pikers
/
piker
4
1
Fork 0
Code Issues 20 Pull Requests 13 Packages Projects Releases Wiki Activity
piker/ai
History
Gud Boi e815fd77cf Save draft Trend Calculus and Jev prototype 
Save the native FHLS recurrence, causal FSP publication, aligned
multi-timeframe evidence, Trio/HTTPX Jev worker and Qt pivot/regime
overlays as one draft snapshot.

Retain tests, research sources, Lua fixtures, runnable examples,
full license notices and prompt provenance. The latest reviewed
offline suite passed 253 tests with one unrelated actor case
excluded and one existing Tractor warning.

Defer behavioral commit splitting and upstream history integration.
Live Jev quality, provider-service wiring and Pine parity remain
follow-ups in Taken.

Prompt-IO: ai/prompt-io/codex/20261005T050218Z_eed58566_trend_sampler_5d9102_prompt_io.md
Prompt-IO: ai/prompt-io/codex/20261005T041132Z_eed58566_trend_b4fe4d_prompt_io.md
Prompt-IO: ai/prompt-io/codex/20261005T054014Z_eed58566_trend_style_e3216f_prompt_io.md

(this patch was generated in some part by `codex` using
GPT-6 family models (`openai`); exact model IDs unavailable)
 		2026-10-06 16:04:41 -04:00
..
claude-code Add `piker-clearing-expert` skill 2026-08-27 23:24:54 -04:00
opencode Add `piker-clearing-expert` skill 2026-08-27 23:24:54 -04:00
prompt-io Save draft Trend Calculus and Jev prototype 2026-10-06 16:04:41 -04:00
README.md Add `piker-clearing-expert` skill 2026-08-27 23:24:54 -04:00

README.md

AI Tooling Integrations

Documentation and usage guides for AI-assisted development tools integrated with this repo.

Each subdirectory corresponds to a specific AI tool or frontend and contains usage docs for the custom skills/prompts/workflows configured for it.

Originally introduced in PR #69; track new integration ideas and proposals in issue #79.

Integrations

Tool Directory Status
Claude Code claude-code/ active
OpenCode opencode/ active

Shared Skills

Provider-neutral skill bundles should use the portable Agent Skills subset and live under .agents/skills/ as their single source. OpenCode discovers that project directory natively. Relative links in provider directories such as .claude/skills/ may bridge clients which do not yet scan .agents/skills/; never copy the skill body.

Existing repo skills under .claude/skills/ predate this convention and can migrate separately without coupling their history to new skills.

Harness-specific command files should only delegate to a shared skill. They must not duplicate the skill body.

Adding a New Integration

Create a subdirectory named after the tool (use lowercase + hyphens), then add:

  1. A README.md covering setup, available skills/commands, and usage examples
  2. Any tool-specific config or prompt files
ai/
├── README.md                  # <- you are here
├── claude-code/
│   └── README.md
├── opencode/
│   └── README.md
└── <your-tool>/
    └── README.md

Conventions

  • Skill/command names use hyphen-case (commit-msg, not commit_msg)
  • Each integration doc should describe what the skill does, how to invoke it, and any output artifacts it produces
  • Keep docs concise; link to the shared skill source files rather than duplicating content
  • Keep skill bodies harness-neutral; isolate slash-command syntax and permissions in each harness integration