본문으로 건너뛰기
cccskills
무료GitHub에 공개

cartridge-forge

Use when the user asks to forge, scaffold, or author a new cartridge — content cartridge, department cartridge, or chipset bundle. Drives the cartridge-forge loop (scaffold → fill → gate checks → commit) via the skill-creator cartridge CLI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md6.2 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Cartridge Forge

Forge a new cartridge end-to-end using the skill-creator cartridge CLI. The forge is the toolchain that builds cartridges; this skill is the playbook that drives it.

When to invoke

Trigger on any of:

  • "create a cartridge for X"
  • "forge a new cartridge"
  • "scaffold a department" / "generate a department cartridge"
  • "build a content cartridge"
  • "make a chipset bundle for X"

Do not trigger for migrating legacy cartridges (that is cartridge migrate) or for forking an existing one (that is cartridge fork).

Prerequisites

  1. docs/cartridge/FORGING-GUIDE.md and docs/cartridge/CARTRIDGE-SPEC.md are the normative references. Read them once per session if the context is not already loaded.
  2. Pick the target directory. Convention:
    • examples/cartridges/<slug>/ for in-repo cartridges
    • ./my-cartridges/<slug>/ for ad-hoc / user-local work
  3. Pick the slug. Drop the -department suffix unless the cartridge is directly tied to a college department in .college/. "systems-administration" — not "systems-administration-department".
  4. Pick the template: department (skills + agents + teams), content (deepMap + story arc), coprocessor (pure functional tooling), or graphics (GLSL / OpenGL / WebGL / Vulkan shader pipeline; grounded in the GFX research series at /Research/GFX/ on tibsfox.com).

The Forge Loop

scaffold → fill → validate → eval → dedup → metrics → commit

Every step is idempotent and JSON-capable. eval is the gate — if it exits non-zero, the cartridge is not ready to ship.

1. Scaffold

skill-creator cartridge scaffold <template> <dir> <slug>

Writes an 8-file skeleton: cartridge.yaml, chipsets/*.yaml, one placeholder skill, agent, and team, plus a README.md. Round-trips through load → validate with zero errors before any edits.

2. Fill

Replace placeholder content with real content. A full department cartridge typically wants:

  • Skills — one per daily responsibility surface (10–15 is a comfortable size; fewer feels thin, more suggests a split)
  • Agents — an Opus capcom + hands-on Sonnet executors; router topology with is_capcom: true on the capcom
  • Teams — one per recurring workflow (author, review, incident, drill) — each team names its roster and use_when
  • Grove record types — 4–8 record types that capture the durable outputs this cartridge produces
  • Evaluation domains — one per skill domain; keep them aligned with the domain: field on each skill

Replace the skeleton's cartridge.yaml header:

  • id: slug
  • name: title case, human-readable
  • author: real author
  • description: one-paragraph, no marketing tone
  • provenance.origin, provenance.createdAt
  • metadata.tags

Delete the three placeholder markdown files (skills/placeholder-skill.md, agents/placeholder-agent.md, teams/placeholder-team.md) and replace them with one markdown file per real skill / agent / team. Each companion file is informational — the loader does not scan them, but a "full" cartridge ships them.

3. Validate

skill-creator cartridge validate <dir>/cartridge.yaml --json

valid: true is the required outcome. If there are validation-debt errors (e.g. around agent_affinity or domains_covered), add --allow-validation-debt and track the debt per docs/cartridge/KNOWN-VALIDATION-DEBT.md.

4. Eval

skill-creator cartridge eval <dir>/cartridge.yaml

Runs the pre-deploy gates declared in chipsets/evaluation.yaml. Default gates:

  • all_skills_have_descriptions
  • all_agents_have_roles
  • grove_record_types_defined
  • has_evaluation_chipset

Exit code 0 is required before commit.

5. Dedup

skill-creator cartridge dedup <dir>/cartridge.yaml

no collisions is required. Collisions mean a skill or agent is defined twice across chipsets — either intentional merge (refactor) or typo (fix).

6. Metrics

skill-creator cartridge metrics <dir>/cartridge.yaml

Informational, not a gate. Captures shape (skill / agent / team / record-type counts) for the commit message.

7. Commit

Conventional Commits, scope cartridge:

feat(cartridge): forge <slug> cartridge

N skills / M agents / K teams / J grove record types.
Forged via cartridge-forge from the <template> template.
All forge gates green: validate, eval, dedup.

Rules

  1. Never hand-author a cartridge.yaml from scratch. Always scaffold first — the template encodes the current schema.
  2. Never skip eval. It is the ship gate.
  3. kind: department is a schema discriminator, not a college tie. The chipset kind stays department even when the cartridge is not tied to a college department.
  4. Drop -department from the slug unless the cartridge is tied to an entry under .college/.
  5. The companion markdown files are not validated. Write them anyway — a cartridge without them is scaffold-quality.
  6. Backup and DR content belongs in a dedicated team (<slug>-dr-drill-team or equivalent) if the cartridge has data-durability responsibilities.

Reference walkthrough

A complete worked example: examples/cartridges/systems-administration/ — 12 skills, 5 agents, 4 teams, 6 grove record types, all forge gates green.

Output contract

After the loop completes, report to the user:

  • Final id, name, and path
  • Chipset list
  • Counts: skills / agents / teams / grove record types
  • validate / eval / dedup verdicts
  • Any validation debt accepted and the follow-up note

Do not report "done" before all three gate checks (validate, eval, dedup) have been run and shown green; metrics is captured for the commit body, not a gate.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Provides web accessibility best practices for semantic HTML, ARIA, keyboard navigation, color contrast, and screen reader patterns. Use when building UI components, reviewing accessibility, or when user mentions 'a11y', 'accessibility', 'ARIA', 'screen reader', 'keyboard navigation', 'WCAG'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Active listening techniques for effective communication. Covers attending behaviors, paraphrasing, reflective listening, clarifying questions, empathic response, barriers to listening, listening in conflict, and cross-cultural listening. Use when building listening skills, improving understanding in conversation, mediating disputes, or analyzing communication breakdowns.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Adversarial spec-compliance PR review — cross-references diffs against approved specs, verifies runtime claims against source, detects competing PRs, audits scope/convention compliance. Use before merging.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Provides best practices for AI agent orchestration including MCP servers, A2A protocol, multi-agent coordination, and swarm architectures. Use when designing agent systems, configuring MCP servers, setting up agent teams, or when user mentions 'MCP', 'A2A', 'agent orchestration', 'multi-agent', 'swarm', 'agent team', 'LangGraph', 'CrewAI', 'AutoGen'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Symbolic manipulation, equation solving, and algebraic structures for mathematical reasoning. Covers distributive law, factoring, completing the square, linear through polynomial equation solving, systems of equations (substitution, elimination, Gaussian elimination, matrix methods), algebraic structures (groups, rings, fields), modular arithmetic, polynomial theory, and inequalities. Use when solving equations, simplifying expressions, working with algebraic structures, or performing symbolic manipulation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Understanding how algorithmic systems shape what users see, know, and do -- from recommendation feeds to search ranking to credit scoring to hiring software. Covers the mechanics of recommendation systems, algorithmic bias and its sources, personalization's effects on information diets, opacity and accountability, AI limitations (hallucination, confident wrongness), and the human-in-the-loop question. Use when a learner needs to think critically about why particular content reached them.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Tibsfox의 스킬 모두 보기

이 스킬의 문제 신고