All authors

Claude Skills by developzone5
github.com/developzone516 skills0 installs0 views
- BraintrustConvene independent specialists and a separate boss using the task's selected Claude or Codex engine. Use for a Sanad-selected panel or an explicit braintrust request. All Codex roles and panel advisors use xhigh; the deliberation dial selects seat count and risk coverage, not runtime effort.Votes: 0GitHub stars: 3
- GateRun your Definition-of-Done and security gate against the current change, now, with real quoted command output. Use when the user types /gate, asks to "run the gate", "prove it works", or "verify before I ship", or before declaring a task done.Votes: 0GitHub stars: 3
- SanadEntry point for every user request. Ask once per new task for Claude or Codex, recommending the current chat engine. Route bounded work directly and uncertain or sensitive work through the selected engine. All Codex roles use xhigh; preserve verification and publishing approval.Votes: 0GitHub stars: 3
- ShipWalk the change through the teach-back brief, then push to staging and open a DRAFT PR — never main/master/prod. Use when the user types /ship or asks to push, open a PR, or ship the change. Stops for explicit approval before pushing.Votes: 0GitHub stars: 3
- SpecCreate or update a durable, version-controllable spec file for a feature that spans multiple sessions — goal, decisions, plan/checklist, risks, and a running log. Invoked manually with /spec when starting or updating multi-session feature work. One lean file per feature, committed with the code.Votes: 0GitHub stars: 3
- BraintrustConvene independent specialists and a separate boss using the task's selected Claude or Codex engine. Use for a Sanad-selected panel or an explicit braintrust request. All Codex roles and panel advisors use xhigh; the deliberation dial selects seat count and risk coverage, not runtime effort.Votes: 0GitHub stars: 3
- DemoInteractive, screen-shareable walkthrough of the Sanad framework. Shows a numbered menu of the skills; the user picks one and you render a short description plus a realistic example of what running it looks like, one card at a time. Presentation only — never create files, spawn agents, run git, or open PRs. Use when the user types /demo or wants to show/explain Sanad to a group.Votes: 0GitHub stars: 3
- Explain PrExplain a whole pull request (or the current branch) so anyone can understand it — one easy lesson page per feature or fix, in a teacher's order — a short 3D animation of one example travelling through the app (page → API → service → database) and changing at the exact station the PR touches, then the problem (with a small picture of the screen), why it happened, the fix, the code with a plain meaning beside each line, a table of cases before and after, and the test that proves it. Arabic by ...Votes: 0GitHub stars: 3
- Full Output EnforcementOverrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.Votes: 0GitHub stars: 3
- GateRun your Definition-of-Done and security gate against the current change, now, with real quoted command output. Use when the user types /gate, asks to "run the gate", "prove it works", or "verify before I ship", or before declaring a task done.Votes: 0GitHub stars: 3
- ImpeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing,...Votes: 0GitHub stars: 3
- Sanad ImplementationInternal implementation stage selected by Sanad after routing a substantive feature, behavior change, bug fix or implementation continuation. Never select for teaching, explanations, status or checking work alone.Votes: 0GitHub stars: 3
- SanadEntry point for every user request. Ask once per new task for Claude or Codex, recommending the current chat engine. Route bounded work directly and uncertain or sensitive work through the selected engine. All Codex roles use xhigh; preserve verification and publishing approval.Votes: 0GitHub stars: 3
- ShipWalk the change through the teach-back brief, then push to staging and open a DRAFT PR — never main/master/prod. Use when the user types /ship or asks to push, open a PR, or ship the change. Stops for explicit approval before pushing.Votes: 0GitHub stars: 3
- SpecCreate or update a durable, version-controllable spec file for a feature that spans multiple sessions — goal, decisions, plan/checklist, risks, and a running log. Invoked manually with /spec when starting or updating multi-session feature work. One lean file per feature, committed with the code.Votes: 0GitHub stars: 3
- WorktreeSpin up a parallel git worktree (own directory, own branch off the integration branch) so a second Claude Code session can advance a second track concurrently; also lists and safely removes worktrees. Use when the user types /worktree, asks for a parallel worktree/track/session, or wants to work two branches at once.Votes: 0GitHub stars: 3