Deeply grill an idea, decision, design, plan, or implied approach through evidence, failure modes, and user-owned decisions. Use discovery mode for raw ideas, clarification, "grill me", or an unfinished Product Brief; use audit mode for a formed target that needs a verdict or revision. Continue every reply in an…
Mindful-coding OS for any LLM coding agent — faster, quality, scalable output. One invoke configures seven layers (0–6): (0) BRIEF — optional one-page PRD.md (skipped if design.MD/README already covers it, or on request), plus git init, gitignore, and a day-one security baseline; (1) HARNESSING — Handoff.MD…
Pattern taxonomy, agent role combinations, model routing, unit-of-work sizing, review-findings settling, and resilience discipline for Claude Code dynamic workflows. ALWAYS load this skill before authoring or running any Workflow tool script, and ALWAYS load it when the user mentions "workflow" or "ultracode" in any…
Use this skill when the user asks to "write a spec", "create a spec", "spec out", "plan the implementation", "draft an implementation plan", "create a feature spec", "document how to implement", or otherwise needs a detailed implementation specification for a feature, integration, refactor, library, CLI, UI flow, data…
Use during Trellis planning when creating or refining a PRD. Applies grill-me style clarification: ask one question at a time, inspect code before asking, provide options and a recommended answer, update prd.md after each decision, verify technical facts against latest knowledge with grok-search-mcp before…
A planning workflow for multi-day or multi-session projects. It creates shared specification, plan, worker-brief, status, and handoff files in the repository before work begins.
This skill should be used when a request is ambiguous, underspecified, conflicting, or high impact. It is intended for vague verbs like optimize, improve, fix, refactor, and add feature; for missing file paths or unknown dependencies; and for risky actions like deploy, delete, overwrite, or migrate. It should not be…
Advisor-orchestrated in-session build loop. The session model (the strongest model you have, or a new SOTA model you want to evaluate) acts as planner + advisor + reviewer; implementation is delegated to cheaper subagent models. Derives a verifiable completion condition up front and interviews the user if one can't be…
Institutional knowledge for the Slope autonomous development loop. Use when executing automated sprints, reviewing loop results, analyzing model tier performance, or working on Slope's own codebase via the loop. Use when user says "run a sprint", "check loop status", "review sprint results", "model performance"…
Use when the user wants to prepare project-specific context engineering documents, AI coding agent instruction files, project starter Markdown files, vibe coding guardrails, PRD/TDD/architecture/security/testing docs, AGENTS.md/CLAUDE.md/Cursor/Windsurf/Continue/Copilot context files, or a complete AI-coding-ready…
A codebase guide generator that scans the current workspace and creates newcomer documentation, including an architecture overview and code-reading path.
Founder/CEO product thinking mode. Challenges whether you're building the right thing. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when user says /plan-ceo, asks for product direction, or needs the 10-star version of a feature.
Draft a Product Requirements Document (PRD) for a new capability. Use when planning a feature, kicking off a project, or when asked for a PRD, feature spec, or requirements document. Triggers on: create a prd, write a prd for, plan this feature, requirements for, spec this out.
The standard gated workflow for shipping ANY repository change: plan → plan-review → implement → cross-review → merge → verify, with two human approval gates. Use whenever the user asks to implement, build, add, fix, or ship a change to a repo ("new feature", "let's implement X", "ship X", "fix this bug and open a…
Turn a rough draft, vague ambition, or messy task brief into a powerful Codex /goal objective for long-running autonomous work. Use when the user asks to write, improve, format, sharpen, stress-test, or activate a Codex goal, thread goal, durable goal, or /goal prompt.
Expert startup advisor with deep knowledge of Y Combinator principles, successful unicorn strategies, and building high-impact billion-dollar companies.
Use this skill when the user needs to transform business requirements, use case descriptions, or meeting transcripts into a technical Power Platform solution architecture, including component selection and Mermaid.js diagrams.
Use at a specflo project's execute phase, when turning a validated plan.md into committed, verified code one task at a time. Triggers include "execute the plan", "start building", "work the next task", or specflo status showing the execute phase. Do NOT use before a plan has been validated, or for trivial fixes…
★not rated 6
changed 10d agoA78 tokens
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: