processize
97Skill Claude Code
Turn a product idea into a manual deliverable process (magic piece of paper) before automating in a Deepiri service.
not rated 2 yesterday A 28 tokens
original Apache-2.0
2Stars on the repository
114Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown
Skill Claude Code
Now / next / later roadmap tied to metrics and Deepiri repo ownership.
not rated 2 yesterday A 19 tokens
original Apache-2.0
quick-recap
99Skill Claude Code
Red/yellow/green final status block for agent responses. Use when adding or following a clear completion-state convention at the end of work.
not rated 2 yesterday A 32 tokens
original Apache-2.0
Skill Claude Code
React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code — components, data fetching, bundle size, or performance.
not rated 2 yesterday A 45 tokens
original Apache-2.0
Skill Claude Code
Force a docs-first pass before guessing: third-party APIs, libraries, frameworks, CLIs, cloud/provider SDKs, upgrades, auth/security/billing, migrations, deploys, or anything "latest/current/official". Web-search and read primary docs before coding from memory.
not rated 2 yesterday A 62 tokens
original Apache-2.0
Skill Claude Code
Trace user stories to tests and repos — coverage matrix for Deepiri delivery.
not rated 2 yesterday A 19 tokens
original Apache-2.0
ship
103Skill Claude Code
Weekend-scope shipping: cut scope, manual-first delivery, one outcome, feedback loop. Pairs with mvp skill for execution after discovery.
not rated 2 yesterday A 31 tokens
original Apache-2.0
stakeholder-map
104Skill Claude Code
RACI and stakeholder map for Deepiri initiatives — eng, product, ops, customers.
not rated 2 yesterday A 22 tokens
original Apache-2.0
Skill Claude Code
Long-running or parallel agent work that must respect usage budgets: check usage between waves, pause near the cap (95%), resume only when the window is clear enough to continue.
not rated 2 yesterday A 41 tokens
original Apache-2.0
Skill Claude Code
Discover candidate governing equations directly from measured data — sparse regression (SINDy and relatives), symbolic regression search (PySR/gplearn-style), and data-driven coordinates (DMD, autoencoders) — as hypothesis generators feeding the disciplined applied-math validation loop. Use when you have dense…
not rated 2 yesterday A 78 tokens
original Apache-2.0
threat-model
107Skill Claude Code
Lightweight threat model — assets, actors, STRIDE per Deepiri service boundary.
not rated 2 yesterday A 21 tokens
original Apache-2.0
token-efficiency
108Skill Claude Code
Deliberate context and token budgeting for long or expensive agent sessions — what to read versus grep, when to delegate to a subagent or fork instead of inlining output, how to keep a session productive as it approaches context limits. Use on long-running work, large-repo exploration, or whenever a session is burning…
not rated 2 yesterday A 76 tokens
original Apache-2.0
user-interview
109Skill Claude Code
Customer discovery interview guide — JTBD questions, notes template, synthesis.
not rated 2 yesterday A 18 tokens
original Apache-2.0
validate-idea
110Skill Claude Code
Validate a business idea before building — manual sale, 10 specific customers, red/green flags. Minimalist entrepreneur + Deepiri dataset signals when relevant.
not rated 2 yesterday A 35 tokens
original Apache-2.0
Skill Claude Code
Review UI code for Web Interface Guidelines compliance. Use when asked to review UI, check accessibility, audit design, review UX, or check a site against web best practices.
not rated 2 yesterday A 39 tokens
original Apache-2.0
Skill Claude Code
Review docs/prose for Writing Guidelines compliance. Use when asked to review docs, check writing style, audit prose, review voice and tone, or check a page against a writing handbook.
not rated 2 yesterday A 41 tokens
original Apache-2.0
ult-quo-company
113Skill Claude CodeCodex
Ultimate Quo-pattern company-domain discovery for Deepiri — full software only. Quo is SHAPE only (universal capability → one underserved niche) — never clone phone answering. Trigger→stack extraction on Deepiri repos, 2026 triggers, network effects, assumption tests. Deepiri only — never Exovra puck / BOM / hardware.…
not rated 2 yesterday A 89 tokens
original Apache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: