tt-a1i/archify / .agents/skills/archify-tuning
archify-tuning
VerifiedImprove Archify diagram accuracy, visual quality and complete authoring speed with fewer repairs. Use for generation experiments or evaluating changes to layout, routing, diagnostics, authoring instructions and acceptance rules against actual diagrams and agent traces.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.9 KB |
| references/experiment-design.md | markdown | 4.1 KB |
| references/trace-export.md | markdown | 2.2 KB |
| references/trace-signals.md | markdown | 4.8 KB |
| scripts/collect.mjs | script | 13.2 KB |
| scripts/lib.mjs | script | 7.8 KB |
| scripts/replay.mjs | script | 6.2 KB |
| scripts/round.mjs | script | 4.5 KB |
| scripts/shots.mjs | script | 5.6 KB |
references/trace-export.md
View on GitHub# Trace export
Use this input when generation ran outside Devin CLI. Export the relevant sessions with the host's supported tools, then normalize tool names and arguments to the format below. Keep the export in the external tuning home; it can contain source-project content. The collector does not discover or parse another agent's private database.
```sh
node .agents/skills/archify-tuning/scripts/collect.mjs <round> --trace-export <trace.json> --dump
```
The JSON object has `schemaVersion: 1` and a `sessions` array. Each session has an `id` and chronological `messages`. Its user task must name the absolute `<round>/<diagram-type>` directory created by `round.mjs`, so collection can associate the session with one diagram.
```json
{
"schemaVersion": 1,
"sessions": [{
"id": "workflow-run-1",
"messages": [
{ "role": "user", "content": "Create the diagram in /absolute/round/workflow" },
{
"role": "assistant",
"content": "Write the first candidate.",
"tool_calls": [{
"id": "write-1",
"name": "write",
"arguments": {
"file_path": "/absolute/round/workflow/.archify/example/candidate.json",
"content": "{\"diagram_type\":\"workflow\"}"
}
}]
},
{ "role": "tool", "tool_call_id": "write-1", "content": "Written" }
]
}]
}
```
The shortened candidate above illustrates encoding only; retain the full actual candidate in an export. Normalize `read` to `{ "file_path": "..." }`, `write` to `{ "file_path": "...", "content": "..." }`, and `exec` to `{ "command": "..." }`. Tool results are strings linked by `tool_call_id`. Preserve command output, including nonzero failures and unknown outcomes. A first draft created through a patch or shell command needs a corresponding normalized `write` event containing its actual first JSON, not the final repaired version.
Keep final candidates in the round directories specified by the prompts. Missing drafts, results or final files are missing evidence; never fabricate events or replace them with successful summaries. Content-change counts flag items to inspect and do not establish factual or semantic equivalence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format. | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |
| internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |