adversarial-squad
Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on…
@spec-kittyInstall SkillAgent Orchestration
Skill
/spk-start-here
Start here for Spec Kitty. Orient CLI users and supported agent-harness users; choose the right command, skill family, and recovery path.
Claude Code
$ npx -y skills add spec-kitty/spec-kitty --skill spk-start-here --agent claude-code
Codex
$ npx skills add spec-kitty/spec-kitty --skill spk-start-here -a codex -y
Cursor
$ npx skills add spec-kitty/spec-kitty --skill spk-start-here -a cursor -y
Gemini CLI
$ npx skills add spec-kitty/spec-kitty --skill spk-start-here -a gemini-cli -y
GitHub Copilot
$ npx skills add spec-kitty/spec-kitty --skill spk-start-here -a github-copilot -y
OpenCode
$ npx skills add spec-kitty/spec-kitty --skill spk-start-here -a opencode -y
Windsurf
$ npx skills add spec-kitty/spec-kitty --skill spk-start-here -a windsurf -y
SKILL.md
spk-start-here.SKILL.mdname: spk-start-here
description: "Start here for Spec Kitty. Orient CLI users and supported agent-harness users; choose the right command, skill family, and recovery path."
spk-start-here
Orient the user by where they are working: command line or supported agent harness.
Access Model
- Command-line users run `spec-kitty` CLI commands. `spk-*` skills are not CLI
commands.
- Agent-harness users invoke installed command surfaces:
`/spec-kitty.<command>` in slash-command hosts, or the `spec-kitty-<command>` command skill in skill hosts (`$spec-kitty-<command>` in Codex, `/skill:spec-kitty-<command>` in Pi, `/spec-kitty-<command>` in Vibe, Letta and Antigravity).
- Public `spk-*` skills are agent operating guides. Use them by name in a
skill-aware harness or let natural-language intent trigger them.
- If commands or skills are missing, route to `spk-admin-setup-doctor`.
Operating Model
Spec Kitty has three visible layers:
1. Commands: `/spec-kitty.*` slash commands and CLI commands that create or advance mission artifacts. 2. Skills: `spk-*` operating guides that teach an agent how to use the product. 3. Doctrine: charter, glossary, profiles, directives, and tactics loaded on demand by the runtime or by specialist skills.
Do not turn this into a full tutorial. Identify entry mode first, then route to the smallest useful workflow.
First Route
- New project or broken install: use `spk-admin-setup-doctor`.
- New feature from scratch: use `spk-start-first-feature`.
- User wants a command list: use `spk-start-command-map`.
- User asks "will this work in Codex or Claude?": use `spk-start-agent-surface`.
- Existing mission needs advancement: use `spk-run-next`.
- Multi-mission or multi-repo program: use `spk-run-program-orchestrate`.
- Review or approval work: use `spk-run-review-wp`, then `spk-gate-accept`.
- Team, SaaS, tracker, or sync concern: use `spk-team-sync` or `spk-team-tracker`.
- Charter or governance concern: use the `spk-charter-*` family.
- Engineering practice (bulk edit, visuals, code reduction): use the `spk-practice-*` family.
- Visual explanation or diagram request: use `spk-practice-show-me`.
- Unsure which skill applies: use `spk-meta-skill-map`.
Agent Behavior
State the route, load only the routed skill, and continue. Prefer commands and runtime outputs over guessing from files. If the user asks for a plan, give the shortest workflow that gets them to the next concrete Spec Kitty action.
Read more
name: spk-start-here description: "Start here for Spec Kitty. Orient CLI users and supported agent-harness users; choose the right command, skill family, and recovery path."
spk-start-here
Orient the user by where they are working: command line or supported agent harness.
Access Model
- Command-line users run `spec-kitty` CLI commands. `spk-*` skills are not CLI
commands.
- Agent-harness users invoke installed command surfaces:
`/spec-kitty.<command>` in slash-command hosts, or the `spec-kitty-<command>` command skill in skill hosts (`$spec-kitty-<command>` in Codex, `/skill:spec-kitty-<command>` in Pi, `/spec-kitty-<command>` in Vibe, Letta and Antigravity).
- Public `spk-*` skills are agent operating guides. Use them by name in a
skill-aware harness or let natural-language intent trigger them.
- If commands or skills are missing, route to `spk-admin-setup-doctor`.
Operating Model
Spec Kitty has three visible layers:
1. Commands: `/spec-kitty.*` slash commands and CLI commands that create or advance mission artifacts. 2. Skills: `spk-*` operating guides that teach an agent how to use the product. 3. Doctrine: charter, glossary, profiles, directives, and tactics loaded on demand by the runtime or by specialist skills.
Do not turn this into a full tutorial. Identify entry mode first, then route to the smallest useful workflow.
First Route
- New project or broken install: use `spk-admin-setup-doctor`.
- New feature from scratch: use `spk-start-first-feature`.
- User wants a command list: use `spk-start-command-map`.
- User asks "will this work in Codex or Claude?": use `spk-start-agent-surface`.
- Existing mission needs advancement: use `spk-run-next`.
- Multi-mission or multi-repo program: use `spk-run-program-orchestrate`.
- Review or approval work: use `spk-run-review-wp`, then `spk-gate-accept`.
- Team, SaaS, tracker, or sync concern: use `spk-team-sync` or `spk-team-tracker`.
- Charter or governance concern: use the `spk-charter-*` family.
- Engineering practice (bulk edit, visuals, code reduction): use the `spk-practice-*` family.
- Visual explanation or diagram request: use `spk-practice-show-me`.
- Unsure which skill applies: use `spk-meta-skill-map`.
Agent Behavior
State the route, load only the routed skill, and continue. Prefer commands and runtime outputs over guessing from files. If the user asks for a plan, give the shortest workflow that gets them to the next concrete Spec Kitty action.
Ships withspec-kitty
Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.
1.7k45 skills
Stars on GitHub
Momentum
- stars in total
- 1.7k
Other skills on spec-kitty.
@spec-kittyInstall Skillspec-kitty-git-workflo…
Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually, worktree…
@spec-kittyInstall Skillspec-kitty-implement-r…
Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state…
@spec-kittyInstall Skillspec-kitty-mission-rev…
Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify spec→code fidelity, FR coverage, drift,…
@spec-kittyInstall Skillspec-kitty-mission-sys…
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action…
@spec-kittyInstall Skillspec-kitty-orchestrato…
Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows from outside the host CLI. Triggers:…
@spec-kittyInstall SkillMore skills from other plugins.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
@paperclipaiInstall Skilladr-create
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
@ruvnetInstall SkillQuestions about spk-start-here.
- Which coding agents can use spk-start-here?
- spk-start-here installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.