bootstrap
Zero-knowledge entry point. Fires at the start of every session — loads prior context, recruits relevant skills, and surfaces capabilities without requiring the user to know any skill names.
- License 许可
- Apache-2.0
- 所属仓库
- pjherron/hypoc
- 最近更新
- 2026-09-01
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- bootstrap
- origin
- Platform
- description
- Zero-knowledge entry point. Fires at the start of every session — loads prior context, recruits relevant skills, and surfaces capabilities without requiring the user to know any skill names.
- disable-model-invocation
- false
03 SKILL.md 正文
Bootstrap
The platform's first action in every session. No user input required to trigger it.
What It Does
- Recruit skills — run
skill-recruitmentto find skills relevant to this project and the user's recent work patterns. - Load prior session — run
session-recruitmentto surface what was worked on previously and any open threads. - Orient the user — present a brief, plain-language summary of what the platform can help with today. Describe capabilities, never skill names.
- Stand by — wait for the user's first request. Detect intent, then present the skill consent prompt before invoking anything.
Skill Consent Prompt
Before invoking any skill, always present:
I can help with [plain-language description of what will happen].
[Accept][Review][Revise][Decline]
- Accept — invoke the skill as-is.
- Review — show the full skill definition, then re-present the prompt.
- Revise — open the skill for inline adjustment; run the revised version. Do not permanently save the revision unless the user asks.
- Decline — skip; do not re-suggest the same skill for the same intent this session.
Rules
- Never name a skill to the user unless they ask.
skill-recruitmentandsession-recruitmentare infrastructure — they run silently without a consent prompt.- If nothing relevant is recruited, say so plainly and ask what the user wants to work on.
- Explicit slash commands (e.g.
/to-spec) bypass the consent prompt — the user already knows what they want.
04 同仓库更多 Skills
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
verification-loop
A comprehensive verification system for Claude Code sessions.
triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in a local file, or native blocking links on a real tracker.