Spike Skill: Validate Ideas Before Building with Hermes Agent

The Spike skill is a structured way to run throwaway experiments that answer a specific feasibility question. You reach for it when you need to know whether something works before you commit to a full implementation. It is bundled with Hermes Agent and lives at skills/software-development/spike.

What it does

Spike turns a vague "I wonder if X works" into a repeatable loop: decompose the idea into testable questions, research the options, build the smallest thing that answers the question, and write a verdict. The output is disposable code and a clear yes/no/maybe that tells you what to do next.

Before you start

Hermes Agent must be running with the Spike skill loaded. It is bundled by default, so no separate install is needed.
The skill works on Linux, macOS, and Windows.
You need a project directory where the spikes/ folder will be created. The skill assumes you are already in a repo or working directory.
For research steps, Hermes tools like web_search, web_extract, and terminal must be available. If you have Context7 MCP configured, the skill can use mcp_*_resolve-library-id and mcp_*_query-docs as well.
If the full GSD system is installed (via npx get-shit-done-cc --hermes), the skill will prefer gsd-spike for persistent state and MANIFEST tracking. This standalone version is for users who do not have or do not want the full system.

Core method

Every spike follows this loop, regardless of scale:

decompose  →  research  →  build  →  verdict
   ↑__________________________________________↓
                  iterate on findings

1. Decompose

Break the user's idea into 2-5 independent feasibility questions. Each question is one spike. Present them as a table with Given/When/Then framing:

#	Spike	Validates (Given/When/Then)	Risk
001	websocket-streaming	Given a WS connection, when LLM streams tokens, then client receives chunks < 100ms	High
002a	pdf-parse-pdfjs	Given a multi-page PDF, when parsed with pdfjs, then structured text is extractable	Medium
002b	pdf-parse-camelot	Given a multi-page PDF, when parsed with camelot, then structured text is extractable	Medium

Spike types:

standard, one approach answering one question
comparison, same question, different approaches (shared number, letter suffix a/b/c)

Good spike questions: specific feasibility with observable output. Bad spike questions: too broad, no observable output, or just "read the docs about X".

Order by risk. The spike most likely to kill the idea runs first. No point prototyping the easy parts if the hard part doesn't work.

Skip decomposition only if the user already knows exactly what they want to spike and says so. Then take their idea as a single spike.

2. Align (for multi-spike ideas)

Present the spike table. Ask: "Build all in this order, or adjust?" Let the user drop, reorder, or re-frame before you write any code.

3. Research (per spike, before building)

Spikes are not research-free, you research enough to pick the right approach, then you build. Per spike:

Brief it. 2-3 sentences: what this spike is, why it matters, key risk.
Surface competing approaches if there's real choice:

Approach	Tool/Library	Pros	Cons	Status
...	...	...	...	maintained / abandoned / beta

Pick one. State why. If 2+ are credible, build quick variants within the spike.
Skip research for pure logic with no external dependencies.

Use Hermes tools for the research step:

web_search("python websocket streaming libraries 2025"), find candidates
web_extract(urls=["https://websockets.readthedocs.io/..."]), read the actual docs (returns markdown)
terminal("pip show websockets | grep Version"), check what's installed in the project's venv

For libraries without docs pages, clone and read their README.md / examples/ via read_file. Context7 MCP (if the user has it configured) is also a good source, mcp_*_resolve-library-id then mcp_*_query-docs.

4. Build

One directory per spike. Keep it standalone.

spikes/
├── 001-websocket-streaming/
│   ├── README.md
│   └── main.py
├── 002a-pdf-parse-pdfjs/
│   ├── README.md
│   └── parse.js
└── 002b-pdf-parse-camelot/
    ├── README.md
    └── parse.py

Bias toward something the user can interact with. Spikes fail when the only output is a log line that says "it works." The user wants to feel the spike working. Default choices, in order of preference:

A runnable CLI that takes input and prints observable output
A minimal HTML page that demonstrates the behavior
A small web server with one endpoint
A unit test that exercises the question with recognizable assertions

Depth over speed. Never declare "it works" after one happy-path run. Test edge cases. Follow surprising findings. The verdict is only trustworthy when the investigation was honest.

Avoid unless the spike specifically requires it: complex package management, build tools/bundlers, Docker, env files, config systems. Hardcode everything, it's a spike.

Building one spike, a typical tool sequence:

terminal("mkdir -p spikes/001-websocket-streaming")
write_file("spikes/001-websocket-streaming/README.md", "# 001: websocket-streaming\n\n...")
write_file("spikes/001-websocket-streaming/main.py", "...")
terminal("cd spikes/001-websocket-streaming && python3 main.py")
# Observe output, iterate.

Parallel comparison spikes (002a / 002b), delegate. When two approaches can run in parallel and both need real engineering (not 10-line prototypes), fan out with delegate_task:

delegate_task(tasks=[
    {"goal": "Build 002a-pdf-parse-pdfjs: ...", "toolsets": ["terminal", "file", "web"]},
    {"goal": "Build 002b-pdf-parse-camelot: ...", "toolsets": ["terminal", "file", "web"]},
])

Each subagent returns its own verdict; you write the head-to-head.

5. Verdict

Each spike's README.md closes with:

## Verdict: VALIDATED | PARTIAL | INVALIDATED

### What worked
- ...

### What didn't
- ...

### Surprises
- ...

### Recommendation for the real build
- ...

VALIDATED = the core question was answered yes, with evidence. PARTIAL = it works under constraints X, Y, Z, document them. INVALIDATED = doesn't work, for this reason. This is a successful spike.

Comparison spikes

When two approaches answer the same question (002a / 002b), build them back to back, then do a head-to-head comparison at the end:

## Head-to-head: pdfjs vs camelot

| Dimension | pdfjs (002a) | camelot (002b) |
|-----------|--------------|----------------|
| Extraction quality | 9/10 structured | 7/10 table-only |
| Setup complexity | npm install, 1 line | pip + ghostscript |
| Perf on 100-page PDF | 3s | 18s |
| Handles rotated text | no | yes |

**Winner:** pdfjs for our use case. Camelot if we need table-first extraction later.

Frontier mode (picking what to spike next)

If spikes already exist and the user says "what should I spike next?", walk the existing directories and look for:

Integration risks, two validated spikes that touch the same resource but were tested independently
Data handoffs, spike A's output was assumed compatible with spike B's input; never proven
Gaps in the vision, capabilities assumed but unproven
Alternative approaches, different angles for PARTIAL or INVALIDATED spikes

Propose 2-4 candidates as Given/When/Then. Let the user pick.

Output

Create spikes/ (or .planning/spikes/ if the user is using GSD conventions) in the repo root
One dir per spike: NNN-descriptive-name/
README.md per spike captures question, approach, results, verdict
Keep the code throwaway, a spike that takes 2 days to "clean up for production" was a bad spike

When not to use it

The source lists three clear exclusions:

The answer is knowable from docs or reading code, just do research, don't build
The work is production path, use the plan skill instead
The idea is already validated, jump straight to implementation

Limits and gotchas

Spikes are disposable by design. Do not clean them up for production. If you find yourself spending two days refactoring a spike, you missed the point.
The verdict is only as good as the depth of your investigation. One happy-path run is not enough.
Avoid complex tooling unless the spike specifically requires it. Hardcode everything.
The skill assumes Hermes tools are available. If web_search or web_extract are not configured, research steps will fail.

Related skills

sketch, for early ideation before a spike
subagent-driven-development, for delegating work to subagents
plan, for production-path work after validation

Attribution

Adapted from the GSD (Get Shit Done) project's /gsd-spike workflow, MIT © 2025 Lex Christopherson (gsd-build/get-shit-done). The full GSD system offers persistent spike state, MANIFEST tracking, and integration with a broader spec-driven development pipeline; install with npx get-shit-done-cc --hermes --global.

Spike Skill for Hermes Agent: Validate Ideas Before Building