Automated summary
This skill runs a structured investigation of technical alternatives and produces a decision memo recommending the least-regret option, backed by evidence and tradeoff analysis.
Strengths
- Enforces seven explicit comparison dimensions (implementability now, dependencies, reversibility, migration cost, operational burden, failure mode, evidence quality)
- Filters out fake options unavailable in the current environment and compares only materially distinct alternatives
- States plainly when evidence is thin and names the next discriminating check instead of guessing
- Relies on a mandated decision-memo template, making deliverables comparable across decisions
Limitations
- Tightly coupled to the groundtruth-kb repository: it depends on the .harness-baseline-configuration/rules/template-decision-memo.md template
- No real prototyping or benchmarking: the assessment stays document-based
- The file is a generated projection, so changes must go through the baseline rather than direct edits
Use it when you must choose between several technical solutions or tools and justify the choice to a team or a governance body.
Avoid it for direct implementation or code review work, or when the project does not follow groundtruth-kb's decision-memo template.
Security analysis
SafeThe skill is a procedural investigation guide. It permits Bash and Agent, but contains no destructive commands, credential handling, exfiltration, obfuscation, or safety-disabling instructions. Tool use is consistent with legitimate architecture and tool-selection research.
No concerns found
How this analysis is madeExamples
Investigate whether we should keep our current Postgres setup or migrate to DynamoDB for the multi-tenant API, and give me a decision memo with a least-regret recommendation.Compare GitHub Actions, GitLab CI and Buildkite for our monorepo, focusing on reversibility and operational burden, and recommend one option with evidence.We are considering moving our frontend from Vue 2 to Svelte. Investigate the realistic alternatives under our current constraints and write the decision memo.name: gtkb-alternatives-investigation description: Investigate technical alternatives and recommend the least-regret option with evidence, tradeoffs, reversibility, and implementation impact. Use for architecture choices, tool selection, and solution comparison. argument-hint: [decision] allowed-tools: Bash, Read, Grep, Glob, Agent license: "Proprietary - Remaker Digital" compatibility:
- claude-code >= 1.0 metadata: project: groundtruth-kb category: investigation
<!-- THIS FILE IS A PROJECTION, NOT CANONICAL. Projected from the neutral harness baseline by the GT-KB projection engine. Do not edit here: change the baseline (.harness-baseline-configuration) and re-project with `gt harness project goose`. If a needed change cannot be made through the baseline and re-projection, file a work item against the projector (GOV-HARNESS-NEUTRAL-BASELINE-001 obligation 6). -->
Alternatives Investigation
Investigate distinct solution paths and recommend the best option under the real project constraints.
Default Deliverable
Use .harness-baseline-configuration/rules/template-decision-memo.md.
Required Comparison Dimensions
Check each option for:
- implementability now
- dependency or approval requirements
- reversibility
- migration cost
- operational burden
- failure mode
- evidence quality
Output Rules
- Compare only materially distinct options.
- Reject fake options that are not actually available in the current environment.
- Name the minimum-regret recommendation, not just the most ambitious one.
- If the evidence is thin, say so and identify the next discriminating check.
© 2026 Remaker Digital, a DBA of VanDusen & Palmeter, LLC. All rights reserved.
<!-- GTKB-GOOSE-SKILL-ADAPTER-BEGIN Generated by: scripts/harness_projection/project_harness.py Generated at: content-addressed 322adadac338 Canonical source: .harness-baseline-configuration/skills/gtkb-alternatives-investigation/SKILL.md Canonical source sha256: 322adadac3386102406797c581cfd67743203a4f567b6b0dd5f81bc740067967 GTKB-GOOSE-SKILL-ADAPTER-END -->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 filesThis 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.mdFrom the root of a test project, save the file as .skill-downloads/technical-alternatives-investigation-mu7w4g3q/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/technical-alternatives-investigation-mu7w4g3q' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/technical-alternatives-investigation-mu7w4g3q/download' --output '.skill-downloads/technical-alternatives-investigation-mu7w4g3q/SKILL.md.part' && mv '.skill-downloads/technical-alternatives-investigation-mu7w4g3q/SKILL.md.part' '.skill-downloads/technical-alternatives-investigation-mu7w4g3q/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.
Tools declared by the author (check availability in your agent): Bash, Read, Grep, Glob, Agent
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/technical-alternatives-investigation-mu7w4g3q/SKILL.md' && test -s '.skill-downloads/technical-alternatives-investigation-mu7w4g3q/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/gtkb-alternatives-investigation' && cp -R '.skill-downloads/technical-alternatives-investigation-mu7w4g3q' '.claude/skills/gtkb-alternatives-investigation'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 installationopenskills install './.skill-downloads/technical-alternatives-investigation-mu7w4g3q'openskills read 'technical-alternatives-investigation-mu7w4g3q'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 syncManual 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/technical-alternatives-investigation-mu7w4g3q/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.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.