agentleFS
product-on-purposeproduct-on-purpose/pm-skills/skills/develop-spike-summary/SKILL.md

develop-spike-summary

Skill777 starsChanged 10 months agoApache-2.0View on GitHub

Documents the results of a completed technical or design spike, capturing the original question, approach, evidence-backed findings, and a clear proceed-or-not recommendation so the team does not re-litigate the exploration. Use once a time-boxed investigation has concluded. For the architecture decision the spike informs, use develop-adr instead; for research-based exploration, use discover-interview-synthesis.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After completing a time-boxed technical exploration

    line 20
  2. Distinctive:

    When evaluating technology choices or vendor options

    line 21
  3. Distinctive:

    After proof-of-concept work that needs to inform team decisions

    line 22
  4. Distinctive:

    When investigating feasibility of a proposed solution

    line 23
  5. Distinctive:

    Before committing engineering resources to a new approach

    line 24
  6. Distinctive:

    When asked to document a spike, follow these steps:

    line 35
  7. Distinctive:

    Document the time allocated (e.g., 3 days) and actual time spent.

    line 41
  8. Distinctive:

    Document what was learned, supported by concrete evidence - code samples, performance benchmarks, screenshots, or API responses.

    line 47
  9. Very specific:

    Use the template in references/TEMPLATE.md to structure the output.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

Spike Summary

A spike summary documents the results of a time-boxed exploration - a focused investigation to reduce uncertainty before committing to implementation. Spikes answer specific questions like "Can we integrate with this API?" or "Is this technology viable for our use case?" The summary captures findings so the team can make informed decisions without the spike participants needing to repeat explanations.

When to Use

  • After completing a time-boxed technical exploration
  • When evaluating technology choices or vendor options
  • After proof-of-concept work that needs to inform team decisions
  • When investigating feasibility of a proposed solution
  • Before committing engineering resources to a new approach

When NOT to Use

  • You are recording the resulting architecture decision itself -> use develop-adr; the spike informs, the ADR decides
  • The exploration was user research, not technical or design feasibility -> use discover-interview-synthesis
  • You want to propose the solution the spike pointed to -> use develop-solution-brief
  • The spike has not happened yet: this skill documents results; time-box and run the exploration first

Instructions

When asked to document a spike, follow these steps:

  1. State the Question Clearly Articulate the specific question the spike was designed to answer. Good spike questions are focused and answerable with the time-box available. If the question evolved during the spike, document both the original and final versions.
  2. Define the Time-Box Document the time allocated (e.g., 3 days) and actual time spent. If the spike exceeded its time-box, explain why and note any remaining work.
  3. Describe the Approach Explain what was tried, in what order, and why. This helps future readers understand the methodology and whether alternative approaches were considered.
  4. Present Findings with Evidence Document what was learned, supported by concrete evidence - code samples, performance benchmarks, screenshots, or API responses. Distinguish between verified findings and hypotheses that need more testing.
  5. Make a Clear Recommendation Answer the original question directly: proceed, do not proceed, or proceed with conditions. Avoid hedging - the team needs actionable guidance.
  6. Document Artifacts Link to any code, prototypes, diagrams, or documentation created during the spike. These artifacts often have ongoing value beyond the summary.
  7. Capture Open Questions Note what the spike didn't answer and what additional investigation might be needed.

Output Format

Use the template in references/TEMPLATE.md to structure the output. A complete spike summary fills every template section: Overview; Background; Approach; Findings; Recommendation; Artifacts; Open Questions; and Follow-up Items.

Quality Checklist

Before finalizing, verify:

  • Original question is clearly stated
  • Time-box is documented (allocated vs. actual)
  • Findings are supported by evidence, not just opinions
  • Recommendation directly answers the question
  • Artifacts (code, diagrams) are linked or attached
  • Open questions identify remaining unknowns

Examples

See references/EXAMPLE.md for a completed example.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.