Automated summary

Produces a concise markdown document recording a project's tech-stack choices with one-line reasons and rejected alternatives, laid out as tables.

Strengths

Enforces a fixed table schema with verbatim column names, so documents are comparable across projects
Requires a one-line reason for each choice and each rejected alternative, preventing essay-style output
Adapts the layers to the actual project rather than forcing a rigid template
Reads an existing project brief first and captures deferred sub-decisions separately

Limitations

Does not evaluate or validate the technical merit of choices; it only formats decisions already made
No handling of versioning, links to existing ADRs, or merging into a doc that already exists
Defaults to writing docs/tech-stack.md and assumes the user supplies the project context

When to use it

Use right after a stack decision is made, to capture the chosen components and why the alternatives lost without writing an essay.

When not to use it

Avoid it for deep technology comparisons or for authoring a full architecture specification.

Security analysis

Safe

Quality score82/100

The skill is a pure markdown documentation template with no declared tools, no executable commands, no network or filesystem operations beyond writing a single docs file as instructed. No obfuscation, exfiltration, or instruction-injection attempts were present in the content.

No concerns found

How this analysis is made

Examples

Document a new project stack

Write the tech stack doc for our new internal billing service. We're going with Go + PostgreSQL on the backend, React with Vite on the frontend, Docker on ECS for infra, and GitHub Actions for CI. Save it to docs/tech-stack.md.

Capture rejected alternatives

Create a tech-stack.md for this project based on the brief in docs/brief.md, and make sure every choice has the alternatives we considered listed with a one-line reason why we didn't pick them.

Add open sub-decisions

Document our stack decision doc: Next.js frontend, Supabase for data, Vercel for hosting. We haven't decided on auth or the email provider yet, so note those as open sub-decisions.

name: tech-stack-doc description: Generate a concise tech-stack decision doc (chosen stack + rejected alternatives, tabular) for a project. Use when the user asks to document/write/create a tech stack, stack decision doc, or "tech-stack.md".

Tech Stack Doc

Name: Tech Stack Decision Doc
Author: Skills Guide Bot

Produce a single markdown doc capturing stack choices and why alternatives were rejected. Keep every reason to one line — no essays.

Steps

If a project brief or similar context doc exists or is referenced, read it first.
Determine the layers relevant to this project (e.g. Backend, Frontend, Data persistence, Infra, CI). Don't force layers that don't apply.
For each component decision, pick one choice and a one-line reason.
For each choice, list the alternatives seriously considered and a one-line "why not" each.
Note any deferred/open sub-decisions at the bottom, if any.
Write to docs/tech-stack.md (or ask for the path if the project's doc conventions differ).

Output format

# Tech Stack — <Project Name>

| Layer | Component | Choice | Reason |
|---|---|---|---|
| <layer> | <component> | <choice> | <one-line reason> |

## Rejected alternatives

| Component | Option | Why not |
|---|---|---|
| <component> | <option> | <one-line reason> |

## Open sub-decisions

- <anything deferred, with a pointer to where it'll be resolved>

Rules

Column names above are fixed — reuse them verbatim across projects; only the row values change.
One row per decision, one line per reason. Full sentences not required.
Every "Choice" needs at least one row in "Rejected alternatives" unless it was genuinely uncontested (note why, e.g. "no viable alternative found").
Omit the "Open sub-decisions" section entirely if there are none.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/tech-stack-decision-doc-mvg6txhk' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/tech-stack-decision-doc-mvg6txhk/download' --output '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md.part' && mv '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md.part' '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md' && test -s '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/tech-stack-doc' && cp -R '.skill-downloads/tech-stack-decision-doc-mvg6txhk' '.claude/skills/tech-stack-doc'

Cursor

test -f '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md' && test -s '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/tech-stack-doc' && cp -R '.skill-downloads/tech-stack-decision-doc-mvg6txhk' '.cursor/skills/tech-stack-doc'

Codex

test -f '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md' && test -s '.skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/tech-stack-doc' && cp -R '.skill-downloads/tech-stack-decision-doc-mvg6txhk' '.agents/skills/tech-stack-doc'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/tech-stack-decision-doc-mvg6txhk'

openskills read 'tech-stack-decision-doc-mvg6txhk'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/tech-stack-decision-doc-mvg6txhk/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Supabase Docs Authoring

Documentation

Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.

Claude CodeintermediateSafe 108,544

Skills Guide Bot