New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Tech Selection Research

by aAAaqwq in aAAaqwq/AGI-Super-Team

A skill your agent uses when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型"…

MITAuto-check: notesBackend & APIs

Install Tech Selection Research

skills CLI
$ npx skills add aAAaqwq/AGI-Super-Team --skill tech-selection-research -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aAAaqwq/AGI-Super-Team tech-selection-research --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tech-selection-research .claude/skills/tech-selection-research && rm -rf skills-src

Use ~/.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/

Facts

Skill name
tech-selection-research
GitHub stars
105
Token cost
~1.6k tokens
SKILL.md length
804 words
Files
8 (incl. scripts, references)
Skills in repo
167
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型"…

  • Works in 6 steps: Frame The Decision → Choose Mode → Use Source Hierarchy → …
  • The user wants to research
  • SKILL.md covers Use This Skill For, Do Not Do, Workflow and Important Guardrails, plus 3 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Tech Selection Research is an agent skill from aAAaqwq/AGI-Super-Team. Use when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型", "compare Spring Boot vs NestJS", "写 ADR", "评估是否适合", "PoC 方案", or "technology radar".

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/evaluation-framework.md`, `references/output-templates.md` and `references/source-hierarchy.md`).

It sits in Backend & APIs, covering Backend development and Architecture decision records. It works with FastAPI, NestJS and Spring Boot. The repository describes itself as: An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters. The licence is MIT.

When your agent uses it

  • The user wants to research
  • Evaluate a technology
  • Engineering tool for product R&D decision-making
  • Such as 调研 FastAPI

Example prompts

  • “调研 FastAPI”
  • “compare Spring Boot vs NestJS”
  • “评估是否适合”
  • “/tech-selection-research”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, WebSearch, WebFetch, Read, Write, Glob, Grep

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Frame The Decision
  2. Choose Mode
  3. Use Source Hierarchy
  4. Evaluate On Standard Dimensions
  5. Produce Decision Outputs
  6. Use The Matrix Script When Helpful

What it can do on your machine

Read from SKILL.md and the folder at commit 331ecd3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • WebSearch
    • WebFetch
    • Read
    • Write
    • Glob
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Tech Selection Research loads about 1.6k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 804 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, WebSearch, WebFetch, Read, Write, Glob, Grep

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); the scripts in this folder are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 331ecd3, republished under its MIT licence (© aAAaqwq). 804 words, ~1,646 tokens.

Download SKILL.mdSave it as .claude/skills/tech-selection-research/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
tech-selection-research
description
Use when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型", "compare Spring Boot vs NestJS", "写 ADR", "评估是否适合", "PoC 方案", or "technology radar".
allowed-tools
Bash, WebSearch, WebFetch, Read, Write, Glob, Grep
disable-model-invocation
true
context
fork

Tech Selection Research

Research a technology or framework for product R&D decisions. The goal is not a generic overview. The goal is a decision-ready output with evidence, tradeoffs, ADR draft, and validation plan.

Use This Skill For

  • Researching a single technology or framework for adoption
  • Comparing 2-4 candidate options for a project
  • Producing an ADR draft for architecture or framework selection
  • Defining a PoC plan and validation checklist
  • Producing a trend update for an already adopted technology

Do Not Do

  • Do not invent benchmark numbers
  • Do not recommend based only on popularity
  • Do not ignore migration cost or team capability
  • Do not give an absolute answer when key project constraints are missing

Workflow

1. Frame The Decision

Convert "research X" into a decision statement:

  • What is being chosen?
  • For which product or engineering context?
  • New build or brownfield migration?
  • What are the hard constraints: language, cloud, compliance, hiring, timeline?

If constraints are missing, make minimal assumptions and label them explicitly.

2. Choose Mode

Pick the lightest mode that matches the request:

  • Quick Scan: one technology, fast assessment
  • Shortlist Comparison: 2-4 candidates
  • Decision Pack: decision-ready report + ADR + PoC
  • Trend Update: latest releases, roadmap, upgrade risks
Quick Scan Workflow

Skip weighted matrix and ADR. Output:

  1. Technology positioning and history
  2. Fit / not-fit summary for the given context
  3. Radar classification: Adopt / Trial / Assess / Hold
  4. Key risks (top 3-5)
  5. Verdict: worth shortlisting or not, with reasoning
Shortlist Comparison Workflow

Use steps 1, 3, and 4 from the main workflow. Output:

  1. Candidate landscape (full universe, then scored shortlist)
  2. Unified dimension comparison table
  3. Exclusion rationale for dropped candidates
  4. Recommended shortlist with brief justification per option
Decision Pack Workflow

Follow the full workflow (steps 1-6). This is the default for any non-trivial selection.

Note: Decision Pack consumes 40-60% of the context window (loading references, multiple WebSearch/WebFetch calls, generating a 300-400 line report). If your current session already has substantial conversation history, run /clear first or start a new session to avoid mid-report context compression.

Trend Update Workflow

Skip candidate landscape and weighted matrix. Focus on delta since last assessment. Output:

  1. Recent releases, breaking changes, deprecations
  2. Roadmap / RFC / proposal summary
  3. Maturity change vs last assessment (radar shift)
  4. Community sentiment changes or emerging concerns
  5. Upgrade or replacement risks
  6. Whether the current adoption decision still holds
3. Use Source Hierarchy

Use sources in this order:

  1. Official docs, release notes, roadmap, RFCs, maintainer material
  2. Foundation or standards bodies, major engineering blogs, InfoQ, Thoughtworks
  3. Community tutorials only for supplemental explanation

When current information matters, verify with current sources. Distinguish:

  • Verified fact
  • Inference from sources
  • Requires PoC or benchmark validation

For source rules and evidence labels, read references/source-hierarchy.md.

Show full SKILL.md (352 more words)Show less
4. Evaluate On Standard Dimensions

Use the standard dimensions unless the user provides their own:

  • Business fit
  • Architecture fit
  • Team capability fit
  • Delivery speed
  • Runtime and scalability
  • Operability and observability
  • Security and compliance
  • Ecosystem maturity
  • Migration cost
  • Long-term evolution

Dimension definitions and scoring guidance are in references/evaluation-framework.md.

Before scoring, map the broader competitor universe. If the space includes multiple paradigm-level alternatives, do not compare only one or two obvious products. Make explicit:

  • the full candidate universe worth mentioning
  • the scored shortlist
  • why some important alternatives were not fully scored
5. Produce Decision Outputs

Default output should contain:

  1. Executive summary (include radar classification: Adopt / Trial / Assess / Hold)
  2. Decision context and assumptions
  3. Candidate landscape
  4. Evidence-based comparison
  5. Recommendation with "recommended when" and "not recommended when"
  6. Risks, unknowns, and tradeoffs
  7. Community negative feedback and criticism
  8. Non-fit scenarios
  9. Important cautions before adoption
  10. PoC plan
  11. ADR draft
  12. Tracking plan

Output structure and ADR template are in references/output-templates.md.

6. Use The Matrix Script When Helpful

If you have structured scores, use:

bash
python3 "$CLAUDE_SKILL_DIR/scripts/build_decision_matrix.py" <input.json>

$CLAUDE_SKILL_DIR is set automatically by Claude Code to the skill's root directory. If running outside Claude Code, substitute the absolute path.

The script expects JSON with weights and options. See the script docstring for shape.

Important Guardrails

  • Every recommendation must include:
    • Why it fits
    • Why it may fail
    • What must be validated next
  • Every performance or cost claim must cite a source or be marked needs PoC
  • Keep alternatives visible. Do not analyze only the named tool if realistic substitutes exist
  • Brownfield decisions must include migration and rollback considerations

Language

  • Top-level section headings: use English exactly as defined in the output template
  • Body content and sub-headings: follow the user's input language
  • Evidence labels (Verified, Inference, Needs PoC): always in English

Output Location

Save the report in the current working directory with the naming pattern: {technology}-decision-pack-{yyyy-mm-dd}.md

For Quick Scan, use {technology}-quick-scan-{yyyy-mm-dd}.md. For Trend Update, use {technology}-trend-update-{yyyy-mm-dd}.md.

Files To Read

  • Read references/evaluation-framework.md for scoring dimensions and ATAM-style tradeoff prompts
  • Read references/source-hierarchy.md for source priority and evidence labeling
  • Read references/output-templates.md for the decision-pack structure, ADR template, and PoC template

© aAAaqwq, MIT. 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 7 other files (scripts, references) in skills/tech-selection-research of aAAaqwq/AGI-Super-Team.

  • SKILL.md
  • references/evaluation-framework.md
  • references/output-templates.md
  • references/source-hierarchy.md
  • references/weights-core-business.json
  • references/weights-mvp.json
  • references/weights-platform.json
  • scripts/build_decision_matrix.py

Open the folder on GitHubat commit 331ecd3

Compare with similar skills

Tech Selection Research 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.

Tech Selection Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tech Selection Research this skillaAAaqwq/AGI-Super-Team105—~1.6kAutomated safety check: NotesMIT
Spring Bootericrisco/rsc-harness174—~4kAutomated safety check: PassMIT
PayRam Checkout IntegrationPayRam/payram-mcp158—~3.4kAutomated safety check: NotesNone
API Designericrisco/rsc-harness174—~3.1kAutomated safety check: PassMIT
Payram Webhook IntegrationPayRam/payram-mcp158—~5.2kAutomated safety check: NotesNone
Csharp Dotnetericrisco/rsc-harness174—~3.3kAutomated safety check: PassMIT

Similar skills

  • Spring Boot

    ericrisco/rsc-harness

    A skill your agent uses when building, reviewing, testing, securing or configuring a Spring Boot 4 / Framework 7 backend — controllers, services, Spring Data JPA, application.yml…

    174 GitHub stars~4k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • PayRam Checkout Integration

    PayRam/payram-mcp

    Adds crypto checkout to a web app with PayRam: create a payment from your backend, send the customer to the payment page, then confirm the result.

    158 GitHub stars~3.4k tokensUpdated today
    Backend & APIsAuto-check: notes

  • API Design

    ericrisco/rsc-harness

    A skill your agent uses when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency —…

    174 GitHub stars~3.1k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Payram Webhook Integration

    PayRam/payram-mcp

    Integrate PayRam webhook handlers for real-time payment and payout event notifications.

    158 GitHub stars~5.2k tokensUpdated today
    Backend & APIsAuto-check: notes

  • Csharp Dotnet

    ericrisco/rsc-harness

    A skill your agent uses when writing, reviewing, testing, or shipping C / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in…

    174 GitHub stars~3.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Twenty Syncable Entity Validation

    twentyhq/twenty

    Contributor guide for step three of adding a syncable entity to the Twenty server: write the validator, the migration action builder and the orchestrator wiring.

    58k GitHub stars~3.3k tokensUpdated today
    Backend & APIsAuto-check passed

More from aAAaqwq/AGI-Super-Team

All 167 skills in this repo

  • Content Creator

    aAAaqwq/AGI-Super-Team

    Create SEO-optimized marketing content with consistent brand voice.

    105 GitHub starsUsed in 3 repos~1.9k tokens
    Auto-check passed

  • Financial Calculator

    aAAaqwq/AGI-Super-Team

    Advanced financial calculator with future value tables, present value, discount calculations, markup pricing, and compound interest.

    105 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed

  • Bankr Signals

    aAAaqwq/AGI-Super-Team

    Transaction-verified trading signals on Base blockchain. An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub starsUsed in 2 repos~3.3k tokens
    Auto-check passed

  • Erc 8004

    aAAaqwq/AGI-Super-Team

    Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents).

    105 GitHub starsUsed in 2 repos~1.2k tokens
    Auto-check passed

  • Frontend Design Ultimate

    aAAaqwq/AGI-Super-Team

    Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed.

    105 GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed

  • Zsxq Smart Publish

    aAAaqwq/AGI-Super-Team

    Publish and manage content on 知识星球 (zsxq.com). An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Tech Selection Research

What does Tech Selection Research do?

A skill your agent uses when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型"…. Tech Selection Research is an agent skill from aAAaqwq/AGI-Super-Team. Use when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型", "compare Spring Boot vs NestJS", "写 ADR", "评估是否适合", "PoC 方案", or "technology radar".

When should I use Tech Selection Research?

Tech Selection Research fits situations like: the user wants to research; evaluate a technology; engineering tool for product R&D decision-making; such as 调研 FastAPI.

How do I install Tech Selection Research in Claude Code?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill tech-selection-research -a claude-code`. Or copy the skill folder (skills/tech-selection-research in aAAaqwq/AGI-Super-Team) into .claude/skills/tech-selection-research in your project. Claude Code loads it when a task matches its description.

How do I install Tech Selection Research in Codex?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill tech-selection-research -a codex`. Or copy the skill folder (skills/tech-selection-research in aAAaqwq/AGI-Super-Team) into .agents/skills/tech-selection-research in your project. Codex loads it when a task matches its description.

Can I use Tech Selection Research 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 aAAaqwq/AGI-Super-Team --skill tech-selection-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tech-selection-research, .gemini/skills/tech-selection-research, .github/skills/tech-selection-research and .opencode/skills/tech-selection-research in your project.

What does Tech Selection Research need to run?

Going by SKILL.md and its folder, Tech Selection Research needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, WebSearch, WebFetch, Read, Write, Glob, Grep.

Does Tech Selection Research 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 Tech Selection Research safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Tech Selection Research use?

Tech Selection Research 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 Tech Selection Research use?

About 1.6k tokens (SKILL.md is roughly 6.6k 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 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Tech Selection Research?

Skills that share tags, products or a category with Tech Selection Research: Spring Boot (ericrisco/rsc-harness, 174 stars), PayRam Checkout Integration (PayRam/payram-mcp, 158 stars), API Design (ericrisco/rsc-harness, 174 stars) and Payram Webhook Integration (PayRam/payram-mcp, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tech Selection Research?

aAAaqwq (a GitHub user) maintains it in aAAaqwq/AGI-Super-Team, which has 105 GitHub stars. The repository holds 167 skills in this directory. The repository was last updated on October 8, 2026.

Source: aAAaqwq/AGI-Super-Team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.