spike

Throwaway experiments to validate an idea before build.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/software-development/spike/SKILL.md

Quality

Content

77%

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 highly actionable, well-sequenced procedural guide with concrete commands, tables, and templates, and a clear validated feedback loop. Its main weaknesses are mild verbosity in the peripheral GSD-integration material and a single-file structure with no progressive disclosure of reusable templates.

Suggestions

Tighten or condense the 'If the user has the full GSD system installed' section to a brief pointer, trimming peripheral tokens.

Extract the verdict markdown template and the comparison head-to-head table format into a reference file (e.g., references/verdict-templates.md) and link to it from the body to improve progressive disclosure.

Consider moving the research-tool command catalogue into a short reference so the core method reads even leaner.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural without padding Claude's basic knowledge, but the multi-paragraph GSD-integration section and some surrounding prose could be tightened, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	It provides fully executable terminal/write_file/delegate_task commands, concrete Given/When/Then spike tables, and copy-paste-ready verdict and head-to-head markdown templates, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The decompose -> research -> build -> verdict loop is clearly numbered with an explicit Align checkpoint before building, a VALIDATED/PARTIAL/INVALIDATED verdict validation step, and an iterate-on-findings feedback loop, matching the anchor for clear sequence with explicit checkpoints.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headings, but the ~185-line skill is a single self-contained file with no external references, and detailed templates (verdict, head-to-head) could be externalized, fitting the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concise and non-vague, naming a clear domain and core action, but it omits an explicit 'Use when...' trigger clause and offers only thin natural-language trigger coverage. This leaves it adequate but not exemplary across all four dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete user phrases such as 'spike this out', 'is this even possible?', or 'compare A vs B' to lift completeness and trigger-term quality.

Enumerate two or three concrete actions (e.g., 'decompose an idea into feasibility questions, build throwaway prototypes, and write a VALIDATED/PARTIAL/INVALIDATED verdict') to improve specificity.

Sharpen distinctiveness by contrasting the spike niche against planning (e.g., 'before committing to a real build; use the plan skill for production work').

Dimension	Reasoning	Score
Specificity	Names the domain ('Throwaway experiments') and one action ('validate an idea') but does not list multiple specific concrete actions, matching the anchor that names domain and some actions yet is not comprehensive.	2 / 3
Completeness	It answers 'what' (throwaway experiments to validate an idea) but 'when' is only implied via 'before build' with no explicit 'Use when...' clause, so completeness is capped at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Includes some relevant keywords a user might say ('experiments', 'validate an idea', 'before build') but lacks common variations and strong natural trigger phrases, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The throwaway-experiment/pre-build niche is somewhat specific, but without explicit triggers it could still overlap with similar skills like plan or sketch, matching the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/software-development/spike/SKILL.md
Commit: 74a56b7

Reviewed: 4 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.