Production prompt engineering for GPT-5.6.
Audit. Optimize. Evaluate. Ship.
SOL ENGINE combines an installable agent skill with two local, deterministic tools: a static prompt audit and an evaluation regression gate. The skill supplies the engineering workflow; the tools make selected checks repeatable. They do not call a model, rewrite files, or decide whether a prompt is better on their own.
Use it to remove behavioral ambiguity while preserving output schemas, permissions, tool contracts, and business rules. A shorter prompt is a candidate, not proof of improvement.
An illustrative cleanup, not a measured model result:
Before
Always inspect the repository before editing. Be concise. Think carefully.
Always inspect the repository before editing. Complete the requested implementation,
then run the relevant tests. Preserve existing user changes unrelated to the request.
Return JSON with exactly these keys:
- summary: concise description of the changes
- tests: validation commands run and their outcomes
Do not modify files outside the repository.
Candidate
Inspect the repository before editing.
Work only inside the repository. Preserve existing user changes unrelated to the
request. Complete the requested implementation, then run the relevant tests.
Return JSON with exactly these keys:
- summary: concise description of the changes
- tests: validation commands run and their outcomes
The candidate removes duplication and vague style instructions while retaining the permission boundary, completion behavior, and output contract. Compare it against the original on representative cases before rollout.
| Capability | What it provides | Boundary |
|---|---|---|
| Prompt audit | Stable findings for duplication, vague directives, long tool descriptions, and profile-specific contract gaps | Heuristics require review |
| Surgical optimization | A workflow for separating behavior from redundant procedure | Preserves explicit contracts and trust layers |
| Migration review | Required compatibility changes separated from optional measured candidates | Does not guess runtime defaults |
| Evaluation gate | Baseline/candidate aggregation with quality, token, latency, and cost thresholds | Uses measurements you supply |
| Source grounding | A dated map to official OpenAI documentation | Changeable facts must be rechecked |
Install the nested skill from the public repository:
npx skills add wp-a/gpt-5.6-prompt-engine --skill gpt-5-6-prompt-engine -g -yAsk Codex to use its built-in $skill-installer with the GitHub tree URL:
$skill-installer install https://github.com/wp-a/gpt-5.6-prompt-engine/tree/main/skills/gpt-5-6-prompt-engine
The Codex installer places the skill under $CODEX_HOME/skills/gpt-5-6-prompt-engine and makes it available on the next turn. Start a new turn or restart a client that does not hot reload skills.
main tracks the latest repository state. Immutable tag pins will be documented once a release exists.
Invoke it by name and provide the prompt, tool stack, migration, or evaluation goal:
Use $gpt-5-6-prompt-engine to audit this coding-agent prompt, preserve its JSON
schema and write boundary, and return findings plus a minimal candidate rewrite.
The skill's default sequence is audit, classify constraints, optimize surgically, evaluate against a controlled baseline, and ship only after the gate passes. See the complete examples:
Both CLIs use only the Python 3.10+ standard library and have zero dependencies beyond Python. They need no API key and make no network request.
audit_prompt.py accepts a text prompt or a JSON tool stack, writes findings to stdout, and leaves the input unchanged. Profiles are general, agent, and research; output can be Markdown or JSON.
python skills/gpt-5-6-prompt-engine/scripts/audit_prompt.py tests/fixtures/duplicate-prompt.txt --profile agentUse - as the input path to read plain text from stdin. Findings are deterministic review signals, not semantic proof of a defect.
compare_eval_runs.py compares records with matching IDs, aggregates available metrics, and exits with status 2 when a configured regression gate fails.
python skills/gpt-5-6-prompt-engine/scripts/compare_eval_runs.py examples/eval-data/baseline.jsonl examples/eval-data/candidate.jsonl --max-success-rate-drop 0 --max-token-increase-pct 5Additional gates cover mean latency and cost per successful task. Quality, required evidence, and reliability should pass before efficiency metrics justify rollout.
Store one attempt per line in each JSONL file. id and success are required. Resource fields are optional, but a metric is comparable only when it is present for every record in both runs.
{"id":"case-001","success":true,"latency_ms":842,"input_tokens":910,"output_tokens":184,"reasoning_tokens":96,"cost_usd":0.0124}Use the same non-empty ID set for baseline and candidate. success must represent a predeclared task contract, not a post-hoc judgment. Token counts are nonnegative integers; latency and cost are nonnegative finite numbers. Start with the checked-in baseline JSONL sample.
Keep lifecycle operations in the same manager that created the global install:
npx skills update gpt-5-6-prompt-engine -g -ynpx skills remove gpt-5-6-prompt-engine -g -yThese commands apply only to installs managed by Agent Skills CLI.
The Codex installer deliberately refuses to overwrite an existing destination. Remove an existing Codex-managed copy with the controls available in that Codex client, then invoke the main URL for the latest repository state. The Agent Skills CLI lifecycle commands above do not manage Codex installs.
Start a new turn or restart clients that cache installed skills.
Only if you copied the skill manually, update it by replacing that copied gpt-5-6-prompt-engine directory and remove it by deleting only that directory. This filesystem guidance does not apply to manager-owned installs. Removing an installed copy does not delete this repository or evaluation data stored elsewhere.
skills/gpt-5-6-prompt-engine/
SKILL.md installable workflow
agents/openai.yaml interface metadata
references/ patterns, migration, evaluation, sources
scripts/ deterministic audit and comparison CLIs
examples/
*.md end-to-end prompt examples
eval-data/ baseline/candidate JSONL samples
tests/ unit, structure, and forward-test artifacts
The official source map records the verified date and maps local guidance to canonical pages. Start with OpenAI's GPT-5.6 model guidance, then check the relevant official page for reasoning, tool calling, caching, structured outputs, or the Responses API.
Model IDs, parameters, defaults, availability, pricing, and beta status can change. Recheck the official documentation before making a current claim or production migration.
The repository uses standard-library unittest, the Agent Skills validator, CLI smoke tests, and six documented forward scenarios. The forward scenarios are manually assessed for semantic behavior; they are not a benchmark or a claim of model-level gains.
See CONTRIBUTING.md for the exact local checks.
- Static audit findings identify review candidates; they cannot prove intent or prompt correctness.
- The comparator aggregates supplied measurements; it does not run GPT-5.6, grade outputs, estimate missing metrics, or validate the quality of a success label.
- Example prompts and thresholds are starting points, not universal defaults.
- SOL ENGINE does not guarantee better quality, fewer tokens, lower latency, or lower cost.
- Prompts, tool descriptions, and evaluation files may contain sensitive data; review them before sharing reports.
SOL ENGINE is an independent open-source project and not an official OpenAI product. OpenAI and GPT-5.6 are referenced only to describe compatibility and source grounding.
Released under the MIT License. Read CONTRIBUTING.md before proposing changes and SECURITY.md before reporting a vulnerability.