prp-spike

Prove or disprove an idea by building the smallest throwaway artifact that could falsify it, in an isolated worktree, ending in a PROVEN / DISPROVEN / CONDITIONAL verdict backed by evidence - never a PR. Use when the user wants to "spike this", "build a proof of concept", "POC this", "prototype it to find out", asks "is this possible", "is this feasible", "does this fit our stack", or "would it be worth changing X to allow Y" and wants it settled by building rather than by analysis, wants to compare approaches on evidence before picking one, or invokes $prp-spike.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable 8-phase workflow with explicit gates and feedback loops. Its main weaknesses are some trimmable rationale prose and a missing mandatory-read template file (templates/spike-report.md) that breaks one navigation path.

Suggestions

Add the missing templates/spike-report.md to the bundle, or remove the 'mandatory read' references to it and inline the report skeleton directly in SKILL.md.

Trim norm-setting rationale sentences (e.g. 'DISPROVEN is a success. It bought a decision with evidence and closed a path that would otherwise have cost weeks.') to directive statements that consume fewer tokens.

Consider moving the long PRP store resolver bash block into a referenced script so the SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Dense and free of basic-concept padding (no 'what is a worktree'), but contains norm-setting rationale prose ('DISPROVEN is a success... closed a path that would otherwise have cost weeks'; 'an agent that has seen its results can reconstruct criteria that flatter them') that could be trimmed without losing guidance.	4 / 5
Actionability	Provides a copy-paste-ready bash resolver block, concrete commands (git switch -c spike/<slug>, mkdir -p), and exact file paths ($PRP_DIR/spikes/spike-<slug>.md); most guidance is executable with minor gaps where steps rely on reading referenced files.	4 / 5
Workflow Clarity	Clear 8-phase sequence with an explicit GATE in Phase 1 ('Do not build without it'), a pre-results re-read checkpoint in Phase 6, and a feedback loop ('re-run the inferred ones before finalizing'), giving explicit validation for a fragile process.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references (references/framing.md, evidence.md, handoff.md all exist), but templates/spike-report.md is cited as a mandatory read in Phase 1 and Phase 6 yet is absent from the bundle — a broken navigation target.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, concrete actions, comprehensive natural trigger phrases, and an explicit Use-when clause. It cleanly distinguishes the skill from related plan/implement/debug skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'building the smallest throwaway artifact that could falsify it', 'in an isolated worktree', 'ending in a PROVEN / DISPROVEN / CONDITIONAL verdict', 'never a PR' — with comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (prove/disprove by building a falsifying throwaway artifact ending in a verdict) and when ('Use when the user wants to...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases including synonyms and the invocation token: 'spike this', 'build a proof of concept', 'POC this', 'prototype it to find out', 'is this possible', 'is this feasible', 'does this fit our stack', plus '$prp-spike'.	5 / 5
Distinctiveness Conflict Risk	Clear niche — falsification-based spikes ending in a verdict and explicitly 'never a PR' — with distinct triggers that separate it from sibling plan/implement/debug skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Wirasm/prp
Path: .agents/skills/prp-spike/SKILL.md
Commit: d62c3ae

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.