CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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 instruction skill with clear sequencing and good single-file organization. Its main weakness is length: the reviewer checklist and duplicate worked examples push the token budget beyond what is strictly necessary for a capable agent.

Suggestions

Condense the 12-point reviewer investigation checklist into a tighter bullet list, trusting the principal-engineer-reviewer sub-agent's existing competence to derive the basics.

Reduce the three full worked examples to one representative end-to-end example plus a compact table of the others, cutting redundant tokens.

Move the long issue-body heredoc template to a reference file (or a script) and reference it, so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is detailed and well-structured but runs long (300+ lines), and the exhaustive 12-point reviewer checklist plus two full worked examples add tokens that partly explain context a capable agent could derive. It is mostly efficient but could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands (gh issue create with a complete heredoc body, gh label list) and concrete instruction prompts for the reviewer sub-agent, with specific placeholders rather than pseudocode.

3 / 3

Workflow Clarity

A clear five-step sequence is laid out with an ASCII overview, explicit checkpoints (clarification policy gating Step 2), and feedback guidance (re-validate after errors, confirm gh auth). Steps are well-sequenced with decision gates.

3 / 3

Progressive Disclosure

The skill is self-contained with no external bundle files; it is organized into clear top-level sections (Prerequisites, Workflow Overview, Steps 1-5, Design Principles, Commands Reference, Examples) with no nested references, appropriate for a single-file skill under the simple-skill guidance.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 high-quality description: concrete capabilities, rich natural trigger terms, explicit 'when' guidance, and a clearly distinct niche tied to a sibling skill. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Investigate a plain-language problem description', 'deeply exploring the codebase', 'create a structured GitHub issue with technical findings' — each a specific, discrete operation rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (investigate a problem, map to codebase, create structured GitHub issue) and 'when' via the 'Trigger keywords' clause, satisfying the explicit-trigger requirement for a top score.

3 / 3

Trigger Term Quality

Provides strong natural-language trigger coverage with explicit, natural keywords: 'spike, investigate, explore, research issue, technical investigation, create spike, new spike, feasibility, codebase exploration' that a user would plausibly say.

3 / 3

Distinctiveness Conflict Risk

The 'Prequel to build-from-issue' framing and spike-investigation niche give it a clear, distinctive trigger set unlikely to conflict with general issue-creation or build skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NVIDIA/OpenShell
Reviewed

Table of Contents

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.