free-memory: skill design — hub-satellite + no dynamic commands + plugin/hook packaging + OpenSpec catch-up (Aaron 2026-05-03)

docs/hygiene-history/ticks/2026/05/03/0020Z.md

@@ -0,0 +1 @@
+| 2026-05-03T00:20:00Z | opus-4-7 / autonomous-loop continuation | a2e2cc3a | **Three same-tick skill-design rules captured (PR #1253) + 6 of 7 Copilot findings on PR #1250 worked example fixed (PR #1250 push) + #1252 rebased after #1251 landed.** Cycle worked: (1) Aaron 2026-05-03 dropped three load-bearing skill-design rules in rapid same-tick succession — hub-satellite separation (DataVault 2.0 pattern), no dynamic commands in skills (TS-wrap), package skill domains as plugins with hooks for contracts (composes with OpenSpec); (2) the OpenSpec catch-up was named as load-bearing architectural debt — *"way behind on it ... if we deleted everything other than it"*; (3) PR #1250 worked example #1 received 7 Copilot findings (3 P1 portability + 1 P1 nonexistent dir + 2 P2 wrong-fact + 1 false-positive-table) — 6 fixed empirically (replaced fictional shard filenames with actual; reworded missing-amara-dir to acknowledge absence; replaced `\|` with `-E`/`|`; corrected layer-10 claim about adjacent artifacts; path-consistency CURRENT-aaron); 1 false positive resolved with explanation; (4) PR #1252 rebased onto main after PR #1251 (post-merge corrections) landed. The pattern Aaron is establishing across this 2-day arc: forward-looking architectural observations + cross-cutting design rules + canonical-substrate naming, all filed in shape that subsequent maturity-triggers can land cleanly. Cron a2e2cc3a still armed. | #1250 (worked example #1) — 6 Copilot findings fixed + 1 false positive resolved; threads all resolved; auto-merge armed; #1251 (post-merge corrections to #1249) merged f8309a85; #1252 (multi-harness future-skill-domain memo with same-tick refinements) rebased + auto-merge armed; #1253 (three skill-design rules + OpenSpec catch-up naming) opened | This tick teaches the operational pattern of (a) substantive in-flight refinements from same-tick maintainer messages composing into single substrate landings (rather than 3+ separate PRs for 3 same-tick rules), AND (b) the recursive hub-satellite architectural separation Aaron has been naming across multiple memos this 2-day arc finally getting its canonical substrate landing. The 5-layer recursive composition (skill body / command / skill domain / cross-skill contracts / spec) IS the design architecture; current state has Rule 1 + 2 mostly correct, Rule 3 is forward-state. OpenSpec catch-up is named as the prereq that must land before Rule 3 is operationally complete. Composes with `memory/feedback_prefer_ts_scripts_over_dynamic_bash_for_conversation_ux_dst_in_ts_aaron_2026_05_01.md` (Rule 2 generalizes from chat-loop to all skills) + the two future-skill-domain memos (canonical-starting-set tables already follow Rule 1 implicitly; this rule names it) + B-0169 (worked example for how to apply Rule 2 — TS-wrap the procedure). |

memory/MEMORY.md

@@ -4,6 +4,7 @@
 <!-- paired-edit log (NOT the single-slot latest-marker — that lives on line 3 above): PR #986 lands carved-sentence fixed-point stability + Zeta soul-file executor architecture (Infer.NET-style Bayesian inference, NOT LLMs) + carved sentences ≈ formal specs provable in DST + Deepseek CSAP review absorption (Aaron 2026-04-30 → 2026-05-01, eight-message chain across two autonomous-loop ticks per the file body's section header). Architectural disclosure: substrate IS the priors; alignment IS substrate. The single-slot latest-marker on line 3 (forever-home Aaron 2026-05-01) takes precedence as the chronologically-latest paired edit; this PR's work is earlier. -->
 **📌 Fast path: read `CURRENT-aaron.md` and `CURRENT-amara.md` first.** <!-- paired-edit: PR #690 scheduled-workflow-null-result-hygiene-scan tier-1 promotion 2026-04-28 --> These per-maintainer distillations show what's currently in force. Raw memories below are the history; CURRENT files are the projection. (`CURRENT-aaron.md` refreshed 2026-04-28 with sections 26-30 — speculation rule + EVIDENCE-BASED labeling + JVM preference + dependency honesty + threading lineage Albahari/Toub/Fowler + TypeScript/Bun-default discipline.)
 
+- [**Skill design — hub-satellite separation + no dynamic commands + plugin/hook packaging + OpenSpec catch-up (Aaron 2026-05-03, three same-tick rules + architectural-debt naming)**](feedback_skills_as_carved_sentences_knowledge_in_docs_datavault_2_0_pattern_aaron_2026_05_03.md) — Three cross-cutting skill-design rules: (1) skills = carved-sentence hubs, knowledge = doc satellites, DataVault 2.0 pattern; (2) no dynamic commands in skills, use TS files under tools/ and reference by path; (3) package skill domains as plugins, use harness hooks for pre/post-condition enforcement (contract-based development). PLUS OpenSpec catch-up named as load-bearing prerequisite — *"if we deleted everything other than it"* — currently sparse; catch-up is its own substantial backlog item. Recursive composition across layers (skill body / command / skill domain / cross-skill contracts / spec).
 - [**Git-native backlog management + long-arc thesis as future skill DOMAIN (Aaron 2026-05-02 forward-looking architectural observation)**](feedback_git_native_backlog_management_long_arc_future_skill_domain_aaron_2026_05_02.md) — Domain emerges (6 procedure skills + 4 named-persona experts + 5 tools) once "down pat"; promotion trigger = 3+ worked examples per skill / 1+ judgment-disagreement per expert. Memo body has Aaron's verbatim quote, Aarav BP-20 composition, canonical starting set.
 - [**Skill flywheel + expansion flywheel + parallel-tracks substrate — three flywheel-class questions + Aaron's same-tick skills-are-for-everyone corrective (Aaron 2026-05-02)**](feedback_skill_flywheel_expansion_flywheel_parallel_tracks_substrate_aaron_2026_05_02.md) — Skills propagate across team + harnesses; memory is per-agent. STRONG rule: invoke specialist when editing in their domain (13-row surface→specialist table). Memo body has Aaron's verbatim quote (typos preserved). Composes with B-0169 (skill not memo).
 - [**depends_on backlog-search discipline — at row creation AND at pickup-time, search backlog for prerequisites first (Aaron 2026-05-02, two messages naming the discipline at two trigger points)**](feedback_depends_on_backlog_search_discipline_at_creation_and_at_pickup_aaron_2026_05_02.md) — Mechanizes depends_on relationship-analysis at the two natural decision-points where the field's correct value is being filled. At-creation: when filing a new row, search backlog for prerequisites; populate depends_on at file-time rather than empty default. At-pickup: when starting work, if it feels like substrate is missing, search backlog for the missing piece. Three outcomes: found → add to depends_on; not found → file new prereq row first, defer original; already-listed → proceed. Composes with PR #1246 schema-completion (160/160 coverage gave the write target; this discipline fills it organically). The act of writing or starting IS the analysis — no separate concentrated effort needed.