If you're building Claude skills at any scale, you need this. It walks you through the entire lifecycle: requirements gathering, architecture planning (linear, router, methodology, widget, or API wrapper patterns), writing the SKILL.md with proper detection flows, creating reference files, and scoring against a quality rubric. The core philosophy is sound: skills must detect available tools at runtime and adapt, never hardcode. Every parameter needs an explicit default, every step needs a pass/fail gate, and complexity goes in reference files to keep the main skill under 250 lines. Opinionated in the right ways.

skills.sh installs
3K
GitHub stars
3.5K
last updated
Aug 21, 2026

Install

$ npx -y skills add himself65/finance-skills --skill skill-creator --agent claude-code

Installs into .claude/skills of the current project.

Files

Skill Creator

Create, evaluate, and iterate on high-quality agent skills. This skill covers the whole lifecycle: planning what the skill should do, writing SKILL.md and reference files, scoring quality against a rubric, and iterating until the skill meets production standards.

Philosophy: A great skill is precise, not long. Its description routes the right requests to it. Its body gives the model the context it can't get anywhere else — the environment, tool contracts, defaults, domain judgment, and the reasons behind each constraint — and leaves out what a capable model already does on its own. Current Claude models follow instructions closely and literally, so every line gets acted on: an over-scripted or shouting skill produces rigid, over-cautious output, while a clear goal and quality bar let the model plan the work itself. references/writing-guide.md covers this in detail.

Runtime adaptation: Skills that touch external tools should detect what is installed, authenticated, and reachable at runtime and adapt, rather than assuming a single method. Offer fallback paths where real alternatives exist. See references/dynamic-calling.md for the pattern catalog.

Sponsors

Details

Repository
github.com/himself65/finance-skills
Categories
Testing & QA, DevOps & CI/CD, Code Review & Quality, Skill Development, Debugging, Automation & Workflows, Design & UI/UX, Finance & Trading
First seen
Jun 3, 2026

More from himself65/finance-skills

All 25
1microsoft avatarupdate-screenshotsmicrosoft/vscodeDownload screenshot baselines from the latest CI run and commit them. Use when asked to update, accept, or refresh component screenshot baselines from CI, or af3Kskills.sh installs
2jezweb avatarux-auditjezweb/claude-skillsWalk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sendi3Kskills.sh installs
3phuryn avataridentify-assumptions-existingphuryn/pm-skillsIdentify risky assumptions for a feature idea in an existing product across Value, Usability, Viability, and Feasibility. Uses multi-perspective devil's advocat2.9Kskills.sh installs
4wshobson avatarquantized-exportwshobson/agentsExport a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes prom2.9Kskills.sh installs
5anthropics avatarcapacity-plananthropics/knowledge-work-pluginsPlan resource capacity — workload analysis and utilization forecasting. Use when heading into quarterly planning, the team feels overallocated and you need the 2.9Kskills.sh installs
6confident-ai avatardeepevalconfident-ai/deepevalDeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn2.9Kskills.sh installs