dogfood-as-user

How to dogfood and verify a Gini behavior change by driving a real chat turn as a real user would. Use when verifying that the agent reaches for a tool or path on its own — a behavioral steer, a new tool, an INSTRUCTIONS.md change, or a dispatch/provider/memory/skill change — or before claiming a steer "works". Enforces bare, uncoached prompts so the test measures the default, not instruction-following.

Quality

86%

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 well-structured, highly actionable skill body that gives concrete commands and explicit good/bad prompt examples within a clear sequenced procedure. The only minor weakness is incidental motivational prose that slightly pads the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly lean and free of concept-explanation padding, but the 'Proven here' anecdote and a few motivational sentences ('the only real test is...') could be trimmed without losing instructional value.	4 / 5
Actionability	Fully executable guidance with copy-paste-ready commands ('tmux new-session -d -A -s gini-<instance> ...', 'gini status --instance <instance>', 'gini chat send <session> "<prompt>"', 'gini browser disconnect --instance <instance>') and concrete good/bad prompt examples covering the common cases.	5 / 5
Workflow Clarity	A clear 6-step procedure with explicit checkpoints (confirm gateway up via '"ok": true', observe rendering, judge honestly), but it lacks an explicit fix-and-retry feedback loop even though the task is non-destructive and does not strictly require one.	4 / 5
Progressive Disclosure	A short (<50 line), single-purpose skill with no need for external references, organized into clearly labeled sections (the one rule, Procedure, Safety, After, Provider caveat), satisfying the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

87%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 what the skill does and when to use it, with concrete trigger phrases drawn from the target audience's natural vocabulary. It is distinct from other skills and carries low conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('dogfood and verify a Gini behavior change by driving a real chat turn', 'Enforces bare, uncoached prompts', 'measures the default, not instruction-following'), but it is a single-purpose process rather than a broad list of capabilities, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('How to dogfood and verify a Gini behavior change by driving a real chat turn as a real user would') and when ('Use when verifying that the agent reaches for a tool or path on its own ... or before claiming a steer works') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of audience-natural triggers ('a behavioral steer, a new tool, an INSTRUCTIONS.md change, or a dispatch/provider/memory/skill change', "before claiming a steer 'works'"), though heavily domain-jargon-laden with a few common synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (dogfooding Gini behavior changes via bare real-user chat turns) with distinct, specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: Open-Curiosity/gini-agent
Path: .claude/skills/dogfood-as-user/SKILL.md
Commit: 6c5d85e

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.