Automated summary
Executes a taskrail task of kind spike: a time-boxed investigation that ends in a documented, reproducible decision rather than production code.
Strengths
- Breaks the investigation into three clear stages (frame, investigate, decide) with human gates on frame and decide
- Requires a complete decision artifact covering verdict, evidence, options, recommendation and what would change the decision
- Demands reproducibility by recording exact commands, versions, commits and primary sources
- Explicitly separates deciding from adopting, pushing adoption into follow-up tasks
Limitations
- Assumes the taskrail skill and its procedure are already installed
- Provides no document template or tooling, only the stages and expected fields
- Human gates depend on someone being available to approve or reject
Use it when a backlog task is a spike, such as evaluating a tool, library or approach before committing to it.
Avoid it for implementing a feature or writing production code, since a spike must end in a decision, not code.
Security analysis
SafeThis is a pure process/workflow skill describing stages (frame, investigate, decide) for a time-boxed investigation. It contains no commands, no code to execute, no network calls, no credential handling, and explicitly forbids writing production code. The only actions it instructs are drafting and committing a markdown artifact in the repository, which is benign and gated by a human review step. It does depend on an external 'taskrail' skill and a metadata source URL, but nothing is fetched or executed by this file.
No concerns found
How this analysis is madeExamples
Run the spike taskrail task for TASK-142: decide whether we should adopt Zod or Valibot for runtime validation in our API layer.Work the spike TASK-87: investigate whether switching our queue from Redis to Postgres-backed jobs is viable, time-boxed to one day.Execute the spike task in .taskrail/ for evaluating Turborepo against Nx for our monorepo build, and give me the decision document.name: taskrail-spike description: Execute a taskrail task of kind spike — a time-boxed investigation that ends in a documented, reproducible decision rather than production code. Use when working a backlog task whose kind is spike, such as evaluating a tool, library or approach. license: MIT metadata: source: https://github.com/alexkander/tools-and-skills/tree/main/tools/taskrail
taskrail-spike
Follow the taskrail skill's procedure; this skill defines the stages. A spike produces a
decision, not code: write no production code, and keep any throwaway code outside the
repository or clearly marked as such.
frame — gate: always
Draft the artifact with: the Question; what Evidence would answer it; the Approach; and the Limits — the time box and what the investigation will not cover. Commit the draft, so it is not lost while the task waits. At the gate, the human agrees on the question and the approach.
investigate — gate: none
Gather evidence that someone else can reproduce. Record the exact commands, versions and commits, and link primary sources. Prefer measuring to reasoning, and running the thing to reading about it. Note anything you could not verify.
decide — gate: always
Complete the artifact:
- Verdict — the first line of the document.
- Question.
- Evidence — measurements and findings, with sources.
- Options considered.
- Recommendation.
- What would change the decision.
- How to reproduce.
Commit it. At the gate, the human accepts or rejects the decision. Adopting it is follow-up work: open tasks for it rather than doing it here.
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/taskrail-spike-investigation-mu0qzo41/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/taskrail-spike-investigation-mu0qzo41' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/taskrail-spike-investigation-mu0qzo41/download' --output '.skill-downloads/taskrail-spike-investigation-mu0qzo41/SKILL.md.part' && mv '.skill-downloads/taskrail-spike-investigation-mu0qzo41/SKILL.md.part' '.skill-downloads/taskrail-spike-investigation-mu0qzo41/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/taskrail-spike-investigation-mu0qzo41/SKILL.md' && test -s '.skill-downloads/taskrail-spike-investigation-mu0qzo41/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/taskrail-spike' && cp -R '.skill-downloads/taskrail-spike-investigation-mu0qzo41' '.claude/skills/taskrail-spike'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/taskrail-spike-investigation-mu0qzo41'openskills read 'taskrail-spike-investigation-mu0qzo41'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/taskrail-spike-investigation-mu0qzo41/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.