Menú
Run cross-model comparison — scan files with haiku, sonnet, and opus study agents to see how model size affects trigger phrase generation.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Discover files with trigger_phrase and/or refresh frontmatter, let the user choose which to schedule for periodic re-injection via CronCreate. Prevents behavioral drift by keeping core rules and goals fresh in context.
Write trigger phrases from .claude/triggers.json into file frontmatter as model-scoped trigger_phrase fields. Bridges trigger generation (scan) with scheduled injection (zenflow:schedule).
Build a GitHub issue into a PR. User-launched with an issue number — reads the issue, confirms with user, creates branch, implements against acceptance criteria, runs verification, and opens a PR. Every decision surfaces via AskUserQuestion.
Collaborative working session — you and the user are a team exploring, researching, and planning together. When implementation work is needed, create well-structured GitHub issues. The user launches Builder agents to implement and Reviewer agents to verify.
Shed accumulated context mid-session. Writes a knowledge handoff document capturing session state, decisions, observations, and behavioral calibration, then guides the user through /clear and resumption.
Runtime verification using Playwright MCP + proof artifacts. Use when acceptance criteria mention UI behavior, when claiming runtime verification, or when independently verifying a PR's claims. Produces artifact-backed proof — screenshots, DOM snapshots — not prose claims.
| name | compare |
| description | Run cross-model comparison — scan files with haiku, sonnet, and opus study agents to see how model size affects trigger phrase generation. |
Compare trigger phrase generation across model sizes. Same file, same prompt, three models.
*.{ts,tsx,js,jsx,py,go,rs,md,json,yaml,sh,sql,css,scss,html,svelte,vue}), exclude node_modules/, dist/, build/, .git/, *.lock, *.min.*Spawn the compare-researcher agent:
Use Agent tool with:
subagent_type: total-recall:compare-researcher
prompt: |
Compare trigger phrase generation across models for these files:
<list each absolute file path, one per line>
Read .claude/compare-results.json if it exists, otherwise create it. Append a new run entry:
{
"version": 1,
"runs": [
{
"runAt": "<ISO timestamp>",
"files": {
"relative/path.md": {
"models": {
"haiku": { "phrase": "...", "samples": [...], "convergence": [...], "confidence": 0.0 },
"sonnet": { "phrase": "...", "samples": [...], "convergence": [...], "confidence": 0.0 },
"opus": { "phrase": "...", "samples": [...], "convergence": [...], "confidence": 0.0 }
},
"crossModelConvergence": [...],
"modelSpecificTerms": { "haiku": [...], "sonnet": [...], "opus": [...] }
}
}
}
]
}
Use relative paths as keys (relative to project root).
Show a comparison table:
## Cross-Model Comparison Results
| File | Haiku | Sonnet | Opus | Shared Terms |
|------|-------|--------|------|--------------|
| testing.md | test behavior not implementation (0.99) | ... (0.xx) | ... (0.xx) | behavior, implementation |
### Analysis
- Files where all models agree: [list] — these are stable attractors
- Files where models diverge: [list] — larger models may surface deeper associations
- Average confidence: haiku X.XX | sonnet X.XX | opus X.XX
This is experimental data. Production triggers in triggers.json are not affected.