Guide a first Spec Kitty feature from setup through specify, plan, tasks, implementation, review, accept, merge, and retrospective.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add Priivacy-ai/spec-kitty --skill spk-start-first-feature --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Spk Start First Feature?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/priivacy-ai-spk-start-first-feature)More formats (shields.io, HTML) on the badges page.
---
name: spk-start-first-feature
description: "Guide a first Spec Kitty feature from setup through specify, plan, tasks, implementation, review, accept, merge, and retrospective."
---
# spk-start-first-feature
Use this skill when a user wants to start their first Spec Kitty mission or
feature and needs the end-to-end path.
## Workflow
1. Verify install and agent surface with `spk-admin-setup-doctor` if commands or
skills are missing.
2. Create or select the mission with `/spec-kitty.specify`.
3. Build the plan with `/spec-kitty.plan`.
4. Produce work packages with `/spec-kitty.tasks` or the outline/packages/finalize
split when the project uses staged task authoring.
5. Advance work with `spk-run-next`.
6. Drive implementation/review loops with `spk-run-implement-review`.
7. Close with `spk-gate-accept`, then `spk-gate-merge`.
8. Finish post-merge checks with `spk-gate-mission-review` and
`spk-gate-retrospective`.
## Guardrails
- Keep the user on one mission until a blocker requires a different route.
- Treat generated runtime prompt files as authoritative for the current action.
- Do not skip review, accept, or merge gates just because implementation appears
complete.
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.
