Synthesize an implementation-ready spec from the current conversation and relevant repository context. Use explicitly when the user wants agreed work captured as a spec or PRD.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add stevesolun/ctx --skill to-spec --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of To Spec?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/stevesolun-to-spec)More formats (shields.io, HTML) on the badges page.
---
name: to-spec
description: Synthesize an implementation-ready spec from the current conversation and relevant repository context. Use explicitly when the user wants agreed work captured as a spec or PRD.
---
# Create a spec
Capture the decisions already made. Resolve only gaps that would materially
change the intended behavior, scope, or feasibility; do not reopen settled
questions for the sake of completing a template.
Inspect the relevant implementation, tests, domain language, and architectural
decisions when they improve fidelity. Keep facts observed in the repository
distinct from decisions inferred from the conversation.
Describe:
- the user-visible problem and desired outcome;
- behavior, edge cases, and acceptance criteria;
- constraints and decisions that implementation must preserve;
- relevant interfaces or test seams when they are already known; and
- explicit exclusions and unresolved questions.
Prefer durable behavioral contracts over file paths and implementation recipes.
Include code or a type shape only when it records a decision more precisely than
prose.
Use the [spec format](SPEC-FORMAT.md) when a structured document helps. Return,
save, or publish the spec in the destination the user requested. Treat tracker
publication and label changes as separate mutations requiring clear scope.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
