agentteams-assets
Static assets for the AgentTeams orchestrator — bundled fixture plans (minimal, multi-feature), CLI/SDK/API example scenarios, and golden files used by the parity harness and acceptance gate. Read-only from the perspective of the org-agentteams skill; consumers reference these via relative paths from packages, scripts, and tests.
- License 许可
- MIT
- 最近更新
- 2026-08-25
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- agentteams-assets
- tier
- org
- description
- Static assets for the AgentTeams orchestrator — bundled fixture plans (minimal, multi-feature), CLI/SDK/API example scenarios, and golden files used by the parity harness and acceptance gate. Read-only from the perspective of the org-agentteams skill; consumers reference these via relative paths from packages, scripts, and tests.
- dependencies
- [ "agentteams" ]
02 资源文件 9
- 参考文档examples/api/README.md3.3 KB
- 参考文档examples/cli/README.md1.7 KB
- 参考文档examples/README.md568 B
- 参考文档examples/sdk/README.md1.4 KB
- 其他fixtures/plans/.gitkeep—
- 参考文档fixtures/plans/minimal-plan/features/01-schema.md742 B
- 参考文档fixtures/plans/minimal-plan/README.md700 B
- 参考文档fixtures/plans/minimal-plan/stories/01/01-schema.md532 B
- 参考文档fixtures/plans/minimal-plan/tasks/01/01/01-declare.md357 B
03 SKILL.md 正文
AgentTeams Assets
Co-located assets for the agentteams skill. Kept under the skills tree so they ship with the skill, not as a sibling that could drift.
Layout
.agents/skills/agentteams-assets/
├── fixtures/
│ └── plans/
│ └── minimal-plan/ # 1F / 1S / 1T hand-authored fixture
│ ├── README.md
│ ├── features/01-schema.md
│ ├── stories/01/01-schema.md
│ └── tasks/01/01/01-declare.md
└── examples/
├── README.md
├── cli/README.md # full-cycle CLI scenarios (analyze → resume)
├── sdk/README.md # library-import scenarios (mjs + py)
└── api/README.md # type signatures + per-surface behavior
Reference paths (consumers hop across the skills tree via ../../agentteams-assets/)
| Consumer | Asset | Resolution |
|---|---|---|
…/agentteams/scripts/mjs/test/smoke.test.mjs |
minimal-plan | path.resolve(__dirname, '../../../../agentteams-assets/fixtures/plans/minimal-plan') |
…/agentteams/scripts/py/tests/test_smoke.py |
minimal-plan | Path(__file__).resolve().parents[4] / 'agentteams-assets' / 'fixtures' / 'plans' / 'minimal-plan' |
…/agentteams/scripts/parity.mjs |
minimal-plan | path.join(SCRIPTS_DIR, '../../agentteams-assets/fixtures/plans/minimal-plan') |
…/agentteams/scripts/acceptance-gate.mjs |
minimal-plan | same (uses the shared ASSETS_DIR constant) |
Root Makefile |
PLAN default |
.agents/skills/agentteams-assets/fixtures/plans/minimal-plan |
All consumers anchor on __dirname / __file__ ascent — never on the repo root or an absolute host path. The asset skill is a peer of the orchestrator skill, so the cross-skill hop is always ../../agentteams-assets/… from the orchestrator's scripts/ dir.
All consumers anchor on the repo root via git rev-parse --show-toplevel semantics (Makefile / scripts) or __dirname / __file__ ascent (tests). No absolute host paths.
Adding a new fixture
- Author
<name>-plan/underfixtures/plans/following thefeatures/stories/tasks3-tier shape. - Drop a
README.mdat the fixture root listing scope + execution order. - Reference from a new test via the same relative-path pattern above — never hard-code an absolute path.
Adding a new example
- Pick a surface —
cli/,sdk/, orapi/. - Add a
README.md(orNN-<scenario>.md) that exercises one or more of the six subcommands. - If the example needs a fresh fixture, add it to
fixtures/plans/first.
04 同仓库更多 Skills
validation_handoff
Forces the agent to conclude its response by generating a strict validation checklist and outlining pending actions, focusing heavily on defensive execution and edge-case testing.
project-ployglot-project-scafford
Scaffold a polyglot library project as TypeScript + Python twin packages under `packages/ts/` + `packages/py/`, with a shared `SPEC.md`, cross-language `tests/parity/fixtures.json`, side-by-side `examples/sdk/` + `examples/api/` documentation, per-package `Makefile`, and a root orchestrator that exposes `make ci`. Open-source friendly — no organization-specific paths or scopes baked in. Use when starting a new polyglot library, porting a single-language library to a twin, or auditing/regularizing an existing two-language repo against the canonical layout.
playwright-ui-locator
Auto-heal Playwright tests after a frontend developer changes a div's class, id, or other selector. Catches a failing Playwright test, captures the old vs new DOM tree, finds the element that drifted, derives the most stable replacement locator, and proposes the fix as a GitHub pull request (confident heals) or files a GitHub issue (ambiguous / element-removed cases) — never editing the working tree directly. Trigger when Playwright tests fail with "locator resolved to 0 elements", "Timeout waiting for selector", or after a UI refactor / class rename / Tailwind cleanup broke previously-passing tests.
org-learn-context-window
Distill the current conversation into a reusable command or skill artifact. Use when the user wants to capture a workflow they just executed (create a reusable slash command) or formalize a resolution/mistake/correction into a reusable skill so the same class of issue never recurs.
org-agent-skill-creator
Scaffold and validate scope-aware agent skills (company, enterprise, org, team, project, application). Use when the user asks to create a new agent skill, generate a SKILL.md file, scaffold a skill directory, or validate that existing skill directories meet SKILL_SPEC.md (frontmatter, naming rules, structure, scope/tier).
app-workshop-session-pdf-recap-next
Extract content from a workshop session PDF and produce a structured recap focused on (1) what was learned, (2) next steps, and (3) possible enhancements. Ingests a single PDF file path, parses session material (slides, transcripts, exercises, Q&A), and emits a Markdown report with Learning Recap, Next Steps, and Enhancement Opportunities sections with page-level traceability. Use when the user asks to "summarize a workshop", "recap a training PDF", "pull next steps from a session deck", or provides a workshop/seminar/tutorial PDF and wants a learn-and-act summary.