gpt-5-6-prompt-builder

Build, transform, audit, and migrate prompts for GPT-5.6 Sol using outcome-first contracts, explicit success criteria, evidence and tool rules, approval boundaries, output requirements, and stop conditions. Use when someone asks for a GPT-5.6 prompt, wants an existing prompt optimized for GPT-5.6, or needs a prompt stack adapted from an older model.

Quality

90%

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

88%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.

An instruction-only skill with strong actionability and a well-sequenced, validation-gated workflow anchored by a copy-paste prompt template. It is somewhat long for a single file with minor internal repetition and no external reference split.

Suggestions

Consolidate the repeated 'ask for the smallest missing field' guidance into one canonical location to trim redundancy and shorten the body.

Consider moving the task-specific additions or the canonical prompt shape into a referenced file so the SKILL.md overview stays leaner and models progressive disclosure.

Tighten the transformation-rules list by merging closely related bullets (e.g., the autonomy/approval and evidence bullets share themes) to reduce token load.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly assumes Claude's competence without explaining basic concepts, but at ~165 lines it repeats a few directives (e.g., "ask for the smallest missing field" appears in both the transformation rules and elsewhere) that could be tightened.	4 / 5
Actionability	Provides a copy-paste canonical prompt shape template, concrete transformation rules, task-specific addition checklists, and an explicit READY/BLOCKED response contract that fully specify execution.	5 / 5
Workflow Clarity	A numbered operating contract, a completeness gate as an explicit validation checkpoint, an ordered questioning protocol, and a BLOCKED→ask→reassess feedback loop give a clear sequenced workflow with checkpoints.	5 / 5
Progressive Disclosure	No bundle files exist, so all content is inline; the body exceeds 50 lines but is well-organized into clearly headed sections with no nested references, placing it just below the simple-skill full-mark exception.	4 / 5
	Total	18 / 20 Passed

Description

92%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 precise, third-person description that pairs four concrete capabilities with an explicit Use-when trigger clause tailored to GPT-5.6. Trigger coverage is strong but leaves room for a few additional natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ("Build, transform, audit, and migrate prompts") plus seven named contract mechanisms (outcome-first contracts, success criteria, evidence/tool rules, approval boundaries, output requirements, stop conditions), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (build/transform/audit/migrate prompts with named contract elements) and when ("Use when someone asks for a GPT-5.6 prompt, wants an existing prompt optimized for GPT-5.6, or needs a prompt stack adapted from an older model") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ("asks for a GPT-5.6 prompt", "existing prompt optimized for GPT-5.6", "prompt stack adapted from an older model") but a few synonyms or shorthand variants are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (GPT-5.6 Sol prompts) with distinct, model-specific triggers and minimal overlap with general prompt or writing skills.	5 / 5
	Total	19 / 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: am-will/codex-skills
Path: skills/gpt-5-6-prompt-builder/SKILL.md
Commit: 9f954c3

Reviewed: 21 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.