spike

Throwaway experiments to validate an idea before build.

Quality

64%

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

75%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 workflow with concrete commands, templates, and a clear decompose-to-verdict loop. It scores solidly across all dimensions, with only minor trimming and a slightly long single-file structure leaving room to reach the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is dense with specific, useful guidance and does not explain concepts Claude already knows (no 'what a PDF is' padding), though a few sections (GSD routing, attribution) and minor redundancies ('throwaway' stated in multiple places) could be trimmed. Not 5 because of those minor padding instances; not 3 because the bulk of tokens earn their place.	4 / 5
Actionability	Provides concrete, executable guidance throughout — specific terminal/write_file/delegate_task calls, a directory tree, and README/verdict templates — with only minor gaps (placeholders like '...' in example file contents). Not 5 because the examples are illustrative rather than fully copy-paste ready; not 3 because the guidance is concrete and executable, not pseudocode.	4 / 5
Workflow Clarity	The decompose → research → build → verdict loop is explicitly sequenced with checkpoints (the Align gate before building, the iterate-on-findings loop, and the verdict validation step). Not 5 because validation/feedback loops are implicit rather than spelled out as validate→fix→retry; not 3 because checkpoints are clearly present and the sequence is coherent.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references and no bundle files, and inline templates are appropriate for a workflow skill. Not 5 because the single file runs long (~190 lines) and some templates (head-to-head comparison, verdict) could live in separate reference files; not 3 because structure is clear and references are not buried.	4 / 5
	Total	16 / 20 Passed

Description

53%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 concise and names a clear niche, but it lacks an explicit "Use when..." trigger clause and a richer vocabulary of natural trigger terms, leaving it mid-range across most dimensions. Adding trigger guidance and synonyms would lift completeness and trigger_term_quality.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger situations (e.g., 'Use when the user wants to spike out an idea, compare approaches, or check feasibility before committing to a build') to raise completeness above the 3 cap.

Broaden trigger vocabulary with natural synonyms users actually say — 'spike', 'prototype', 'proof of concept', 'feasibility', 'compare A vs B' — to improve trigger_term_quality.

List one or two more concrete actions (e.g., 'compare approaches' or 'surface unknowns') to move specificity from a single action toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (throwaway experiments) and one concrete action ("validate an idea before build"), but does not enumerate several specific actions, matching the 1-2-actions anchor. Not 4 because it lacks a broader list of specific actions; not 2 because it does name a concrete action beyond the domain.	3 / 5
Completeness	Has a clear "what" (throwaway experiments to validate an idea) but no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline. Not 4 because "when" is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	Includes some natural phrases ("throwaway experiments", "validate an idea", "before build") but misses common synonyms a user would say such as "spike", "prototype", "proof of concept", or "feasibility". Not 4 because coverage is thin with several natural terms missing; not 2 because the phrases present are reasonably natural rather than purely generic.	3 / 5
Distinctiveness Conflict Risk	The throwaway/feasibility-experiment framing carves a clear niche distinct from production build or plain research, with only minor overlap risk against closely related skills like plan or sketch. Not 5 because it could still overlap with those adjacent planning/exploration skills.	4 / 5
	Total	13 / 20 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: 6327930

Reviewed: 3 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.