Skip to main content
eumemic
GitHub クリエイタープロフィール

eumemic

7 件の GitHub リポジトリにある 26 件の収集済み skills をリポジトリ単位で表示します。

収集済み skills
26
リポジトリ
7
更新
2026-07-10
リポジトリエクスプローラー

リポジトリと代表的な skills

bughunt
ソフトウェア品質保証アナリスト・テスター

One iteration of hypothesis-driven bug discovery — audit the codebase against project invariants and risk patterns via parallel agents, adversarially verify each candidate, and file a groomed bug-issue (red-test sketch + verification evidence + proposed root-cause fix) for every finding that clears the gate. Does NOT implement or ship — specialized dev processes pick up the filed issues. Use when invoked as `/bughunt` (runs one iteration); use `/loop bughunt` to run it as an autonomous loop. Project-agnostic; reads risk dimensions from CLAUDE.md key-invariants and project memory.

2026-07-10
build-cycle
ソフトウェア開発者

Reference document used by the build-iteration skill /shovel-ready for its single-iteration machinery — branch, sync-with-master, /ship handoff, /retro pass, merge, and declaring the loop outcome. NOT user-invokable, and NOT the loop. The loop lives in `/loop`; this is one iteration's build cycle. The find-and-file siblings (/kaizen, /bughunt, /kaikaku) use `file-cycle` instead. Only load when a build-iteration skill directs you here.

2026-07-10
file-cycle
ソフトウェア開発者

Reference document shared by the find-and-file iteration skills (/kaizen, /bughunt, /kaikaku) for their common single-iteration machinery — author groomed issue(s), label by validation, file autonomously (multi-output), and declare the loop outcome. NOT user-invokable, and NOT the loop. The loop lives in `/loop`; this is one iteration's file cycle. The file-type sibling of `build-cycle`. Only load when a find-and-file skill directs you here.

2026-07-10
kaikaku
ソフトウェア開発者

Continuous architectural simplification and correctness-by-construction — whole-system recon via parallel agents to find high-leverage opportunities to simplify-and-beautify a structure OR foreclose a whole defect-class by making an illegal state unrepresentable, at the module/layer/concept altitude; steelman each candidate against Chesterton's Fence, then file groomed design-issue(s) for every candidate that clears the gate — autonomously, labeled by validation (no build, no in-session approval gate). Use when invoked as `/kaikaku` (runs one iteration); use `/loop kaikaku` to run it as an autonomous loop. The architectural-altitude sibling of `/kaizen`. Project-agnostic; reads simplicity + beauty + correctness stance from CLAUDE.md and project memory.

2026-07-10
kaizen
ソフトウェア開発者

One iteration of accidental-complexity reduction — audit the codebase against craftsmanship principles via parallel agents, and file a groomed cleanup-issue for every candidate that clears the gate. Does NOT implement or ship — specialized dev processes pick up the filed issues. Use when invoked as `/kaizen` (runs one iteration); use `/loop kaizen` to run it as an autonomous loop. The instance/tidy-altitude sibling of `/kaikaku`. Project-agnostic; reads simplicity heuristics from CLAUDE.md and project memory.

2026-07-10
loop
ソフトウェア開発者

Drive any single-iteration development skill as an autonomous loop — invoke one iteration, read its declared outcome, then pace, escalate, or stop. Use when invoked as `/loop <skill> [flags]` (e.g. `/loop kaizen --auto`, `/loop bughunt`, `/loop kaikaku`, `/loop shovel-ready --auto`). Owns cadence, idle escalation, and re-arming so the iteration skills stay pure. Pass `--once` to run exactly one iteration.

2026-07-10
retro
ソフトウェア開発者

Reflect on a slice of the current session (a single iteration, the whole session, or a natural pause point) to identify durable, codifiable learnings about workflow OR dev infrastructure — and ship them only if they clear a quality bar. Most invocations produce nothing; that's the point. Use when the user asks to "run a retro", "do a retrospective", "reflect on the session", "what did you learn", "improve skills based on this session", "codify learnings"; when invoked from a loop driver (`/shovel-ready`) with `--scope=iteration`; or **proactively at pause points** when the agent is waiting on async work (CI, autodev runs, monitor events) and has cycles to think meta.

2026-07-10
ship
ソフトウェア開発者

Drive a code change from working tree to a green PR — runs project checks, /simplify, code-review subagent, commits, opens PR, monitors CI. Stops when CI is green; caller handles merge. Use when invoked as `/ship`, or when `/shovel-ready` hands off a working tree of changes to be shipped. Project-agnostic; reads check commands from CLAUDE.md.

2026-07-10
このリポジトリの収集済み skills 12 件中、上位 8 件を表示しています。
benchmarking
ソフトウェア開発者

This skill should be used when the user asks to "run the benchmark", "run locomo", "benchmark ragzoom", "evaluate recall quality", "compare with letta", "check accuracy", "run the evaluation harness", "agentic evaluation", "max iterations", or mentions benchmarking, evaluation, or competitive comparison of the memory system.

2026-02-14
memory-tool-usage
ソフトウェア開発者

This skill should be used when needing to recall earlier conversation details, after compaction occurs, when resuming a session, when details feel fuzzy, or when the user references something from earlier in the conversation. Provides guidance on effective use of the `recall` memory tool.

2026-02-13
ragzoom-memory
その他コンピュータ職

Set up persistent hierarchical memory using RagZoom. Use when bootstrapping an OpenClaw agent with long-term memory, configuring transcript sync, or querying historical context. Triggers on "set up memory", "install ragzoom", "persistent memory", "recall past conversations".

2026-02-01
ragzoom-usage
ソフトウェア開発者

This skill should be used when the user asks "how do I index a document", "how do I query", "CLI commands", "REST API", "Python API", "configuration options", or mentions using RagZoom as an end user rather than developing it.

2026-01-28
memory-tool-usage
その他コンピュータ職

This skill should be used when needing to recall earlier conversation details, after compaction occurs, when resuming a session, when details feel fuzzy, or when the user references something from earlier in the conversation. Provides guidance on effective use of the `recall` memory tool.

2026-01-27
ragzoom-development
ソフトウェア開発者

This skill should be used when the user asks to "run tests", "run checks", "debug a test", "benchmark performance", "set up development environment", "understand the architecture", "how does indexing work", "how does the tiling algorithm work", "study the codebase", "learn the codebase", or mentions testing, linting, type checking, or development workflows.

2026-01-12
aios-live-monitor
ネットワーク・コンピュータシステム管理者

This skill should be used when the user asks to "watch the live aios session", "tail factchecker", "set up live monitoring on aios", "monitor the chat", "tail worker errors", "narrate aios session activity", or runs a smoke test that requires persistent observation of a running aios api+worker pair. Provides a chat-stream filter, error-grep pattern, and pre-flight probe to arm Monitor-tool tasks safely (always with --after-seq to avoid backfill blowing up the context window).

2026-06-16
aios-smoke-setup
ソフトウェア開発者

This skill should be used when the user asks to "smoke test the connector", "DM the bot in this worktree", "set up a fresh aios runtime", "spin up aios", "prep a smoke session", "bring up aios on this branch", "bring up aios headless", "spin up aios without a bot", "no-connector runtime", or needs a running aios runtime to "verify a harness change" / repro a sweep/loop/context/tool_dispatch issue — whether pointed at a real Telegram/Signal/WhatsApp bot OR headless (api+worker only, driven via the CLI). Bundles the pre-flight checks (bot getUpdates conflict, sibling worktree non-interference, free port), the isolated `.env` overrides (separate DB + port + ``AIOS_URL`` + absolute ``AIOS_WORKSPACE_ROOT`` + ``AIOS_DEFAULT_MCP_PERMISSION_POLICY=always_allow``), the right migration command (``aios migrate``, not ``alembic upgrade head``), the fresh-DB ``bootstrap_root`` step (a new DB 401s every call until an account key is minted), and the env/agent/(connection)/session resource chain in one ``setup.sh`` so the f

2026-06-08
aios-whatsapp-pair
ソフトウェア開発者

This skill should be used when the user asks to "smoke the whatsapp connector", "pair whatsapp", "link whatsapp", "scan the QR for whatsapp", "set up whatsapp smoke", "bring up the whatsapp bot", "rebind the whatsapp connection", "redo the whatsapp pairing", or otherwise wants to attach a real WhatsApp account to the aios runtime running in the current worktree. Bundles the daemon cross-compile (Docker `golang:1.25` when local Go < 1.25), runtime-token mint, daemon spawn, start-pairing/confirm-pairing API calls, and — critically — the **ASCII-in-terminal QR rendering** that makes the pair flow actually work. Hand off to `aios-live-monitor` for narration after `status=success`.

2026-05-23
7 件中 7 件のリポジトリを表示
すべてのリポジトリを表示しました
eumemic Agent Skills | SkillsMP