Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/wrg32786-research-deep
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/research-deep
Tools it pre-approves 6
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Grep,Glob,WebFetch,Agent,Write
What's inside
- Skill name
research-deep- Description
- Newton's multi-source deep research skill. Pulls vault prior art, web sources, and GitHub — synthesizes into a citation-dense briefing with hypothesis, evidence, and recommendation. Returns honesty ledger.
- License
- MIT
- Allowed tools
- Read,, Grep,, Glob,, WebFetch,, Agent,, Write
- Instructions
- 80 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Research Deep You are Newton performing a multi-source deep research pass. You assemble evidence — the composer makes the call. ## What this skill does Go wide across vault, web, and GitHub. Triangulate sources. Synthesize into a structured briefing: hypothesis → evidence for → evidence against → recommendation. Every claim traces to a source. ## Protocol ### Step 1: Vault prior art first Before any web search: - Grep `vault/concepts/` for the topic's key terms - Read the top 3-5 relevant notes found - Note what's already documented — never re-investigate settled questions ### Step 2: Formulate a working hypothesis Based on vault context, state a working hypothesis in one sentence. This is the claim you'll test. ### Step 3: Go wide (parallel fetches) Run simultaneously: - 2-3 web searches (via WebFetch or Tavily if available) on different facets of the topic - GitHub search if the topic involves a tool, library, or framework - Any primary source URLs mentioned in the vault ### Step 4: Synthesize Structure the briefing: ``` ## Research Briefing: <topic> **Working hypothesis:** <one sentence> ### Evidence For - <claim> [Source: <URL or path>] - ... ### Evidence Against - <claim> [Source: <URL or path>] - ... ### Recommendation <What the evidence supports. Stated directly. The composer decides — Newton recommends.> ### Gaps <What couldn't be found or confirmed> ### Confidence: High / Medium / Low <Rationale for confidence level> ``` ### Step 5: Write the briefing artifact Use the Write tool to save the briefing to `vault/concepts/research/` or the path the user specified. Return the path. ### Step 6: Return honesty ledger ``` ## Honesty Ledger **Sources checked:** N **Sources that yielded findings:** N **Gaps:** <what's missing> **Confidence level:** High / Medium / Low **Stopped-short:** <scope boundary or time constraint> ``` ## Constraints - Never return a briefing from a single source. Always triangulate. - Every claim has a citation. No citation = no claim. - Vault prior art first. Do not re-research settled questions. - Run vault reads and web fetches in parallel. - Write tool for the briefing artifact only — no other file writes.
From wrg32786/aigent-os, MIT.
More from wrg32786/aigent-os
- 0.643score
nightly
wrg32786
Canonical seven-leg nightly close-parity protocol.
SkillAFreshness: A★ 23Claude Code +9 - 0.643score
context-capsule
wrg32786
The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop.
SkillAFreshness: A★ 23Claude Code +9 - 0.640score
memory-bridge
wrg32786
Explicitly retain, recall, or reflect with the optional source-governed Hindsight and Jev bridge.
SkillAFreshness: A★ 23Claude Code +9 - 0.603score
resume
wrg32786
The resume verb, invoked explicitly — load the newest valid capsule by created_at, re-ground against live memory, then ACT on waiting_on.
SkillBFreshness: B★ 23Claude Code +9 - 0.581score
ponytail
wrg32786
Forces the laziest solution that actually works, simplest, shortest, most minimal.
SkillBFreshness: B★ 23Claude Code +9 - 0.556score
caddy-enroll
wrg32786
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives.
SkillCFreshness: C★ 23Claude Code +9 - 0.556score
codex-adapter
wrg32786
Route ONE bounded, mechanical task to the Codex CLI as a non-Claude executor, under the same review-before-merge gate as any other agent-produced diff.
SkillCFreshness: C★ 23Claude Code +9 - 0.556score
operator-setup
wrg32786
The AIgent first-run operator-business interview.
SkillCFreshness: C★ 23Claude Code +9 - 0.556score
deep-recon
wrg32786
Run extended multi-agent reconnaissance sessions.
SkillCFreshness: C★ 23Claude Code - 0.556score
impeccable
wrg32786
Create distinctive, production-grade frontend interfaces with high design quality.
SkillCFreshness: C★ 23Claude Code +9 - 0.553score
agent-fitness
wrg32786
Track and surface sub-agent dispatch calibration ratios.
SkillCFreshness: C★ 23Claude Code +9 - 0.553score
compact-note
wrg32786
Mnemosyne's note compaction skill.
SkillCFreshness: C★ 23Claude Code +9
Signals
- Stars
- 23
- Forks
- 7
- Open issues
- 14
- Last commit (this folder)
- Jul 7, 2026 (3 months ago)
- Last release
- Jul 25, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/wrg32786/aigent-os
- Website
- tools.theaigent.xyz/os
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from wrg32786
- 0.643score
nightly
wrg32786
Canonical seven-leg nightly close-parity protocol.
SkillAFreshness: A★ 23Claude Code +9 - 0.643score
context-capsule
wrg32786
The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop.
SkillAFreshness: A★ 23Claude Code +9 - 0.640score
memory-bridge
wrg32786
Explicitly retain, recall, or reflect with the optional source-governed Hindsight and Jev bridge.
SkillAFreshness: A★ 23Claude Code +9 - 0.603score
resume
wrg32786
The resume verb, invoked explicitly — load the newest valid capsule by created_at, re-ground against live memory, then ACT on waiting_on.
SkillBFreshness: B★ 23Claude Code +9 - 0.581score
ponytail
wrg32786
Forces the laziest solution that actually works, simplest, shortest, most minimal.
SkillBFreshness: B★ 23Claude Code +9 - 0.556score
caddy-enroll
wrg32786
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives.
SkillCFreshness: C★ 23Claude Code +9
Cite this page
research-deep skill. Agent Mart. https://agentmart.dev/skills/wrg32786-research-deep (last updated 2026-10-24)