generic-document-type
中文优先指导 generic_document 与 external profile 设计资产的 agent-runtime使用边界;当前 Python 不加载profile,同时保留provenance、HITL、sample/reference和final-report limits。
Skill by Exquisite0828
Chalk Labs
Need help deploying generic-document-type?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/exquisite0828-generic-document-type
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
Use cases: documents, agent-building
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/generic-document-type
What's inside
- Skill name
generic-document-type- Description
- 中文优先指导 generic_document 与 external profile 设计资产的 agent-runtime使用边界;当前 Python 不加载profile,同时保留provenance、HITL、sample/reference和final-report limits。
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "generic-document-type" does not match folder "generic_document"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Generic Document Skill Use this skill for `task_type: generic_document` and when a user explicitly supplies external profile design material such as `custom_technical_note`. Current Python records task metadata but does not load or validate profiles. Default communication is Chinese; keep `generic_document`, `document_profile.yaml`, Markdown Spec, candidate profile, custom_technical_note, HITL, NEEDS_USER_CONFIRMATION. ## Purpose `generic_document` is an L1 generic design/Skill asset, not an official L3 professional document type. Agent workers may use explicitly supplied source, template, checklist, sample, reference, task, or profile material as guidance, but current Python does not execute a generic content pipeline and no mode promises complete domain professional judgment. External `document_profile.yaml` is a proposed L2/customer mechanism. `custom_technical_note` is a design/demo asset, not official L3. There is no current Python profile validator; do not describe a profile as active or validated. ## Inputs And Sections Inputs may include project `source`, `template`, `checklist`, `reference`, `sample`, a user-selected profile design asset, or an upstream Markdown Spec used as worker guidance. Profile/Spec assets remain advisory because the current Python package does not load or validate them. Default sections: Background and Scope, Confirmed Source Facts, Proposed Approach, Risks and Open Questions, Decision and Human Confirmations, Review Summary. A worker may adopt sections from an explicitly selected external profile as advisory guidance, but must not describe that profile as Python-validated or active. ## Critical Claims Critical claims may come from task YAML or explicitly reviewed user guidance. Profile/spec fields are advisory until a future loader exists. Defaults include final decision recommendation, approval/acceptance, compliance, release readiness, risk acceptance, cost/schedule commitment, and security/safety claims. Without source or HITL, keep `NEEDS_USER_CONFIRMATION`, pending, or open. Forbidden final claims without T0/T1 and HITL: approved, accepted, validated, compliant, risk accepted, production ready, release approved, fixed final cost/schedule, no unresolved risk. ## Source Policy T0=HITL, T1=project source, T2=template/checklist, T3=reference methodology/background/terminology, T4=sample style/shape, T5=inference. sample is not fact source. reference cannot prove project facts. T3/T4/T5 cannot support critical claim by themselves. Preserve provenance, source tier, claim/evidence/human-confirmation status, profile id, and profile version when available. ## Review / Verification Focus Check template/checklist coverage, confirmed source fact separation, unsupported decision/approval/cost/schedule/compliance/readiness/security/safety claims, sample/reference misuse, unresolved risks, explicitly supplied profile metadata, required artifacts, citation integrity, candidate update inactive, and document type terminology isolation. Do not claim Python profile validation. ## Profile Boundary Markdown Spec and profile YAML are human-readable design/config assets in the current tree. Python does not load, generate, or validate them. Any worker-created candidate output stays proposed/inactive and must not overwrite profiles or stable Skills.
From Exquisite0828/AI_writer_plugin, MIT.
More from Exquisite0828/AI_writer_plugin
- 0.469score
step-candidate-profile-update
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow candidate profile update.
SkillCFreshness: CClaude Code +9 - 0.469score
step-conservative-draft
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow conservative draft generation.
SkillCFreshness: CClaude Code +9 - 0.469score
step-evidence-map
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 6 evidence map, citation plan, and section tasks.
SkillCFreshness: CClaude Code +9 - 0.469score
step-final-report
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow final report delivery.
SkillCFreshness: CClaude Code +9 - 0.469score
step-input-materials
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 1 input materials.
SkillCFreshness: CClaude Code +9 - 0.469score
step-material-inventory
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 2 material inventory.
SkillCFreshness: CClaude Code +9 - 0.469score
step-research-questions
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 5 research questions and writing-plan analysis.
SkillCFreshness: CClaude Code +9 - 0.469score
step-review
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow review.
SkillCFreshness: CClaude Code +9 - 0.468score
fsr-document-type
Exquisite0828
中文优先指导 fsr document type work,同时保留 functional safety requirement、safety goal、ASIL、source tier、provenance、sample/reference、HITL、final-report、TSC-deferred 和…
SkillCFreshness: CClaude Code +9 - 0.468score
item-definition-document-type
Exquisite0828
中文优先指导 Item Definition Document(功能安全 Item 定义文档)写作;保留 ISO 26262-3 Clause 5 术语、source tier、HITL、sample/reference 边界与 candidate-update 约束。
SkillCFreshness: CClaude Code +9 - 0.468score
software-architecture-document-type
Exquisite0828
中文优先指导汽车控制器产品 Software Architecture(SwAD,软件架构)文档写作;保留 ASPICE SWE.2、ISO 26262-6 软件层接口、SwRS 追溯、组件分配、接口边界、tier、HITL 与 candidate-update 约束。
SkillCFreshness: CClaude Code +9 - 0.468score
software-requirement-document-type
Exquisite0828
中文优先指导汽车控制器产品 Software Requirement(SwRS,软件需求)文档写作;保留 ASPICE SWE.1、ISO 26262-6 软件层接口、追溯、System Architecture 参考边界、tier、HITL 与 candidate-update 约束。
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 13, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Exquisite0828
- 0.469score
step-evidence-map
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 6 evidence map, citation plan, and section tasks.
SkillCFreshness: CClaude Code +9 - 0.469score
step-input-materials
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 1 input materials.
SkillCFreshness: CClaude Code +9 - 0.469score
step-candidate-profile-update
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow candidate profile update.
SkillCFreshness: CClaude Code +9 - 0.469score
step-conservative-draft
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow conservative draft generation.
SkillCFreshness: CClaude Code +9 - 0.469score
step-final-report
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow final report delivery.
SkillCFreshness: CClaude Code +9 - 0.469score
step-material-inventory
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 2 material inventory.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get generic-document-type running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
generic-document-type skill. Agent Mart. https://agentmart.dev/skills/exquisite0828-generic-document-type (last updated 2026-10-24)