS.md section against the shared ref-agentfile-hygiene rubric and emits one remediation deliverable per offending section
contract-check
parsoFish
"The declaration carrier and display identity for the onboard-project flow's contract gate — the REAL forge↔project contract preflight (runPreflight, packages/projects/preflight.ts) runs orchestrator-side (ADR-036); never spawned via the flow path (the only path onboard-project uses), but standalone-dispatchable like any other band-guard def — see 'What this is, honestly' below."
transcription-skill
kajisho5
Transcribe speech in audio or video files (mp4, mov, mkv, wav, m4a, mp3) into a structured, timestamped Transcript with a local ASR engine (faster-whisper), Japanese and English first-class; export plain SRT/VTT; derive speech intervals. Use this skill whenever the user asks what is said in a recording, wants a transcript, timestamps of speech, word timings, or timed text to hand to a subtitle or editing tool. It does not edit video, style subtitles, detect speakers, or decide anything about a production.
phase-4-plan
cuioss
Domain-agnostic task planning from deliverables with skill resolution and optimization
audit-archived-plan-retrospectives
cuioss
Audit archived plans across twenty-four retrospective checks — execution-manifest correctness, quality-verification findings, metrics anomalies, cross-plan recurring patterns, token-efficiency trend, scope-estimate accuracy, track-selection-accuracy (actual planning track vs counterfactual correct track), PR-merge velocity, task-count efficiency, global-log analysis, token-economics, quality-chain, sequence-and-build-minimality, input-integrity corpus completeness, task-graph redundancy, architecture-lookup-ratio (information-lookup vs build-lookup), preference-pattern-detector (recurring user gate-dispositions → architecture hints), dispatch-topology (leaf/dispatch-topology invariant), finalize-flow-conformance (post-#849 deterministic ci_verify mechanics), merge-window-accounting (widened merge-mutex admission window), lane-lever-effectiveness (checkpoint measurement arm — per-scope-class token spend vs armed targets + lane-lever engagement), exploration-share (measured share of tool-call spend that went to exploration rather than to work), billing-composition (re-derived billing-formula and payload-byte composition, reconciled against the dispatch-boundary ledger, every figure carrying its own population), and cross-check-synthesis facet-completeness — file lessons through the three-gate policy, and dormate reviewed plans
ref-agentfile-hygiene
cuioss
Agentfile context-hygiene rubric — objective criteria classifying every CLAUDE.md/AGENTS.md section as always-on-justified, demotable-to-skill, or inert/deletable, plus the always-on line budget and directory-tree anti-pattern; the shared source of truth for the recipe and the plugin-doctor backstop rules
phase-6-finalize
cuioss
Complete plan execution with git workflow and PR management