Is the Tech Assessment skill free?

Yes. The skill itself is free from zircote-plugins/sigint. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Tech Assessment SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Tech Assessment?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Tech Assessment with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Tech Assessment

Weighted build-vs-buy scoring with TRL, hype cycle and an anti-inflation check

by zircote-plugins · zircote-plugins/sigint

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Aug 5, 2026
Environment: Claude Code 2.x (agent harness)

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Aug 5, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Asked it to settle a real decision — DuckDB-on-Parquet versus ClickHouse Cloud for a 6-engineer SaaS with 40 GB in Postgres and 8-20s dashboards — and answered the same question first without the skill. Both runs said fix Postgres rollups first, but the skill's weighted matrix (Build 2.65 vs Buy 3.60, arithmetic shown) flipped the fallback from DuckDB to ClickHouse Cloud and explained why: buy wins on the two heaviest factors, build wins only on the lightest. It also forced an assumptions block, an inflation check, cost bands, a $900/mo billing-alarm mitigation, and four monitoring indicators with numeric decision thresholds the baseline had none of. One packaging catch worth knowing: the body loads protocols/TREND-INDICATORS.md from the plugin root, so a plain copy of the skill folder leaves that reference dangling — the install command above copies it in.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Tech Assessment does

A technology evaluation framework that turns 'should we adopt X' into a scored decision: TRL level, Gartner hype-cycle position, a weighted build-vs-buy matrix with the arithmetic shown, and INC/DEC/CONST trend indicators on every technology mentioned. Triggers on build vs buy questions, tech stack analysis, technical feasibility, architecture assessment, and technical due diligence, with extra checklists for AI/ML, fintech, healthcare and infrastructure targets. Its scoring calibration and inflation check exist specifically to stop the assessment ending in 'it depends'.

How to install Tech Assessment

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Tech Assessment

/tech-assessment Weighted build-vs-buy scoring with TRL, hype cycle and an anti-inflation check

It also activates on plain-language prompts like these:

Should we build our own feature-flag system or buy LaunchDarkly?
Evaluate moving our analytics stack from DuckDB to ClickHouse
Do technical due diligence on this acquisition target's AI stack

Frequently asked questions

Is the Tech Assessment skill free?: Yes. The skill itself is free from zircote-plugins/sigint. SkillProof publishes the install command and an independent test verdict at no cost.
Does Tech Assessment work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 5, 2026. Verdict: Tested · Works. Asked it to settle a real decision — DuckDB-on-Parquet versus ClickHouse Cloud for a 6-engineer SaaS with 40 GB in Postgres and 8-20s dashboards — and answered the same question first without the skill. Both runs said fix Postgres rollups first, but the skill's weighted matrix (Build 2.65 vs Buy 3.60, arithmetic shown) flipped the fallback from DuckDB to ClickHouse Cloud and explained why: buy wins on the two heaviest factors, build wins only on the lightest. It also forced an assumptions block, an inflation check, cost bands, a $900/mo billing-alarm mitigation, and four monitoring indicators with numeric decision thresholds the baseline had none of. One packaging catch worth knowing: the body loads protocols/TREND-INDICATORS.md from the plugin root, so a plain copy of the skill folder leaves that reference dangling — the install command above copies it in.
What is the Tech Assessment SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Tech Assessment?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Tech Assessment with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.