Time-boxed technical spikes: resolve decisions before building
Create time-boxed technical spike documents for researching critical decisions before implementation — research questions, investigation plans, success criteria, evidence-based recommendations
- What
- Create time-boxed technical spike documents for researching critical decisions before implementation — research questions, investigation plans, success criteria, evidence-based recommendations
- Cost
- Free
- Needs
- a critical technical decision to research — the skill is a document template and methodology the agent follows, not software to install
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @github's skill for creating time-boxed technical spike documents that resolve critical decisions before implementation: one question per spike, with a full document template — Summary (spike objective, why it matters, timebox, decision deadline), Research Questions (primary + secondary), Investigation Plan (research tasks with a checklist, success criteria: the spike is complete only when a clear recommendation is documented and a proof of concept completed where applicable), Technical Context (related components, dependencies on other spikes/decisions, constraints), Research Findings (investigation results, prototype/testing notes, external resources), Decision (recommendation, rationale, implementation notes, follow-up actions), and Status History (🔴 Not Started → 🟡 In Progress → 🟢 Complete). File naming `[category]-[short-description]-spike.md` in a spikes directory; categories covered (API integration, architecture & design, performance & scalability, platform & infrastructure, security & compliance, UX); agent best practices (evidence-based decisions, clear recommendations, dependency tracking, outcome-focused — every spike must end in an actionable decision); and a 3-phase research strategy (gather → validate → decide). Honest caveats: methodology and template only — the agent still has to run the actual research; the tool references (search, fetch, codebase, runTasks, editFiles, vscodeAPI) are Copilot-agent conventions — adapt them to your own agent's tools. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Time-boxed technical spikes is a free Muse skill for creating time-boxed technical spike documents that resolve critical decisions before implementation, with one question per spike. It uses a document template covering summary, research questions, investigation plan and technical context, and a spike is complete only when a clear recommendation is documented and a proof of concept is completed where applicable.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 82701c2Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a critical technical decision to research — the skill is a document template and methodology the agent follows, not software to install Install "Time-boxed technical spikes: resolve decisions before building" for me. It gives my agent @github's technical-spike workflow: one question per spike; the full document template (Summary with objective/timebox/decision deadline, Research Questions, Investigation Plan with success criteria, Technical Context, Research Findings, Decision with recommendation and rationale, Status History); file naming [category]-[short-description]-spike.md; categories (API integration, architecture, performance, platform, security, UX); agent best practices (evidence-based, outcome-focused, one spike per question); and the 3-phase research strategy (gather → validate → decide). MIT-licensed. Repository: https://raw.githubusercontent.com/github/awesome-copilot/82701c24b99488536ca399ff4789a458b7a05db7/skills/create-technical-spike/SKILL.md Pinned version: install the code at commit 82701c24b99488536ca399ff4789a458b7a05db7 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "create-technical-spike". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. hand the agent the technical decision to research, the category, and the timebox; adapt the Copilot-agent tool references to your own agent's tools). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 82701c2 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.