hap-help
Explain Hapstack setup, hap-mode routing, skills, playbooks, principles, prerequisites, and host-specific invocation.
Skill by hapwi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hapwi-hap-help
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/hap-help
What's inside
- Skill name
hap-help- Description
- Explain Hapstack setup, hap-mode routing, skills, playbooks, principles, prerequisites, and host-specific invocation. Use for hap-help or questions about using Hapstack.
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- openai.yaml · agents/
- prompting.md · references/
- recipes.md · references/
SKILL.md (first lines)
# Hapstack help Read the [package README](https://github.com/hapwi/hapstack/blob/main/README.md) and [runtime contract](../hap-mode/references/runtime.md). Answer the user's specific question with the relevant installed file; read it before describing its rules. Do not run a workflow merely because you are explaining it. - Setup and model/budget preferences: [setup-hapstack](../setup-hapstack/SKILL.md) and its configuration reference. - Task routing: [hap-mode](../hap-mode/SKILL.md). Patch-to-score and shipping route to patcher and ship, overriding generic playbook triggers. - Understanding: how, why, teach, recall, ketchup, in-your-own-words. - Design and review: architect, arena, swarm, interrogate, blast-radius. - Verification: tdd, benchmark-checklist, create-verification-skill, maintain-verification-skill, control-ui, control-cli. - Writing and code cleanup: unslop, bro, technical-writing, deslop, no-comments. - Long work and learning: figure-it-out, show-me-your-work, reflect, correct, automate-me, make-bot-ui, and the orchestration/autonomy playbooks. - Every skill and principle: [catalogue](https://github.com/hapwi/hapstack/blob/main/CATALOG.md). Detailed guidance: [guide](https://github.com/hapwi/hapstack/blob/main/docs/guide/README.md). In Codex native plugins use `$hapstack:hap-mode` and `$hapstack:setup-hapstack`; linked standalone skills use `$hap-mode` and `$setup-hapstack`. Other hosts use their documented slash or plugin-qualified form. T3 consumes provider-discovered skills and supplies its existing MCP tools; Hapstack itself ships no MCP server. Host discovery and persistent custom modes vary. If a picker omits a skill, verify the actual installation path or explicitly point the agent to its file. No configuration is required: current-model roles, on-request delegation, existing tooling, and project-defined versioning are defaults. Setup changes those preferences without activating jobs or granting external-write authority. There is no fixed Grok/Claude requirement. Deslop and host control adapters are bundled; private built-ins are not prerequisites. For an unavailable browser, delegation, scheduler, history source, forge, or score service, report the specific limitation and a supported next step. Never advertise unperformed discovery, a nonexistent tool, or an unverified 100/100. Link the relevant public file under the repository from plugin.json, not a private cache path.
From hapwi/hapstack, MIT.
More from hapwi/hapstack
- 0.567score
hap-mode
hapwi
Route requested Hapstack engineering tasks to playbooks and skills, including patch-to-score and shipping.
SkillAFreshness: AClaude Code +9 - 0.561score
setup-benny
hapwi
Prepare and configure the dormant Benny issue-triage and bug-reproduction automation pack for an explicitly selected project and supported host scheduler.
SkillAFreshness: AClaude Code +9 - 0.556score
control-cli
hapwi
Exercise a requested CLI or terminal UI through the current host’s shell and PTY controls, recording actual behavior and preserving unrelated files and…
SkillAFreshness: AClaude Code +9 - 0.556score
control-ui
hapwi
Drive and inspect a requested UI using the active host’s browser or desktop controls, collecting evidence from the actual affected surface.
SkillAFreshness: AClaude Code +9 - 0.541score
how
hapwi
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: AClaude Code +9 - 0.541score
interrogate
hapwi
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: AClaude Code +9 - 0.541score
architect
hapwi
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: AClaude Code +9 - 0.541score
create-verification-skill
hapwi
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: AClaude Code +9 - 0.539score
benchmark-checklist
hapwi
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: AClaude Code +9 - 0.539score
correct
hapwi
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: AClaude Code +9 - 0.536score
arena
hapwi
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: AClaude Code +9 - 0.536score
blast-radius
hapwi
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hapwi/hapstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hapwi
- 0.567score
hap-mode
hapwi
Route requested Hapstack engineering tasks to playbooks and skills, including patch-to-score and shipping.
SkillAFreshness: AClaude Code +9 - 0.561score
setup-benny
hapwi
Prepare and configure the dormant Benny issue-triage and bug-reproduction automation pack for an explicitly selected project and supported host scheduler.
SkillAFreshness: AClaude Code +9 - 0.556score
control-ui
hapwi
Drive and inspect a requested UI using the active host’s browser or desktop controls, collecting evidence from the actual affected surface.
SkillAFreshness: AClaude Code +9 - 0.556score
control-cli
hapwi
Exercise a requested CLI or terminal UI through the current host’s shell and PTY controls, recording actual behavior and preserving unrelated files and…
SkillAFreshness: AClaude Code +9 - 0.541score
architect
hapwi
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: AClaude Code +9 - 0.541score
create-verification-skill
hapwi
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: AClaude Code +9
Cite this page
hap-help skill. Agent Mart. https://agentmart.dev/skills/hapwi-hap-help (last updated 2026-10-24)