Azure AI Projects Python SDK
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail.
Install Capture Project Learning
$ npx skills add shm11C3/HardwareVisualizer --skill capture-project-learning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shm11C3/HardwareVisualizer capture-project-learning --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/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/capture-project-learning .claude/skills/capture-project-learning && 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 "capture-project-learning" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/capture-project-learning into .claude/skills/capture-project-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-project-learning", 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/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/capture-project-learningType 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 shm11C3/HardwareVisualizer --skill capture-project-learning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shm11C3/HardwareVisualizer capture-project-learning --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/capture-project-learning .agents/skills/capture-project-learning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "capture-project-learning" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/capture-project-learning into .agents/skills/capture-project-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-project-learning", 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 shm11C3/HardwareVisualizer --skill capture-project-learning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shm11C3/HardwareVisualizer capture-project-learning --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/capture-project-learning .cursor/skills/capture-project-learning && 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 "capture-project-learning" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/capture-project-learning into .cursor/skills/capture-project-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-project-learning", 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/shm11C3/HardwareVisualizer.git --path .agents/skills/capture-project-learning--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 shm11C3/HardwareVisualizer --skill capture-project-learning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shm11C3/HardwareVisualizer capture-project-learning --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/capture-project-learning .gemini/skills/capture-project-learning && 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 "capture-project-learning" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/capture-project-learning into .gemini/skills/capture-project-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-project-learning", 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 shm11C3/HardwareVisualizer capture-project-learningInstalls 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 shm11C3/HardwareVisualizer --skill capture-project-learning -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/capture-project-learning .github/skills/capture-project-learning && 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 "capture-project-learning" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/capture-project-learning into .github/skills/capture-project-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-project-learning", 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 shm11C3/HardwareVisualizer --skill capture-project-learning -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shm11C3/HardwareVisualizer capture-project-learning --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/capture-project-learning .opencode/skills/capture-project-learning && 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 "capture-project-learning" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/capture-project-learning into .opencode/skills/capture-project-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-project-learning", 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
capture-project-learning- GitHub stars
- 183
- Token cost
- ~858 tokens
- SKILL.md length
- 375 words
- Files
- 2
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail.
- Works in 6 steps: Decide Whether It Is A Learning → Search Before Adding → Verify The Cause → …
- Asked to record learnings
- SKILL.md covers Goal, Workflow and Completion Criteria
- Calls npm and git
What it does
Capture Project Learning is an agent skill from shm11C3/HardwareVisualizer. Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail. Use when asked to record learnings, prevent the same AI mistake, update AGENTS/rules/hooks/skills, or when completed work reveals a reusable repository-specific lesson.
Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in AI & LLM Engineering. The repository describes itself as: A cross-platform hardware monitor with real-time metrics, local history, and customizable dashboards. The licence is GPL-3.0.
When your agent uses it
- Asked to record learnings
- Prevent the same AI mistake
- Update AGENTS/rules/hooks/skills
- Completed work reveals a reusable repository-specific lesson
Example prompts
- “/capture-project-learning”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit fc54f73. 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
Shell commands in SKILL.md call:
npmgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.
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
Capture Project Learning loads about 858 tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 375 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 shm11C3/HardwareVisualizer at commit fc54f73, republished under its GPL-3.0 licence (© shm11C3). 375 words, ~858 tokens.
Download SKILL.mdSave it as
.claude/skills/capture-project-learning/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- capture-project-learning
- description
- Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail. Use when asked to record learnings, prevent the same AI mistake, update AGENTS/rules/hooks/skills, or when completed work reveals a reusable repository-specific lesson.
Capture Project Learning
Goal
Convert experience into a small durable improvement without turning chat history into always-on context.
The lifecycle is:
observe -> verify -> record -> promote -> enforce -> revalidateWorkflow
1. Decide Whether It Is A Learning
Record one when at least one is true:
- the maintainer corrected an assumption or product interpretation;
- the same CI, review, environment, or implementation failure repeated;
- investigation found a non-obvious invariant or evidence path;
- an undocumented design decision materially changed implementation;
- a manual check can become a deterministic regression guard.
Do not record a guess, secret, credential, personal absolute path, temporary check state, or generic software-engineering advice.
2. Search Before Adding
Search docs/agents/lessons/, docs/design-principles.md, CONTEXT.md, ADRs,
architecture docs, scoped instructions, skills, tests, and CI. Update or
supersede an existing lesson instead of creating a duplicate.
3. Verify The Cause
Confirm the observation against current evidence. Prefer current code/tests,
leaf-job logs, runtime/SQLite data, rendered artifacts, release assets, and
current GitHub state. If the cause is not confirmed, record a candidate and do
not promote it as a rule.
Separate the durable invariant from time-specific evidence such as a dependency version, PR number, runner timing, or spec revision.
4. Add One Learning Record
Create one file under docs/agents/lessons/ using the required frontmatter in
that directory's README. Use an ID of the form LRN-YYYYMMDD-short-slug, update
the records index, and state exactly when the lesson must be revalidated.
Show full SKILL.md (153 more words)Show less
5. Promote To The Real Owner
Use this routing:
- vocabulary ->
CONTEXT.md; - cross-cutting decision lens ->
docs/design-principles.md; - specific trade-off -> ADR;
- current ownership/structure -> architecture doc or owner README;
- always-on AI constraint -> root or scoped
AGENTS.md; - path-specific AI constraint ->
.agents/rules/**; - repeated multi-step procedure ->
.agents/skills/**; - deterministic invariant -> test, non-mutating script, hook, or CI;
- expiring/environment fact -> learning record only.
Keep hooks cheap and deterministic. They may validate paths, schemas, links, generated-file edit attempts, or exact dependency invariants. They must not infer product meaning, clean-room contamination, or change kind.
6. Validate
Run:
npm run check:agent-guidance
git diff --checkRun any new focused regression test or script. Inspect the diff for duplicated or conflicting guidance.
Completion Criteria
A learning is complete when:
- its cause is labeled confirmed or candidate honestly;
- its durable rule has one canonical owner;
- AI entry points link to, rather than duplicate, detailed facts;
- deterministic behavior is enforced by a test/script/CI where practical;
- the record says when it can expire or must be revalidated.
© shm11C3, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/capture-project-learning of shm11C3/HardwareVisualizer.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit fc54f73
Compare with similar skills
Capture Project Learning 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 |
|---|---|---|---|---|---|---|
| Capture Project Learning this skillshm11C3/HardwareVisualizer | 183 | — | ~858 | Automated safety check: Pass | GPL-3.0 | |
| Azure AI Projects Python SDKmicrosoft/skills | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT | |
| AI Research Reproductionlllllllama/RigorPilot-Skills | 497 | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Onnxtxtonnx/onnx | 22k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Add Publication DocsRLinf/RLinf | 5.5k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Hugging Face API Tool Builderhuggingface/skills | 11k | 5 repos | ~1.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
AI Research Reproduction
lllllllama/RigorPilot-Skills
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.
Onnxtxt
onnx/onnx
Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.
Add Publication Docs
RLinf/RLinf
Adds a new publication page to the RLinf Sphinx docs (EN + ZH) and wires it into the Publications index/toctree.
- Official
Hugging Face API Tool Builder
huggingface/skills
Builds reusable command line scripts that fetch, enrich or process data from the Hugging Face API, aimed at chained, repeated or automated tasks.
Create Simple Prompt
pnp/copilot-prompts
This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…
More from shm11C3/HardwareVisualizer
Change Kind Naming
shm11C3/HardwareVisualizer
Decide the correct change kind and semantically align branch names, PR titles, commit prefixes, and PR template types.
Gh AI Review Triage
shm11C3/HardwareVisualizer
Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots.
Deliver Pull Request
shm11C3/HardwareVisualizer
Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion.
Hardwarevisualizer Design Review
shm11C3/HardwareVisualizer
Review or shape HardwareVisualizer product and architecture changes against the maintainer's design principles.
Verify Identity Contracts
shm11C3/HardwareVisualizer
Verify the id/key contract between backend producers and frontend consumers before implementing any change that joins, selects, persists, or attributes entities keyed by backend-produced ids (GPUs…
Related
Categories
Questions about Capture Project Learning
What does Capture Project Learning do?
Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail. Capture Project Learning is an agent skill from shm11C3/HardwareVisualizer. Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail.
When should I use Capture Project Learning?
Capture Project Learning fits situations like: asked to record learnings; prevent the same AI mistake; update AGENTS/rules/hooks/skills; completed work reveals a reusable repository-specific lesson.
How do I install Capture Project Learning in Claude Code?
Run `npx skills add shm11C3/HardwareVisualizer --skill capture-project-learning -a claude-code`. Or copy the skill folder (.agents/skills/capture-project-learning in shm11C3/HardwareVisualizer) into .claude/skills/capture-project-learning in your project. Claude Code loads it when a task matches its description.
How do I install Capture Project Learning in Codex?
Run `npx skills add shm11C3/HardwareVisualizer --skill capture-project-learning -a codex`. Or copy the skill folder (.agents/skills/capture-project-learning in shm11C3/HardwareVisualizer) into .agents/skills/capture-project-learning in your project. Codex loads it when a task matches its description.
Can I use Capture Project Learning 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 shm11C3/HardwareVisualizer --skill capture-project-learning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/capture-project-learning, .gemini/skills/capture-project-learning, .github/skills/capture-project-learning and .opencode/skills/capture-project-learning in your project.
What does Capture Project Learning need to run?
Going by SKILL.md and its folder, Capture Project Learning needs the command-line tools its instructions call (npm and git).
Does Capture Project Learning access the network?
SKILL.md contains no URLs. Its commands use npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Capture Project Learning 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 Capture Project Learning use?
Capture Project Learning is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Capture Project Learning use?
About 858 tokens (SKILL.md is roughly 3.4k 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 Capture Project Learning?
Skills that share tags, products or a category with Capture Project Learning: Azure AI Projects Python SDK (microsoft/skills, 3.1k stars), AI Research Reproduction (lllllllama/RigorPilot-Skills, 497 stars), Onnxtxt (onnx/onnx, 22k stars) and Add Publication Docs (RLinf/RLinf, 5.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Capture Project Learning?
shm11C3 (a GitHub user) maintains it in shm11C3/HardwareVisualizer, which has 183 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.
Source: shm11C3/HardwareVisualizer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.