episteme-compaction · git:20261018.b2b1b02 · 2026-10-18 · sha256 d1973af1044f8f2c
episteme-compaction git:20261018.b2b1b02A
Immutable. This exact content never changes and is served at /api/v1/blob/d1973af1044f8f2c.
--- name: episteme-compaction description: | Lossless compaction of epistemes: prose ↔ compact typed-slot notation (F4-F5; ~65% median token savings, measured on the instruction-file corpus — see references/relations.md) with a source-claims vs [bracketed] split and reconstruction back to source. Use for AI-agent or FPF-literate-human output needing token economy and auditability. NOT narrativization. Depends on fpf-core. --- # Episteme Compaction — Dispatcher **Bounded context:** lossless compaction of epistemes — prose ↔ compact typed-slot notation (F4-F5), governed by the FPF A.6.3 (Epistemic Viewing) family. **Readiness (collective):** `source-faithful` — bodies drafted through E.8 from the sources named in `references/relations.md`; not yet `case-validated` (no per-card E.21 results; selected acceptance cases only). Every card is `seed` until a per-card E.21 pass plus feedback-driven repairs (CC-QR.2). This skill is the access-facing carrier bearing the `EpistemeCompactionPrinciplesFramework` edition. The edition is recoverable from `references/` (the canonical pattern bodies). There is no monolith and no separate reader-facing publication form. ## Routing table | Situation | Load | |---|---| | Decide formality level (F0 vs F4-F5 vs F3 hybrid) for an output | `references/ECPF.1.md` | | Render prose claims as typed slots (the core move) | `references/ECPF.2.md` | | Render Γ aggregation / F-G-R-CL trust metrics | `references/ECPF.3.md` | | Render evidence provenance / ADI reasoning | `references/ECPF.4.md` | | Check strict distinctions / category errors | `references/ECPF.5.md` | | Evaluate a rendering before admission | `references/ECPF.6.md` | | Reconstruct prose from a compact episteme (reverse render) | `references/ECPF.7.md` | | Govern the episteme↔prose round-trip / drift | `references/ECPF.TG.md` | ## Navigation rule The dominant chain is a rendering pipeline: start at `references/ECPF.1.md` (formality gates everything), then `references/ECPF.2.md` (the core typed-slot render), then `references/ECPF.3.md` / `references/ECPF.4.md` for aggregation/trust and evidence/reasoning, then `references/ECPF.5.md` for distinction compliance, closing with `references/ECPF.6.md` for admission. For the reverse direction (notation → prose), load `references/ECPF.7.md`; load `references/ECPF.TG.md` when the round-trip across passes must stay drift-free. ## Lookup rules - **Index first, then "no".** Before looking for a pattern, check `references/INDEX.md`. If the id is not listed there, the pattern does not exist — answer "no"; do not open files searching for it. - **Read once.** Do not reopen a file you have already read — reuse its already-read content from your context. ## Single surface `references/*.md` is canonical. No `assets/` monolith and no "generated → do not edit" projection exists; `SKILL.md` (this file) is routing-only. The runtime-normative consumer surface is this dispatcher plus the routed `references/ECPF.*.md` card; `INDEX.md`, `relations.md`, and the source citation are reference-only. The graph section of `references/relations.md` is generated by `scripts/build_relations.py` — never hand-edit it; run the script after changing any card's frontmatter dependencies.