repro-api

Reproduce an EmDash bug below the browser layer -- REST handlers, CLI, MCP, migrations, schema registry, or build tooling. No browser. Prefer a failing vitest test in the affected package, run in an attached container.

Quality

81%

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

Quality

Content

92%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 tight, highly actionable procedure with concrete commands, explicit validation checkpoints, and a feedback loop for matching the reported failure mode. Well-organized into clear sections with no need for bundle files.

Dimension	Reasoning	Score
Conciseness	Mostly lean, directive prose that assumes Claude's competence and avoids explaining known concepts; a few minor instances (intro restating the description, the fairly long 'When to skip' list) could be trimmed slightly.	4 / 5
Actionability	Provides fully executable, specific guidance — concrete commands (`pnpm --filter <package> test <path>`, `pnpm exec emdash ...`), exact file-path mappings, a test-naming template, and a scaffolding utility (`setupTestDatabase()`) — covering the common cases.	5 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation checkpoints ('confirm it fails for the reason reported', 'Confirm the failure mode matches') and an error-recovery feedback loop (lower confidence on adjacent failures).	5 / 5
Progressive Disclosure	A ~52-line single-purpose skill with no need for external references, organized into well-signaled sections (Environment, Do not, Procedure, When to skip, Output), matching the simple-skill exception for a 5.	5 / 5
	Total	19 / 20 Passed

Description

70%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 specific, well-scoped description that clearly carves out a niche and names concrete subsystems and a preferred reproduction method. Its main gap is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reproducing an EmDash bug that does not require a browser — in REST handlers, the CLI, MCP, migrations, the schema registry, or build tooling.'

Include a natural synonym or two (e.g. 'regression', 'repro') to broaden trigger coverage.

Name one or two additional concrete actions (e.g. 'write a failing test, run a repro script') to push specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	Names concrete targets (REST handlers, CLI, MCP, migrations, schema registry, build tooling) and a preferred action (a failing vitest test in an attached container), with minor coverage gaps rather than a comprehensive multi-action list.	4 / 5
Completeness	The 'what' is clear (reproduce an EmDash bug below the browser layer via a failing vitest test), but there is no explicit 'Use when...' trigger clause, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Strong natural terms for the audience ('reproduce', 'bug', 'REST', 'CLI', 'MCP', 'migrations', 'vitest test') plus the distinctive 'below the browser layer' phrasing, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The EmDash-scoped, below-browser niche with an explicit 'No browser' boundary and enumerated subsystems gives it a clear, distinct trigger set with minimal overlap risk.	5 / 5
	Total	16 / 20 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: emdash-cms/emdash
Path: infra/emdash-bot/.flue/skills/repro-api/SKILL.md
Commit: 9ca2de5

Reviewed: 3 hours 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.