Building Pydantic AI Agents
docling-project/docling
Patterns and tested examples for building agents with Pydantic AI: tools, capabilities, structured output, dependency injection, hooks, YAML specs, streaming and testing.
Validation and diagnostic skill for HASTE. An agent skill from microsoft/haste.
OfficialMITAuto-check passed
Install Validation Diagnostics
$ npx skills add microsoft/haste --skill validation-diagnostics -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/haste validation-diagnostics --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/microsoft/haste.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/validation-diagnostics .claude/skills/validation-diagnostics && 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 "validation-diagnostics" agent skill from https://github.com/microsoft/haste/tree/main/.github/skills/validation-diagnostics into .claude/skills/validation-diagnostics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validation-diagnostics", 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/microsoft/haste/tree/main/.github/skills/validation-diagnosticsType 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 microsoft/haste --skill validation-diagnostics -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/haste validation-diagnostics --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/haste.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/validation-diagnostics .agents/skills/validation-diagnostics && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "validation-diagnostics" agent skill from https://github.com/microsoft/haste/tree/main/.github/skills/validation-diagnostics into .agents/skills/validation-diagnostics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validation-diagnostics", 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 microsoft/haste --skill validation-diagnostics -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/haste validation-diagnostics --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/haste.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/validation-diagnostics .cursor/skills/validation-diagnostics && 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 "validation-diagnostics" agent skill from https://github.com/microsoft/haste/tree/main/.github/skills/validation-diagnostics into .cursor/skills/validation-diagnostics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validation-diagnostics", 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/microsoft/haste.git --path .github/skills/validation-diagnostics--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 microsoft/haste --skill validation-diagnostics -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/haste validation-diagnostics --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/haste.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/validation-diagnostics .gemini/skills/validation-diagnostics && 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 "validation-diagnostics" agent skill from https://github.com/microsoft/haste/tree/main/.github/skills/validation-diagnostics into .gemini/skills/validation-diagnostics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validation-diagnostics", 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 microsoft/haste validation-diagnosticsInstalls 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 microsoft/haste --skill validation-diagnostics -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/haste.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/validation-diagnostics .github/skills/validation-diagnostics && 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 "validation-diagnostics" agent skill from https://github.com/microsoft/haste/tree/main/.github/skills/validation-diagnostics into .github/skills/validation-diagnostics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validation-diagnostics", 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 microsoft/haste --skill validation-diagnostics -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/haste validation-diagnostics --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/haste.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/validation-diagnostics .opencode/skills/validation-diagnostics && 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 "validation-diagnostics" agent skill from https://github.com/microsoft/haste/tree/main/.github/skills/validation-diagnostics into .opencode/skills/validation-diagnostics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "validation-diagnostics", 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.
Facts
- Skill name
validation-diagnostics- GitHub stars
- 106
- Token cost
- ~1.1k tokens
- SKILL.md length
- 354 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
Validation and diagnostic skill for HASTE. An agent skill from microsoft/haste.
- Works in 4 steps: Document the miss in the diagnostic report → Identify the pattern (was it a… → Propose a skill update or instruction… → …
- : validate implementation
- SKILL.md covers Overview, Key Concepts, Patterns & Techniques and Decision Framework, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Validation Diagnostics is an agent skill from microsoft/haste, published by the product's own GitHub organization. Validation and diagnostic skill for HASTE. Compare planned vs implemented work, generate diagnostic reports, and feed misses back into skill refinement. Use when: 'validate implementation', 'compare to spec', 'diagnostic report', 'drift analysis', 'coverage check', 'implementation review'.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Pydantic. The repository describes itself as: High Speed Assessment and Satellite Tracking for Emergencies. The licence is MIT.
When your agent uses it
- : validate implementation
- Compare to spec
- Diagnostic report
- Implementation review
Example prompts
- “validate implementation”
- “compare to spec”
- “diagnostic report”
- “/validation-diagnostics”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Document the miss in the diagnostic report
- Identify the pattern (was it a convention violation? missing test? spec ambiguity?)
- Propose a skill update or instruction addition to prevent recurrence
- Flag to the Orchestrator for tracking
What it can do on your machine
Read from SKILL.md and the folder at commit 079bd89. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
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.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Validation Diagnostics loads about 1.1k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 354 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from microsoft/haste at commit 079bd89, republished under its MIT licence (© microsoft). 354 words, ~1,093 tokens.
Download SKILL.mdSave it as
.claude/skills/validation-diagnostics/SKILL.md (or your agent's skills folder).- name
- validation-diagnostics
- description
- Validation and diagnostic skill for HASTE. Compare planned vs implemented work, generate diagnostic reports, and feed misses back into skill refinement. Use when: 'validate implementation', 'compare to spec', 'diagnostic report', 'drift analysis', 'coverage check', 'implementation review'.
- source
- HASTE validation practices
- domain
- quality
- level
- intermediate
- agents
- backend-validation, ui-validation, security-validation, orchestrator
- created_date
- 2026-04-27
- status
- draft
Validation & Diagnostics
Overview
Structured process for comparing planned vs implemented work, generating diagnostic reports, and identifying gaps. Used by validation agents to provide concrete, evidence-based assessments.
Key Concepts
The Trust Problem
Agents will claim work is complete when it isn't. Validation must be:
- Observable — Based on test output, not agent claims
- Deterministic — Same input produces same verdict
- Evidence-based — Every finding references concrete code or test results
- Structured — Consistent format for easy human review
Patterns & Techniques
Planned vs Implemented Comparison
Step 1: Extract planned items From the spec, issue, or plan, extract a checklist of:
- Acceptance criteria
- Required endpoints/functions
- Expected model fields
- Required test coverage
- UI components specified
Step 2: Verify each item For each planned item, check:
- Does the code exist? (file search, grep)
- Does it match the specification? (read and compare)
- Is it tested? (find corresponding test)
- Does the test pass? (run and capture output)
Step 3: Generate drift report
## Drift Analysis: [Feature]
| Planned Item | Status | Evidence |
|-------------|--------|----------|
| [spec item] | ✅ Implemented | [file:line] |
| [spec item] | ⚠️ Partial | [what's missing] |
| [spec item] | ❌ Not found | [searched in...] |
| [unplanned] | ⚡ Scope creep | [file:line] |Diagnostic Report Template
## Diagnostic Report: [Component/Feature]
### Summary
[1-2 sentence verdict]
### Test Results[Actual test output — copy/paste, not paraphrased]
### Code Quality
| Metric | Result |
|--------|--------|
| Type hints present | ✅ / ❌ |
| Pydantic models used | ✅ / ❌ |
| Config class used (no hardcoded secrets) | ✅ / ❌ |
| Error handling present | ✅ / ❌ |
| Logger used (not print) | ✅ / ❌ |
### Findings
| # | Severity | Finding | Location | Recommendation |
|---|----------|---------|----------|----------------|
| 1 | [High/Med/Low] | [what] | [file:line] | [fix] |
### Coverage Gaps
[Code paths without tests]
### Verdict
✅ PASS | ⚠️ CONDITIONAL PASS | ❌ FAIL
[Explanation with evidence]HASTE-Specific Validation Checks
| Component | Must Verify |
|---|---|
| New API endpoint | Auth level, Pydantic validation, error codes, CORS |
| New processor | Config injection, logger usage, error handling |
| New data model | Pydantic BaseModel, field types, validation rules |
| New data layer | Abstract interface compliance, connection handling |
| New UI component | FluentUI usage, no alt frameworks, responsive |
| Geospatial code | CRS preservation, COG compliance, GDAL/rasterio usage |
Show full SKILL.md (136 more words)Show less
Feedback Loop
When validation reveals a miss:
- Document the miss in the diagnostic report
- Identify the pattern (was it a convention violation? missing test? spec ambiguity?)
- Propose a skill update or instruction addition to prevent recurrence
- Flag to the Orchestrator for tracking
Decision Framework
| Validation Result | Action |
|---|---|
| All checks pass, tests green | ✅ Approve |
| Minor issues, tests pass | ⚠️ Conditional — list issues for human review |
| Tests fail | ❌ Block — must fix before proceeding |
| Scope creep detected | ⚠️ Flag — human decides if extra work is acceptable |
| Spec ambiguity found | ⚠️ Flag — needs clarification before validation |
Common Pitfalls
- Accepting "tests passed" without seeing output — Always run and capture
- Validating only happy path — Check error handling and edge cases
- Skipping convention checks — HASTE has specific patterns that must be followed
- Not checking for scope creep — Extra changes can introduce regressions
© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .github/skills/validation-diagnostics of microsoft/haste.
Open the folder on GitHubat commit 079bd89
Compare with similar skills
Validation Diagnostics 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 |
|---|---|---|---|---|---|---|
| Validation Diagnostics this skillmicrosoft/haste | 106 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Building Pydantic AI Agentsdocling-project/docling | 68k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Datachain Knowledgedatachain-ai/datachain | 2.8k | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Fastcrudbenavlabs/fastcrud | 1.6k | — | ~5k | Automated safety check: Pass | MIT | |
| Building Pydantic AI Agentspydantic/pydantic-ai | 20k | — | ~8k | Automated safety check: Pass | MIT | |
| Investor Panel Stock Reviewwbh604/UZI-Skill | 7.1k | — | ~757 | Automated safety check: Pass | MIT |
Similar skills
Datachain Knowledge
datachain-ai/datachain
A skill your agent uses whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure…
Fastcrud
benavlabs/fastcrud
A skill your agent uses when building or modifying CRUD endpoints with FastCRUD (the fastcrud PyPI package) in a FastAPI project — covers FastCRUD, crudrouter, EndpointCreator, FilterConfig…
- Official
Building Pydantic AI Agents
pydantic/pydantic-ai
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns.
Investor Panel Stock Review
wbh604/UZI-Skill
Scores a stock through a panel of well-known investor personas, each applying their own method and returning a structured signal, then tallies the votes.
Fastapi
Open-TutorAi/open-tutor-ai-CE
FastAPI best practices and conventions. An agent skill from Open-TutorAi/open-tutor-ai-CE.
More from microsoft/haste
All 9 skills in this repo- Official
API Design
microsoft/haste
Guide for designing and documenting RESTful APIs. An agent skill from microsoft/haste.
- Official
Copilot CLI Modes
microsoft/haste
Comprehensive guide to all Copilot CLI running modes: Interactive, Plan, Autopilot, Fleet, Research, Chronicle, and Delegate.
- Official
Debug Test Failures
microsoft/haste
Systematic debugging workflow for test failures. An agent skill from microsoft/haste.
- Official
Dependency Update
microsoft/haste
Guide for safely updating project dependencies. An agent skill from microsoft/haste.
- Official
Imagery Provider Adaptation
microsoft/haste
Imagery provider adaptation skill for HASTE. An agent skill from microsoft/haste.
- Official
Security Analysis
microsoft/haste
Dependabot and security analysis skill for HASTE. An agent skill from microsoft/haste.
Related
Works with
Questions about Validation Diagnostics
What does Validation Diagnostics do?
Validation and diagnostic skill for HASTE. An agent skill from microsoft/haste. Validation Diagnostics is an agent skill from microsoft/haste, published by the product's own GitHub organization. Validation and diagnostic skill for HASTE.
When should I use Validation Diagnostics?
Validation Diagnostics fits situations like: : validate implementation; compare to spec; diagnostic report; implementation review.
How do I install Validation Diagnostics in Claude Code?
Run `npx skills add microsoft/haste --skill validation-diagnostics -a claude-code`. Or copy the skill folder (.github/skills/validation-diagnostics in microsoft/haste) into .claude/skills/validation-diagnostics in your project. Claude Code loads it when a task matches its description.
How do I install Validation Diagnostics in Codex?
Run `npx skills add microsoft/haste --skill validation-diagnostics -a codex`. Or copy the skill folder (.github/skills/validation-diagnostics in microsoft/haste) into .agents/skills/validation-diagnostics in your project. Codex loads it when a task matches its description.
Can I use Validation Diagnostics in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/haste --skill validation-diagnostics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/validation-diagnostics, .gemini/skills/validation-diagnostics, .github/skills/validation-diagnostics and .opencode/skills/validation-diagnostics in your project.
What does Validation Diagnostics need to run?
SKILL.md names no scripts, command-line tools or credentials: Validation Diagnostics is instructions for the agent only.
Does Validation Diagnostics access the network?
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.
Is Validation Diagnostics safe to install?
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.
What licence does Validation Diagnostics use?
Validation Diagnostics is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Validation Diagnostics use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Validation Diagnostics?
Skills that share tags, products or a category with Validation Diagnostics: Building Pydantic AI Agents (docling-project/docling, 68k stars), Datachain Knowledge (datachain-ai/datachain, 2.8k stars), Fastcrud (benavlabs/fastcrud, 1.6k stars) and Building Pydantic AI Agents (pydantic/pydantic-ai, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Validation Diagnostics?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/haste, which has 106 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 2, 2026.
Source: microsoft/haste on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.