levi-qiao/longgraph-skill / skills/loop-graph
loop-graph
FlaggedUse only when the user explicitly invokes /loop-graph or names this skill. Compiles a custom loop-graph run. Do not use unless named. Existing runtime nodes are self-contained.
examples/migrate-blob-storage/archive/directives.md
View on GitHub# shutterlog — Folded directives D-001–D-003
D-001 · 2026-07-20 — Round 4 recorded M2 as verified on the backfill script's own `processed` counter: self-generated evidence, not an independent proof → produce a primary-key set diff between `attachments` and a fresh object-store listing plus a 1% checksum sample; M2 stays open until the diff is empty. (Decided under delegated authority — re-verification is reversible and touches no owner-only item.)
D-002 · 2026-07-20 — **M2 milestone acceptance.** Independent audit of the M2 boundary: re-ran `scripts/verify_backfill.py` (set diff empty), full `pytest -q` (12 passed), `scripts/smoke_serve.sh` (20/20 byte-identical), inspected diff for undisclosed shortcuts (none found). All exit conditions verified from clean context. → Executor: flip Milestone gate to `passed` and advance to M3. (Decided under delegated authority — M2→M3 promotion is not itself DDL or production-touching; the DDL is M3's *content*, gated separately by the owner-only list.)
D-003 · 2026-07-20 — **GAP-002 acceptance.** Diff is confined to `docs/object-store-access-policy.md`; it is independent of M2/M3 and shared surfaces, and its required headings + markdown lint pass. → Executor: mark GAP-002 accepted and close its row. This verdict does not change the Milestone gate.
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: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |