Agent Skill

Ulw Research skill

ulw-researchcode-yeongyu/oh-my-openagentpackages/omo-senpi/skills/ulw-research/SKILL.md

Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw' research wording.

70k

always on

51 tokname + description

once used

13,485 tokSKILL.md body

bundled files

215 KB

repo stars

70kGitHub

Install the Ulw Research skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/code-yeongyu/oh-my-openagent --skill ulw-research

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent
mkdir -p ~/.claude/skills
cp -R /tmp/oh-my-openagent/packages/omo-senpi/skills/ulw-research ~/.claude/skills/ulw-research

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	51 tok
When the agent uses it	The SKILL.md instructions	13,485 tok
Only if opened	2 bundled files (15 KB)	varies

Until it is used, ulw-research costs about 27× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 60 skills from code-yeongyu/oh-my-openagent would load 5,128 tokens of descriptions. Skills vs MCP study

Checks

The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

ULW-RESEARCH — Team-First Maximum-Saturation Research
Activation
How this maps to omo-senpi
Authority while active
Success criteria
Epistemic instrumentation
Phase 0 — Scope solo, organize the brief
Run it as a loop, and journal in real time
Deliverable lane, format, and the empty-info interview
Phase 1 — Stand up the team (DEFAULT composition)
Team lifecycle — one team, or a sequence, decided by scale and precision
Member brief contract
Phase 2 — Saturation wave
Phase 3 — Expand and debate until convergence
Excursions — dive deep on a new find, then surface back out
Phase 4 — Verify contested claims by running code
Phase 4b — Lock non-code claims through the claim graph
Phase 5 — Synthesize
Phase 6 — Final materials, then teardown
The delivery gates — every gate for the QA tier must PASS, in order

More skills from code-yeongyu/oh-my-openagent

All skills in this repo

ast-grepcode-yeongyu/oh-my-openagent
Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.
70k560 tok idle · 3,466 in use
browsercode-yeongyu/oh-my-openagent
Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA traces. Use for any interactive browser task; not for a plain search or an unblocked static fetch.
70k493 tok idle · 1,970 in use
codex-qacode-yeongyu/oh-my-openagent
QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG / logs SQLite / /debug-config). Ships tested helper scripts each with a --self-test. Use whenever someone changes anything under packages/omo-codex or wants to QA, smoke-test, verify, or debug the Codex plugin, its hooks/components, the installer/config.toml, the app-server flow, or the Codex TUI. Triggers: codex qa, qa codex, codex-qa, test codex plugin, verify codex hook, codex app-server, lazycodex qa, isolated CODEX_HOME, prove codex hook fired, codex tui test.
70k9239 tok idle · 1,789 in use
coding-agent-sessionscode-yeongyu/oh-my-openagent
Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.
70k2362 tok idle · 2,672 in use
comment-checkercode-yeongyu/oh-my-openagent
Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.
70k29 tok idle · 104 in use
dag-librarycode-yeongyu/oh-my-openagent
Stores a DAG definition once and re-runs it by name, instead of pasting the definition into every run. Use when the user wants to save a DAG, run a saved one, or schedule the same multi-agent graph repeatedly.
70k50 tok idle · 1,055 in use
data-scientistcode-yeongyu/oh-my-openagent
Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or plotting a dataset.
70k554 tok idle · 1,278 in use
debuggingcode-yeongyu/oh-my-openagent
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
70k353 tok idle · 3,031 in use