probe

Answer one question that can't be settled by reading or arguing — build the smallest throwaway thing that makes the answer visible, inside a timebox, against a decision rule declared before the build starts. Returns a 4-line finding (Q / Tried / Found / Decides) plus a manipulable micro-world when the thing has a visible surface, then deletes the spike. Use when the user says "spike this", "try both and see", "we won't know until we build it", "is X fast enough", "which of A or B", "prototype it first", when an interview hits "I don't know yet" on something no one can know, or when `sightline` resolves a PROBE row. Standalone: /probe <question> [--rule "..."] [--box "..."].

Quality

94%

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

88%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 tight, highly actionable guide with a clear sequenced workflow and explicit validation gates for its destructive operations. Its only gaps are minor: a little narrative that could be trimmed and a single-file structure that, while well-organized, has no progressive-disclosure references.

Suggestions

Tighten the illustrative anecdotes (transit-API timestamps, the 'seventeen spikes' story) to one or two lines each so the body fully hits the lean/efficient bar.

Consider extracting the GOOD/BAD decision-rule examples or the micro-world kind/table into a one-level-deep reference file to improve progressive-disclosure navigation for the longer sections.

Dimension	Reasoning	Score
Conciseness	Dense and purposeful with no basic-concept padding and every section earning its place, but a few narrative flourishes (the transit-API timestamp anecdote, 'seventeen this way') could be trimmed while preserving the point — efficient with minor instances of over-explanation, matching score 4 rather than the fully lean 5.	4 / 5
Actionability	Provides concrete executable guidance — the exact 4-line finding format with a worked example, GOOD/BAD decision-rule examples, quarantine paths, `sight spike`/`sight burn` commands, and a micro-world HTML spec — fully actionable and copy-paste ready for the common cases.	5 / 5
Workflow Clarity	The probe workflow is clearly sequenced (refuse → rule → timebox → quarantine → build → manipulable → hand seam → numbered Ending) with explicit validation checkpoints (instrument self-check before findings, `burn` refusing until the finding is on disk) and feedback loops (refuse → re-scope cheaper question → DEFER); the destructive spike-deletion has validation, so the cap-3 does not apply.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is a single self-contained file with well-organized, clearly-headed sections and no nested references; good structure, but at ~230 lines it exceeds the under-50-line simple-skill exception that would allow a 5, so it sits at 4.	4 / 5
	Total	18 / 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 specific, trigger-rich, and explicitly covers both what the skill does and when to invoke it, using third-person voice throughout. It is a strong, low-conflict description with no notable weaknesses.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'build the smallest throwaway thing', 'Returns a 4-line finding', 'plus a manipulable micro-world', 'deletes the spike' — with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what (build spike, return 4-line finding + micro-world, delete spike) and when (a 'Use when...' clause with concrete trigger phrases), matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say — 'spike this', 'try both and see', 'we won't know until we build it', 'is X fast enough', 'which of A or B', 'prototype it first' — including synonyms and an interview trigger.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear spike/probe-for-decisions niche with distinct triggers and a standalone invocation form, giving minimal overlap risk with other 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: MrToxy/claude-skills
Path: probe/SKILL.md
Commit: 66c7102

Reviewed: 2 hours 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.