Updated 1d ago
by lennoxsaint
Skills
AI agent skills for Claude Code and Codex. They make your agent finish the job and show receipts.
39 GitHub stars (39)
+28 in 3 days
| Period | New stars |
|---|---|
| Nov 11 | +1 |
| Nov 12 | +5 |
| Nov 13 | +22 |
- 5 skills (5 skills found in its SKILL.md files)
- 0 forks (0 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add lennoxsaint/Skills
Asks which skills and agents to install. Just one: npx skills add lennoxsaint/Skills --skill ambitious — add -g for every project.
Claude Code
git clone https://github.com/lennoxsaint/Skillscp -r "Skills/ambitious" ~/.claude/skills/
Copies the ambitious skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add lennoxsaint/Skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
ambitious
Runs a big task the way the field's best practitioner would, then proves it. Load it first, before any context-recall or domain skill, when the person explicitly asks for exceptional effort ("go above and beyond", "blow me away", "show off", "be ambitious", "best possible version", "one-shot this", "pull out all the stops", "max effort", "the one that matters most", /ambitious) or explicitly says…
ambitious/SKILL.md on GitHub (opens in a new tab) -
email-triage-pro
Triage one or more Gmail inboxes, surface the messages that matter, draft a small reply queue, and learn the user's archive and writing preferences. Use for inbox reviews, email cleanup decisions, reply drafting, or recurring Gmail briefings. Never use it to send email without a separate explicit request.
email-triage-pro/SKILL.md on GitHub (opens in a new tab) -
goal
Generate durable Codex goal packets or optimized Claude /goal prompts from user-provided plans, specs, or task lists. Use when someone asks to turn a plan into a /goal prompt, create a steerable autonomous execution goal, optimize a goal prompt, or write a goal contract for implementation.
goal/SKILL.md on GitHub (opens in a new tab) -
hill-climb
Turn real data into a locked answer key, then climb toward a measured target with fresh agent sessions until the number and two outside judges say it is done. Use for long, ambitious work that must reach a provable quality bar - "hill climb this", "build an eval and climb it", "make the harness/app/agent hit X%", "use the logs as a benchmark", "keep going until it passes", or any big job where vi…
hill-climb/SKILL.md on GitHub (opens in a new tab) -
save-10-percent
Audit personal and small-business recurring costs from CSV, JSON, OFX/QFX, QIF, text PDF, invoices, or read-only billing sources; verify actual use and dependencies; compare cheaper alternatives; persist until at least 10% in net recurring savings is evidenced or every safe lane is exhausted; and optionally execute an exact approved cancellation or downgrade batch with live browser preflight and…
save-10-percent/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.