gpt-5-6-prompt-builder
Skill1k starsChanged 10 months agoNo licenceView on GitHub
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.
We split this skill into the rules it gives an agent
20 rules. About 0 are common, 15 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈15
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Trending
More talk lately.about the whole repository
Who's talking about am-will/codex-skills
- @tom-doerr.bsky.social“https://github.com/am-will/codex-skills”Bluesky · Apr 28, 2026 · 1 likes
- sudosubin/agents.nix“claude-code-plugins.github.am-will.codex-skills: init at 0-unstable-2026-07-14”GitHub · Oct 4, 2026
- sudosubin/agents.nix“agent-skills.github.am-will.codex-skills: init at 0-unstable-2026-07-14”GitHub · Sep 25, 2026
- vamseeachanta/workspace-hub“WRK-213: 'Codex multi-agent roles — assess native role system vs workspace-hub agent skill approach'”GitHub · Mar 19, 2026
- aiskillstore/marketplace“New skill: /am-will-parallel-task-spark (safe risk)”GitHub · Mar 7, 2026
The biggest 5 of 21 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 21
Talked about on GitHub and Bluesky (21 times).
On GitHub · 20
- Oct 4, 2026claude-code-plugins.github.am-will.codex-skills: init at 0-unstable-2026-07-14 — sudosubin/agents.nix0 reactions
- Sep 25, 2026agent-skills.github.am-will.codex-skills: init at 0-unstable-2026-07-14 — sudosubin/agents.nix0 reactions
- Mar 19, 2026WRK-213: 'Codex multi-agent roles — assess native role system vs workspace-hub agent skill approach' — vamseeachanta/workspace-hub0 reactions
- Mar 7, 2026New skill: /am-will-parallel-task-spark (safe risk) — aiskillstore/marketplace0 reactions
- Mar 7, 2026New skill: /am-will-super-swarm-spark (low risk) — aiskillstore/marketplace0 reactions
15 more on GitHub
- Mar 6, 2026New skill: /am-will-vercel-react-best-practices (safe risk) — aiskillstore/marketplace0 reactions
- Mar 6, 2026New skill: /am-will-llm-council (low risk) — aiskillstore/marketplace0 reactions
- Mar 6, 2026New skill: /am-will-gemini-computer-use (safe risk) — aiskillstore/marketplace0 reactions
- Mar 6, 2026New skill: /am-will-swarm-planner (safe risk) — aiskillstore/marketplace0 reactions
- Mar 6, 2026New skill: /am-will-role-creator (low risk) — aiskillstore/marketplace0 reactions
- Mar 6, 2026New skill: /am-will-markdown-url (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-openai-docs-skill (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-agent-browser (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-frontend-design (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-planner (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-read-github (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-parallel-task (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-plan-harder (safe risk) — aiskillstore/marketplace0 reactions
- Mar 4, 2026New skill: /am-will-context7 (safe risk) — aiskillstore/marketplace0 reactions
- Jan 26, 2026Add parallel-task skill from am-will/codex-skills — jdrhyne/agent-skills0 reactions
On Bluesky · 1
- Apr 28, 2026https://github.com/am-will/codex-skills — @tom-doerr.bsky.social1 likes and repost
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- Agent BrowserSkill
- create-hookSkill
- frontend-designSkill
- Frontend Responsive Design StandardsSkill
- gemini-computer-useSkill
- img-to-frontendSkill
- llm-councilSkill
- markdown-urlSkill
- openai-docs-skillSkill
- parallelSkill
- parallel-taskSkill
- parallel-task-sparkSkill
- plan-harderSkill
- plannerSkill
- pluginstallerSkill
- read-githubSkill
- role-creatorSkill
- super-swarm-sparkSkill
- swarm-plannerSkill
- update-codexSkill
- vercel-react-best-practicesSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.