Client Docs

Community

jh941213

client-docs

Use when asked for client-submission SI/AO deliverables (architecture design doc, interface spec, DB design doc, requirements traceability matrix, test result reports, manuals, operations reports). Triggered by acceptance/delivery/deliverable requests. On-demand only — produce exactly the deliverable requested

Overview

Publisher	jh941213
Repository	`my-cc-harness`
Skill name	`client-docs`
Stars	125
Forks	35
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by jh941213 on GitHub. Read the source before you install it.

Installation

Install the Client Docs AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/jh941213/my-cc-harness.git /tmp/my-cc-harness
mkdir -p .claude/skills
cp -r /tmp/my-cc-harness/skills_en/client-docs .claude/skills/client-docs

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Client Docs in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Client Docs on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Client Docs is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Client-Docs (on-demand client deliverables)

Principle: deliverables are infrequent. Generate only the requested one, by transforming materials that already exist (docs/, code, actual run output).

Deliverable routing

Deliverable	Source material (generate first if missing)	Notes
Architecture design doc	`docs/ARCHITECTURE.md` + diagrams + ERD (else /docs arch first)
Interface spec	`docs/api/` OpenAPI (else /docs api first)	includes internal/external integrations
DB design doc	ERD + model/migration code → table definition tables
Requirements spec / RTM	SPEC.md·PRD.md + requirement↔implementation(files/commits)↔test mapping	never fill cells without mapping evidence
Unit/integration test report	actual test run output (pytest/CI logs)	recording results of tests that were not run is absolutely forbidden — evidence-based reporting
User/operator manual	`docs/manuals/`, `docs/ops/` (else /docs manual·ops first)
AO operations report	AUDIT.log, incident/change records, git log	confirm the reporting period with the user

Generation rules

Output location: {project}/deliverables/[name]_[YYYY-MM-DD].md
Common skeleton: cover (project name·date·version) → revision history → TOC → body → appendix. Body structure follows each deliverable's convention
Client template wins: if ~/.claude/templates/client/ or {project}/templates/ has the client's template, follow its structure and field names exactly. Otherwise generate markdown with the skeleton above (convert to Excel/Word later via pandoc etc.)
Facts only: only content verified from code/docs/run output. Leave unverified items empty marked [NEEDS CONFIRMATION] — never fill plausibly
If sources are stale, run /docs sync first, then generate
After generating, add a deliverables/ routing row to memory/INDEX.md if absent (keywords: deliverable, acceptance, delivery)
Acceptance-grade requirements (rejection-prevention rules from independent evaluation):
- Test reports need more than summary tables — include a per-case detail appendix (ID, test name, verdict) generated from actual -v output
- Coverage must state the measurement command and scope; never report a tests-included figure alone — also give the source-package-only figure (denominator differences can double the apparent number)
- Include an approval box (author/reviewer/approver) and a requirements traceability matrix skeleton — mark missing values [NEEDS CONFIRMATION]
After generating, verify facts (number reproduction) with a separate agent when possible — the generator must not grade its own deliverable

Entry points

Slash command: /client-docs [arch|api|db|rtm|test|manual|ops|report]
Natural language: requests like "acceptance deliverables", "delivery docs", "test result report"

Forbidden

Bulk-generating deliverables that weren't requested (on-demand principle)
Recording test results that weren't run or figures that weren't verified
Modifying docs/ originals (deliverables go to deliverables/ only — originals are owned by the /docs suite)

Frequently asked questions

What does the Client Docs AI skill do?

Why use Client Docs on TypingMind?

Because you install it once and use it with any model. Client Docs is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Client Docs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jh941213/my-cc-harness/tree/main/skills_en/client-docs. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Client Docs?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Client Docs?

As many as you like. As long as a model supports skills, you can use Client Docs with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Client Docs AI skill free?

It is published on GitHub by jh941213. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Research

mattpocock

CommunityPopular

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading…

Resolving Merge Conflicts

mattpocock

CommunityPopular

Use when you need to resolve an in-progress git merge/rebase conflict.

Setup Matt Pocock Skills

mattpocock

CommunityPopular

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

Tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Client-Docs (on-demand client deliverables)

Deliverable routing

Generation rules

Entry points

Forbidden

Frequently asked questions

Related AI Skills

Set up your own AI workspace now