create-spike

Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings. Prequel to build-from-issue — maps vague ideas to concrete, buildable issues. Trigger keywords - spike, investigate, explore, research issue, technical investigation, create spike, new spike, feasibility, codebase exploration.

Quality

81%

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

71%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.

A thorough, highly actionable workflow skill with concrete commands and a complete issue template, sequenced clearly with an evidence-threshold checkpoint. It is somewhat repetitive and monolithic, with content that could be offloaded to reference files.

Suggestions

Remove the 'Useful Commands Reference' table and the 'Design Principles' section where they restate guidance already covered in Steps 1–5, or trim them to only net-new information to improve conciseness.

Move the full issue-body heredoc template and/or the three worked examples into a references/ file (e.g. ISSUE_TEMPLATE.md and EXAMPLES.md) and link to them from Step 4, enabling progressive disclosure and shrinking the SKILL.md overview.

Add an explicit post-creation verification step (e.g. `gh issue view <number> --json ...` to confirm labels and body rendered correctly) to strengthen the workflow's validation checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's intelligence (no explanation of gh/git basics), but the Design Principles section restates step guidance and the Useful Commands Reference duplicates commands already shown inline, so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready executable guidance — a complete `gh issue create` heredoc with a full issue-body template, concrete `gh label list` commands, and an explicit subagent invocation — covering the common cases fully.	5 / 5
Workflow Clarity	A clear five-step sequence with an evidence-threshold validation checkpoint (state:validated vs state:needs-info) and explicit label-selection rules; the only minor gap is no post-creation verification of the created issue.	4 / 5
Progressive Disclosure	Well-organized with clear section headers, but all content — the large issue-body template and three detailed worked examples — is inlined into a single ~310-line SKILL.md with no bundle files or one-level-deep references to split it out.	3 / 5
	Total	15 / 20 Passed

Description

91%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.

A strong description that clearly states what the skill does and when to use it, with comprehensive natural trigger terms and a distinct niche. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'deeply exploring the codebase', 'create a structured GitHub issue with technical findings', 'maps vague ideas to concrete, buildable issues' — but coverage is bounded to one workflow rather than comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' (investigate a problem, explore the codebase, create a structured GitHub issue) and 'when' via an explicit trigger-keywords clause, matching the top anchor.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger terms including synonyms — 'spike, investigate, explore, research issue, technical investigation, create spike, new spike, feasibility, codebase exploration' — terms a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche as the 'prequel to build-from-issue' spike workflow with distinctive 'spike'/'create spike' triggers, though 'investigate'/'explore' carry minor overlap risk with general exploration skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/OpenShell
Path: .agents/skills/create-spike/SKILL.md
Commit: 292559c

Reviewed: 5 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.