write-spike

Use when starting a new initiative spike, investigating technical feasibility, assessing impact across services, or writing an engineering discovery document — produces a structured spike doc with diagrams and a private notes file

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 well-sequenced, highly actionable multi-phase investigation process with strong validation checkpoints and feedback loops. Its main weakness is progressive disclosure: it depends on a `spike-template.md` for its core deliverable format that is not actually shipped in the bundle, and the long process body is largely monolithic.

Suggestions

Ship the referenced `spike-template.md` (and `company-config.yaml`) as actual bundle files, or inline the spike-doc section structure so the 'REQUIRED REFERENCE' is not a dead link.

Trim the atmospheric framing in the opening paragraph ('spikes that changed architectural direction and spikes that were shelved because they were too shallow') to tighten token efficiency without losing the core principle.

Consider moving the detailed Phase 2 classification tables and Quality Gates into a referenced file to keep SKILL.md as a leaner overview while the body grows.

Dimension	Reasoning	Score
Conciseness	It assumes Claude's competence and avoids explaining basics (no 'what is a spike/Jira/Mermaid'), but the atmospheric opening ('spikes that changed architectural direction and spikes that were shelved') and a few redundancies ('Every phase is mandatory. Do not skip phases.') keep it from being perfectly lean.	2 / 3
Actionability	Concrete throughout: named subagents with exact duties, A/B1/B2/C classification, specific file-naming ('.<date>-<slug>.private.md'), exact commands (gh, curl), and a populated Quality Gates table — actionable instruction-only guidance.	3 / 3
Workflow Clarity	A clear 4-phase sequence with a Mermaid flowchart, mandatory-phase enforcement, a post-Phase-1 scope check, Quality Gates (3.4), and Self-Review/grill-me feedback loops; DB migrations include rollback plans and replication-lag monitoring, so destructive/batch operations are not left unvalidated.	3 / 3
Progressive Disclosure	References to `spike-template.md` ('REQUIRED REFERENCE') and `company-config.yaml` are clearly signaled and one-level-deep, but neither file exists in the bundle (only SKILL.md and config.json are present), so the disclosure structure is incomplete and the body carries most detail inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 strong: it pairs an explicit 'Use when' trigger clause with concrete deliverables and distinct, natural-sounding engineering terms. Voice is appropriately third-person ('produces'), and there is no vague fluff or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'investigating technical feasibility, assessing impact across services', and 'produces a structured spike doc with diagrams and a private notes file' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both: when ('Use when starting a new initiative spike, investigating...') and what ('produces a structured spike doc with diagrams and a private notes file').	3 / 3
Trigger Term Quality	Natural engineering terms a user would say — 'initiative spike', 'technical feasibility', 'impact across services', 'engineering discovery document' — give good coverage of likely triggers.	3 / 3
Distinctiveness Conflict Risk	The spike-doc-plus-private-notes niche with engineering-discovery triggers is distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: AndreJorgeLopes/proof-of-skill
Commit: 4a74f2c

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.