system-prompts

Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.

Quality

87%

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

86%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 dense, highly actionable prompt-authoring style guide with strong structure and validation cues. Its one notable defect is a broken progressive-disclosure reference: small-models.md is declared a MUST-read but is absent from the bundle.

Suggestions

Add the missing small-models.md to the bundle (e.g. under references/) or remove the "MUST read small-models.md" pointer so the signaled reference resolves.

Add an explicit validate→fix→retry loop for prompt authoring (e.g. after drafting, run the Checklist, fix violations, re-check) to lift workflow clarity.

Consider splitting the larger reference material (e.g. the full tool-prompt anatomy or per-tool examples) into one-level-deep reference files with clear links, rather than keeping it all inline.

Dimension	Reasoning	Score
Conciseness	Exemplary density: "Load-bearing tokens only; every bullet adds a claim", tactical bullets capped at 5–12 words, symbol shorthand (→, =, +/<), and tables throughout, assuming Claude's competence without explaining what a system prompt or RFC 2119 is. The Bad/Good blocks are pedagogically load-bearing rather than padding. Not 4 because virtually every token earns its place.	5 / 5
Actionability	Concrete and executable throughout: the RFC keyword table, the "state once: > RFC 2119 applies..." template, the "Quick check `X? Y.`" rule, ordered front/back matter, named tool examples (read.md, lsp.md, ast_edit, hashline.md), and a 6-part tool-prompt anatomy. Not 4 because guidance is copy-applicable with specific examples covering common cases.	5 / 5
Workflow Clarity	Clear sequencing via ordered front-matter (1–5) and back-matter (1–3) lists, the tool-prompt anatomy (1–6), and a closing Checklist plus Anti-Patterns table that act as validation. Not 5 because there is no explicit validate→fix→retry feedback loop for the main authoring task; not 3 because checkpoints (Checklist, Anti-Patterns) are present.	4 / 5
Progressive Disclosure	In-body structure is strong with clear section headers, but the one signaled external reference — "MUST read small-models.md" — does not exist in the bundle (no references/, scripts/, or assets/ directories), so a critical navigation pointer is broken. Not 4 because the missing MUST-read file breaks easy navigation; not 2 because the in-body organization itself is good, not minimal.	3 / 5
	Total	17 / 20 Passed

Description

88%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, specific description that clearly states both capabilities and a concrete use-trigger, with a distinctive prompt-authoring niche. Minor synonym coverage and slight breadth in the trigger phrase keep trigger-term quality and distinctiveness just below perfect.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Write system prompts, tool docs, and agent definitions" plus "Project tag conventions + RFC 2119 keywords + dense compression" — giving comprehensive coverage of the skill's domain. Not 4 because coverage is broad and specific rather than having minor gaps.	5 / 5
Completeness	Explicitly answers what ("Write system prompts, tool docs, and agent definitions...") and when ("Use when authoring or editing any prompt the model reads") with a concrete trigger phrase. Not 4 because both halves are explicit and concrete, not merely adequate.	5 / 5
Trigger Term Quality	Natural terms like "system prompts", "tool docs", "agent definitions", and "authoring or editing any prompt" map to what a user would say, but common synonyms ("instructions", "system messages", "prompt engineering") are missing. Not 5 due to those synonym gaps; not 3 because coverage is genuinely good.	4 / 5
Distinctiveness Conflict Risk	The combination of system prompts, tool docs, agent definitions, and RFC 2119/tag conventions is a clear niche with distinct triggers, but "editing any prompt the model reads" is broad enough to risk minor overlap with general editing skills. Not 5 because of that breadth; not 3 because the what-portion is distinctive.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: can1357/oh-my-pi
Path: .omp/skills/system-prompts/SKILL.md
Commit: cdb9c4d

Reviewed: 1 day 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.