Erd Studio Setup
liam-machine/erd-studio
Friendly, step-by-step setup for ERD Studio in an existing dbt project, for people who may be new to dbt or data modelling.
Agent skill
by mattgierhart in mattgierhart/PRD-driven-context-engineering
Define implementation contracts (APIs and data models) that developers will build against during PRD v0.6 Architecture.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v06-technical-specification --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prd-v06-technical-specification .claude/skills/prd-v06-technical-specification && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prd-v06-technical-specification" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v06-technical-specification into .claude/skills/prd-v06-technical-specification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v06-technical-specification", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v06-technical-specificationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v06-technical-specification --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/prd-v06-technical-specification .agents/skills/prd-v06-technical-specification && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prd-v06-technical-specification" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v06-technical-specification into .agents/skills/prd-v06-technical-specification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v06-technical-specification", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v06-technical-specification --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/prd-v06-technical-specification .cursor/skills/prd-v06-technical-specification && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prd-v06-technical-specification" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v06-technical-specification into .cursor/skills/prd-v06-technical-specification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v06-technical-specification", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mattgierhart/PRD-driven-context-engineering.git --path .claude/skills/prd-v06-technical-specification--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v06-technical-specification --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/prd-v06-technical-specification .gemini/skills/prd-v06-technical-specification && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prd-v06-technical-specification" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v06-technical-specification into .gemini/skills/prd-v06-technical-specification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v06-technical-specification", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v06-technical-specificationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/prd-v06-technical-specification .github/skills/prd-v06-technical-specification && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prd-v06-technical-specification" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v06-technical-specification into .github/skills/prd-v06-technical-specification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v06-technical-specification", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v06-technical-specification --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/prd-v06-technical-specification .opencode/skills/prd-v06-technical-specification && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prd-v06-technical-specification" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v06-technical-specification into .opencode/skills/prd-v06-technical-specification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v06-technical-specification", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
prd-v06-technical-specificationDefine implementation contracts (APIs and data models) that developers will build against during PRD v0.6 Architecture.
Prd V06 Technical Specification is an agent skill from mattgierhart/PRD-driven-context-engineering. Define implementation contracts (APIs and data models) that developers will build against during PRD v0.6 Architecture. Triggers on requests to define APIs, design database schema, create data models, or when user asks "define APIs", "data model", "database schema", "API contracts", "technical spec", "endpoint design", "schema design". Consumes ARC- (architecture), TECH- (Build items), UJ- (flows), SCR- (screens). Outputs API- entries for endpoints and DBT- entries for data models. Feeds v0.7 Build Execution.
Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files and assets (for example `assets/api.md`, `assets/dbt.md` and `references/examples.md`).
It sits in Product & Project Management, covering Database schema design, PRD writing and Data pipelines and ETL. It works with dbt. The repository describes itself as: PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD… The licence is MIT.
7 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGlobGrepFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Prd V06 Technical Specification loads about 3.4k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 843 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 843 words, ~3,357 tokens.
.claude/skills/prd-v06-technical-specification/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Position in workflow: v0.6 Architecture Design → v0.6 Technical Specification → v0.7 Build Execution
Technical specification defines the contracts developers build against: API endpoints and data models. This is the bridge between architecture and implementation.
This skill requires prior work from v0.3-v0.6:
This skill assumes v0.6 Architecture Design is complete with ARC- entries providing system structure.
This skill creates/updates:
All API- and DBT- entries are implementation contracts (not confidence-based). They are:
Example API- entry (from UJ- and SCR-):
API-001: Create Report
Method: POST
Path: /api/reports
Purpose: Create new report from selected data source and template (implements UJ-001 Step 1)
Auth: User
Journey: UJ-001 (Step 1 - Create Report)
Screen: SCR-002 (Report Builder)
Request:
Body:
{
title: string (required) — Report name
templateId: string (required) — Selected template (FEA-008)
dataSourceId: string (required) — Connected data source (FEA-001)
options: { dateRange: { start, end }, filters: [...] }
}
Response:
Success (201):
{
data: { id, title, status: "pending|generating|ready", createdAt }
}
Errors:
- 400: Invalid input — Missing required field
- 403: Forbidden — User doesn't own data source
- 404: Not found — Template or data source not found
- 429: Rate limit exceeded
Business Rules: BR-015 (max 100 reports per user)
Data: DBT-001 (reports table), DBT-002 (data_sources table)Example DBT- entry (referenced by API- entries):
DBT-001: Reports
Purpose: Stores user-generated reports (entities created by API-001, updated by API-004)
Table: reports
Fields:
- id: uuid — Primary key
- user_id: uuid — Report owner (FK → users) [NOT NULL]
- title: varchar(255) — Display name [NOT NULL]
- status: enum('pending','generating','ready','failed') [NOT NULL]
- created_at: timestamp [NOT NULL, DEFAULT now()]
Relationships:
- belongs_to: users via user_id
- belongs_to: templates via template_id
Indexes:
- user_id — List reports by user (API-003)
- (user_id, created_at DESC) — Recent reports (API-003)
- status — Find pending reports (background job)
Constraints:
- title: NOT NULL, length 1-255
- status: valid enum only
Business Rules: BR-015 (max 100 per user — enforce in API-001)
APIs: API-001 (create), API-002 (get), API-003 (list), API-005 (delete)| Type | What It Defines | Example |
|---|---|---|
| API- | Endpoint contracts | POST /users, GET /reports/:id |
| DBT- | Data model/schema | Users table, Reports table |
Rule: Every API- should know which DBT- it reads/writes. Every DBT- should know which API- accesses it.
Pull ARC- decisions — System structure and boundaries
Pull TECH- Build items — What we're implementing
Pull UJ- journeys — User flows the API must support
Pull SCR- screens — UI data requirements
Define API contracts for each endpoint:
Define data models for each entity:
Validate consistency:
API-XXX: [Endpoint Name]
Method: [GET | POST | PUT | PATCH | DELETE]
Path: [/resource/{id}/action]
Purpose: [What this endpoint does]
Auth: [Public | User | Admin | Service]
Journey: [UJ-XXX that uses this]
Screen: [SCR-XXX that calls this]
Request:
Headers:
- Authorization: Bearer <token>
- Content-Type: application/json
Params:
- id: string (required) — Resource identifier
Query:
- limit: number (optional, default 20) — Pagination limit
Body:
{
field: type — Description
}
Response:
Success (200/201):
{
data: { ... }
}
Errors:
- 400: Invalid input — [when this occurs]
- 401: Unauthorized — [when this occurs]
- 404: Not found — [when this occurs]
- 500: Server error — [when this occurs]
Business Rules: [BR-XXX enforced here]
Data: [DBT-XXX entities accessed]
Rate Limit: [requests/minute if applicable]Example API- entry:
API-001: Create Report
Method: POST
Path: /api/reports
Purpose: Create a new report from selected data source and template
Auth: User
Journey: UJ-001 (Step 1 - Create Report)
Screen: SCR-002 (Report Builder)
Request:
Headers:
- Authorization: Bearer <token>
- Content-Type: application/json
Body:
{
title: string (required) — Report name
templateId: string (required) — Selected template
dataSourceId: string (required) — Connected data source
options: {
dateRange: { start: ISO8601, end: ISO8601 }
filters: [{ field: string, operator: string, value: any }]
}
}
Response:
Success (201):
{
data: {
id: string
title: string
status: "pending" | "generating" | "ready"
createdAt: ISO8601
}
}
Errors:
- 400: Invalid input — Missing required field or invalid templateId
- 401: Unauthorized — Invalid or expired token
- 403: Forbidden — User doesn't own data source
- 404: Not found — Template or data source not found
- 429: Too many requests — Rate limit exceeded
Business Rules: BR-015 (max 100 reports per user)
Data: DBT-001 (reports), DBT-002 (data_sources)
Rate Limit: 10 requests/minuteDBT-XXX: [Entity Name]
Purpose: [What this entity represents]
Table: [database_table_name]
Fields:
- id: uuid — Primary key, auto-generated
- [field_name]: [type] — Description [constraints]
- created_at: timestamp — Record creation (auto)
- updated_at: timestamp — Last modification (auto)
Relationships:
- belongs_to: [DBT-YYY] via [foreign_key]
- has_many: [DBT-ZZZ]
Indexes:
- [field_name] — [Query pattern it supports]
Constraints:
- [field]: [UNIQUE | NOT NULL | CHECK expression]
Business Rules: [BR-XXX that affect this entity]
APIs: [API-XXX that read/write this]Example DBT- entry:
DBT-001: Reports
Purpose: Stores user-generated reports with configuration and status
Table: reports
Fields:
- id: uuid — Primary key
- user_id: uuid — Report owner (FK → users) [NOT NULL]
- title: varchar(255) — Display name [NOT NULL]
- template_id: uuid — Template used (FK → templates) [NOT NULL]
- data_source_id: uuid — Data source (FK → data_sources) [NOT NULL]
- status: enum('pending','generating','ready','failed') — Generation status [NOT NULL, DEFAULT 'pending']
- options: jsonb — Report configuration (date range, filters) [DEFAULT '{}']
- output_url: varchar(500) — Generated report file URL [NULL until ready]
- created_at: timestamp — [NOT NULL, DEFAULT now()]
- updated_at: timestamp — [NOT NULL, DEFAULT now()]
Relationships:
- belongs_to: DBT-010 (users) via user_id
- belongs_to: DBT-002 (templates) via template_id
- belongs_to: DBT-003 (data_sources) via data_source_id
Indexes:
- user_id — List reports by user
- (user_id, created_at DESC) — List recent reports
- status — Find pending reports for processing
Constraints:
- title: NOT NULL, length 1-255
- status: NOT NULL, valid enum value
Business Rules: BR-015 (max 100 reports per user — enforce in API)
APIs: API-001 (create), API-002 (get), API-003 (list), API-005 (delete)| Principle | Guidance | Example |
|---|---|---|
| Resource-oriented | URLs are nouns, not verbs | /reports not /createReport |
| Consistent naming | Plural nouns, kebab-case | /data-sources not /dataSource |
| Stateless | No server-side sessions | Auth via token, not cookie session |
| Versioned | Prefix for breaking changes | /v1/reports |
| Documented errors | Clear codes and messages | { error: { code: "LIMIT_EXCEEDED", message: "..." } } |
| Principle | Guidance | Example |
|---|---|---|
| Normalized | Avoid redundancy (unless denormalized for performance) | User name in users table, not duplicated |
| Audit trail | created_at, updated_at on all tables | Track when records change |
| Soft delete | deleted_at instead of hard delete (when needed) | Recover deleted data |
| Foreign keys | Enforce referential integrity | user_id → users.id |
| Index strategy | Index fields in WHERE and JOIN | Filter fields, FK columns |
Use this to ensure spec completeness:
| Anti-Pattern | Signal | Fix |
|---|---|---|
| API/UI mismatch | Screen needs data not in any API | Add API- or modify existing |
| Schema sprawl | 50+ tables for MVP | Consolidate; YAGNI applies |
| Missing constraints | No validation, anything accepted | Add BR- enforcement |
| N+1 queries baked in | API design requires multiple calls for one view | Add compound endpoints |
| No error handling | Only happy path documented | Define all error responses |
| Vague types | data: any | Specify exact shape |
Before proceeding to Build Execution:
API- and DBT- entries feed into:
| Consumer | What It Uses | Example |
|---|---|---|
| v0.7 Epic Scoping | API- and DBT- define EPIC scope | EPIC-01 implements API-001–005 |
| v0.7 Test Planning | API- defines test contracts | TEST-001 validates API-001 |
| v0.7 Implementation Loop | API-/DBT- are implementation tasks | Code implements API-001 |
| API Documentation | API- becomes OpenAPI spec | Swagger from API- entries |
references/examples.mdassets/api.mdassets/dbt.md© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references, assets) in .claude/skills/prd-v06-technical-specification of mattgierhart/PRD-driven-context-engineering.
Open the folder on GitHubat commit 30ed1b0
Prd V06 Technical Specification next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prd V06 Technical Specification this skillmattgierhart/PRD-driven-context-engineering | 180 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Erd Studio Setupliam-machine/erd-studio | 165 | — | ~8.6k | Automated safety check: Pass | Custom licence | |
| Modelersidequery/sidemantic | 129 | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Analytics Engineerborghei/Claude-Skills | 891 | — | ~3.4k | Automated safety check: Pass | MIT | |
| API Architectcuriositech/some_claude_skills | 244 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Tushare Plugin BuilderYourdaylight/stock_datasource | 189 | — | ~2.5k | Automated safety check: Pass | MIT |
liam-machine/erd-studio
Friendly, step-by-step setup for ERD Studio in an existing dbt project, for people who may be new to dbt or data modelling.
sidequery/sidemantic
Build, validate, and manage semantic models using Sidemantic.
borghei/Claude-Skills
Analytics engineering across data modeling, dbt, transformation, and semantic layers.
curiositech/some_claude_skills
Expert API designer for REST, GraphQL, gRPC architectures. An agent skill from curiositech/some_claude_skills.
Yourdaylight/stock_datasource
Turns a Tushare API doc URL into a full data plugin for the stock_datasource repo: extractor, ClickHouse schema, query service, config and curl examples.
sickn33/agentic-awesome-skills
Comprehensive Snowflake development assistant covering SQL best practices, data pipeline design (Dynamic Tables, Streams, Tasks, Snowpipe), Cortex AI functions, Cortex Agents, Snowpark Python, dbt…
mattgierhart/PRD-driven-context-engineering
Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py).
mattgierhart/PRD-driven-context-engineering
Extracts durable insights from temp/ files to SoT during EPIC Phase E.
mattgierhart/PRD-driven-context-engineering
Validates and registers new SoT IDs with cross-reference integrity.
mattgierhart/PRD-driven-context-engineering
Creates new Source of Truth (SoT) files when existing templates don't fit your needs.
mattgierhart/PRD-driven-context-engineering
Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark.
mattgierhart/PRD-driven-context-engineering
Transform validated pain points into articulated user value statements for PRD v0.1 Spark.
Works with
Define implementation contracts (APIs and data models) that developers will build against during PRD v0.6 Architecture. Prd V06 Technical Specification is an agent skill from mattgierhart/PRD-driven-context-engineering.6 Architecture.
Prd V06 Technical Specification fits situations like: requests to define APIs; design database schema; create data models; user asks define APIs.
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a claude-code`. Or copy the skill folder (.claude/skills/prd-v06-technical-specification in mattgierhart/PRD-driven-context-engineering) into .claude/skills/prd-v06-technical-specification in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a codex`. Or copy the skill folder (.claude/skills/prd-v06-technical-specification in mattgierhart/PRD-driven-context-engineering) into .agents/skills/prd-v06-technical-specification in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v06-technical-specification -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-v06-technical-specification, .gemini/skills/prd-v06-technical-specification, .github/skills/prd-v06-technical-specification and .opencode/skills/prd-v06-technical-specification in your project.
SKILL.md names no scripts, command-line tools or credentials: Prd V06 Technical Specification is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Prd V06 Technical Specification is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.4k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Prd V06 Technical Specification: Erd Studio Setup (liam-machine/erd-studio, 165 stars), Modeler (sidequery/sidemantic, 129 stars), Analytics Engineer (borghei/Claude-Skills, 891 stars) and API Architect (curiositech/some_claude_skills, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mattgierhart (a GitHub user) maintains it in mattgierhart/PRD-driven-context-engineering, which has 180 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on August 31, 2026.
Source: mattgierhart/PRD-driven-context-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.