remembering/SKILL.md
Memory operations for Muninn (recall, remember, supersede, config). The canonical implementation has moved to oaustegard/muninn-utilities/remembering/. This file is a pointer; do not load skills from this path.
npx skillsauth add oaustegard/claude-skills rememberingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The remembering skill (memory architecture, recall/remember/supersede/config_*,
boot orchestration, profile/ops loading) now lives in its own repo:
→ https://github.com/oaustegard/muninn-utilities/tree/main/remembering
That repo is also the home of muninn_utils/, the utilities package boot installs
into ~/muninn_utils/. Co-locating the two ended a drift problem (e.g. recall(query=)
alias landing in one copy but not the other).
oaustegard/muninn-utilities and add
<clone>/remembering to your .pth. The boot block in Muninn's project
instructions already does this.oaustegard/muninn-utilities/remembering/ and
open PRs against that repo.claude-skills/remembering/ to the new location.Other skills (and external readers) may link to
claude-skills/remembering/SKILL.md. Removing the directory entirely would
404 those links; leaving a one-page redirect costs almost nothing and routes
people to the live source.
testing
Disciplined, validation-gated revision of an EXISTING skill so each edit is a measured improvement rather than a guess. Use when editing, revising, or tuning a skill that already exists and there is evidence it underperforms (observed failures, drift, complaints) — invoke by name, or have versioning-skills / creating-skill defer to it before applying edits. Not for authoring a brand-new skill from scratch (use creating-skill) or one-off prose.
development
Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and synthesizes results. Self-answers trivial lookups inline. No SDK dependency — uses raw HTTP via httpx. Use when tasks require multiple analytical perspectives, when context is large and subtasks only need portions, or when orchestrating-agents spawns too many redundant subagents.
tools
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.
development
Invokes Google Gemini models for structured outputs, image generation, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, structured JSON output, Google API integration, or cost-effective parallel processing.