Doc Coauthoring
aws-samples/sample-strands-agent-with-agentcore
Guide users through a structured workflow for co-authoring documentation.
Manage domain-watch surveillance configs — seed new domains, review scan status and proposals, activate Watch Log proposals into thinking topics, pause domains, and update PIRs or watch queries
$ npx skills add Abilityai/cornelius --skill manage-watching-domains -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Abilityai/cornelius manage-watching-domains --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/manage-watching-domains .claude/skills/manage-watching-domains && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "manage-watching-domains" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/manage-watching-domains into .claude/skills/manage-watching-domains/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-watching-domains", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Abilityai/cornelius/tree/main/.claude/skills/manage-watching-domainsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Abilityai/cornelius --skill manage-watching-domains -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Abilityai/cornelius manage-watching-domains --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/manage-watching-domains .agents/skills/manage-watching-domains && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "manage-watching-domains" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/manage-watching-domains into .agents/skills/manage-watching-domains/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-watching-domains", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Abilityai/cornelius --skill manage-watching-domains -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Abilityai/cornelius manage-watching-domains --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/manage-watching-domains .cursor/skills/manage-watching-domains && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "manage-watching-domains" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/manage-watching-domains into .cursor/skills/manage-watching-domains/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-watching-domains", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Abilityai/cornelius.git --path .claude/skills/manage-watching-domains--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Abilityai/cornelius --skill manage-watching-domains -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Abilityai/cornelius manage-watching-domains --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/manage-watching-domains .gemini/skills/manage-watching-domains && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "manage-watching-domains" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/manage-watching-domains into .gemini/skills/manage-watching-domains/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-watching-domains", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Abilityai/cornelius manage-watching-domainsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Abilityai/cornelius --skill manage-watching-domains -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/manage-watching-domains .github/skills/manage-watching-domains && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "manage-watching-domains" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/manage-watching-domains into .github/skills/manage-watching-domains/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-watching-domains", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Abilityai/cornelius --skill manage-watching-domains -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Abilityai/cornelius manage-watching-domains --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/manage-watching-domains .opencode/skills/manage-watching-domains && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "manage-watching-domains" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/manage-watching-domains into .opencode/skills/manage-watching-domains/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manage-watching-domains", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
manage-watching-domainsManage domain-watch surveillance configs — seed new domains, review scan status and proposals, activate Watch Log proposals into thinking topics, pause domains, and update PIRs or watch queries
Manage Watching Domains is an agent skill from Abilityai/cornelius. Manage domain-watch surveillance configs — seed new domains, review scan status and proposals, activate Watch Log proposals into thinking topics, pause domains, and update PIRs or watch queries
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Sales & Support, covering Proposals and quotes. The repository describes itself as: AI-powered second brain template for Claude Code + Obsidian. The licence is MIT.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit b9bea90. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGrepGlobBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Manage Watching Domains loads about 3.5k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 1,309 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Write, Edit, Grep, Glob, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Abilityai/cornelius at commit b9bea90, republished under its MIT licence (© Abilityai). 1,309 words, ~3,465 tokens.
.claude/skills/manage-watching-domains/SKILL.md (or your agent's skills folder).Human-in-the-loop manager for the domain-watch surveillance layer. Handles the full lifecycle: seeding new domains for continuous monitoring, reviewing scan status and signal level, activating Watch Log proposals into thinking topics, pausing domains, and updating intelligence requirements.
Companion skills:
.claude/skills/domain-watch/SKILL.md — the autonomous scanning engine (runs daily, perceives and proposes).claude/skills/manage-thinking-topics/SKILL.md — manages the thinking topics that watching domains feed intoArchitecture: domain-watch perceives → manage-watching-domains activates → incubation-loop analyses
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Watching Registry | Brain/05-Meta/Watching/WATCHING-REGISTRY.md | ✓ | ✓ | Master list of domains + scan status |
| Domain Configs | Brain/05-Meta/Watching/[domain-slug].md | ✓ | ✓ | Per-domain PIRs, queries, baseline counts |
| Watch Log | Brain/05-Meta/Watching/WATCH-LOG.md | ✓ | ✓ | Proposals awaiting activation |
| Thinking Registry | Brain/05-Meta/Thinking/THINKING-REGISTRY.md | ✓ | ✓ | Destination when activating proposals |
| Thinking Files | Brain/05-Meta/Thinking/[topic-slug].md | ✓ | Created during activation |
Invoke with one of five modes. If no mode is provided, default to review.
Purpose: Full status dashboard — what domains are active, when they last scanned, what signal level they found, and what proposals are sitting in the Watch Log awaiting your decision.
date '+%Y-%m-%d'Read Brain/05-Meta/Watching/WATCHING-REGISTRY.md. Parse all domains.
For each domain, read Brain/05-Meta/Watching/[domain-slug].md. Extract:
label - human-readable namemode - surveillance or hypothesislast_scan - date of last scan (null = never scanned)notes_at_scan - baseline note countspawn_threshold - delta needed to trigger proposalpriority_intelligence_requirements - list of PIRs (count them)watch_queries - list of search terms (count them)Read Brain/05-Meta/Watching/WATCH-LOG.md.
Extract all proposals that are not yet marked **Activated:**. For each:
## Watching Domains: Status Review [DATE]
### Active Domains (N)
| Domain | Mode | Last Scan | Notes @ Scan | Threshold | PIRs | Status |
|--------|------|-----------|-------------|-----------|------|--------|
| [label] | surveillance/hypothesis | YYYY-MM-DD or never | N | +N | N | active |
### Proposals Awaiting Activation (N)
| Domain | Signal | Scan Date | Proposed Question | Suggested Slug |
|--------|--------|-----------|------------------|----------------|
### Paused Domains (N)
| Domain | Paused Since | Reason |
|--------|-------------|--------|
### Summary
- [N] domains under active surveillance
- [N] proposals waiting for your activation decision
- [N] domains never scanned (next domain-watch run will establish baseline)
- Next domain-watch run: daily at 7am UTCIf proposals are waiting: "[N] proposals in Watch Log — run /manage-watching-domains activate [slug] to seed into the incubation loop."
If domains have last_scan: null: "[N] domains have never been scanned — run /domain-watch to establish baselines."
Purpose: Add a new domain to the surveillance registry.
Argument: domain slug (e.g., quantum-computing-applications)
If the domain slug is not provided, ask for it. Then gather:
surveillance (watch for accumulation of notes on a topic) or hypothesis (track whether specific claims become answerable)surveillance for broad domains you want to monitorhypothesis for specific questions where you're waiting for evidenceCheck that Brain/05-Meta/Watching/[domain-slug].md does NOT already exist. If it does, warn and stop.
Check the slug is not already in the registry. If it is, warn and stop.
date '+%Y-%m-%d'Create Brain/05-Meta/Watching/[domain-slug].md:
---
created: YYYY-MM-DD
updated: YYYY-MM-DD
created_by: claude-sonnet-4-6
updated_by: claude-sonnet-4-6
agent_version: 01.25
slug: [domain-slug]
label: "[Human-readable label]"
mode: [surveillance|hypothesis]
watch_queries:
- "[primary search term]"
- "[secondary search term]"
priority_intelligence_requirements:
- "PIR 1: [specific answerable question]"
- "PIR 2: [specific answerable question]"
last_scan: null
notes_at_scan: 0
spawn_threshold: [N]
---
# Watching: [Label]
## Why This Domain
[1-2 sentences on why this domain warrants ongoing surveillance]
## What Would Trigger Incubation
[Concrete examples of the kind of signal that would warrant a thinking topic]
## Related Thinking Topics
None yet.Edit Brain/05-Meta/Watching/WATCHING-REGISTRY.md:
Add a row to the domains table:
| [domain-slug] | [label] | [mode] | null | active |Update updated and updated_by in frontmatter.
Report:
Brain/05-Meta/Watching/[domain-slug].mdPurpose: Take a Watch Log proposal and create a thinking topic from it, completing the perception → deliberation handoff.
Argument: suggested-slug from a Watch Log proposal (or domain-slug to pick the latest proposal for that domain)
Read Brain/05-Meta/Watching/WATCH-LOG.md.
Find the proposal matching the slug argument. If multiple proposals exist for the same domain, show them all and ask which to activate.
If the proposal is already marked **Activated:**, warn and stop.
Extract from the proposal:
Check that Brain/05-Meta/Thinking/[suggested-slug].md does NOT already exist.
Check that the slug is not already in the Thinking Registry. If so, warn and offer to use a variant slug.
Present the proposed central question and hypotheses. Ask:
"Activating: [suggested-slug]
Central question: [question] H1: [statement] (~X%) H2: [statement] (~Y%)
Any changes before creating? (Press enter to accept as-is, or describe revisions)"
[APPROVAL GATE] Wait for response.
Create Brain/05-Meta/Thinking/[suggested-slug].md using the standard incubation-loop template:
---
created: YYYY-MM-DD
updated: YYYY-MM-DD
created_by: claude-sonnet-4-6
updated_by: claude-sonnet-4-6
agent_version: 01.25
topic: "[exact central question]"
run_count: 0
last_run: null
status: active
---
# Thinking: [Topic Title]
## Central Question
[The exact question from the proposal, with any revisions]
## Why This Question Matters
[1-2 sentences synthesized from the Watch Log signal basis]
## Initial Hypotheses
| Hypothesis | Initial Confidence | Basis |
|-----------|-------------------|-------|
| H1: [statement] | X% | [from proposal known evidence] |
| H2: [statement] | Y% | [from proposal known evidence] |
## Known Evidence (Pre-Run)
[Note links and external sources from the Watch Log proposal]
## Constraints and Assumptions
[Any scope limits worth noting]
---
*Analytical runs will be appended below by the incubation loop*Edit Brain/05-Meta/Thinking/THINKING-REGISTRY.md:
Add a row to the Active Topics table:
| [suggested-slug] | [central question] | active | 0 | null |Update updated and updated_by in frontmatter.
Edit Brain/05-Meta/Watching/WATCH-LOG.md:
Find the proposal entry and append under it:
**Activated:** [[suggested-slug]] — YYYY-MM-DDUpdate updated and updated_by in frontmatter.
Edit Brain/05-Meta/Watching/[domain-slug].md:
In the Related Thinking Topics section, add:
- [[suggested-slug]] — activated YYYY-MM-DDUpdate updated and updated_by in frontmatter.
Report:
Brain/05-Meta/Thinking/[suggested-slug].mdPurpose: Temporarily suspend a domain from scanning (without deleting its config or history).
Argument: domain slug
Read Brain/05-Meta/Watching/[domain-slug].md. Show:
[APPROVAL GATE] Ask:
"Pausing '[label]' will stop domain-watch from scanning this domain on scheduled runs. The config and Watch Log history are preserved. Reason for pausing? (or type 'cancel')"
Capture the reason.
Edit Brain/05-Meta/Watching/[domain-slug].md:
paused_reason: "[reason]" to frontmatterpaused_on: YYYY-MM-DD to frontmatterupdated and updated_byEdit Brain/05-Meta/Watching/WATCHING-REGISTRY.md:
Status column to pausedupdated and updated_by in frontmatterReport:
paused_reason and paused_on, set registry status back to activePurpose: Modify a domain's PIRs or watch queries to sharpen its signal detection.
Argument: domain slug
Read Brain/05-Meta/Watching/[domain-slug].md. Display current:
[APPROVAL GATE] Ask:
"What do you want to update for '[label]'?
- Add/remove/edit a watch query
- Add/remove/edit a PIR
- Change the spawn threshold (or describe the change directly)"
Apply the requested changes. Do not overwrite other frontmatter fields.
Edit Brain/05-Meta/Watching/[domain-slug].md:
updated: YYYY-MM-DD and updated_by: claude-sonnet-4-6Report the specific fields changed and their new values.
| Error | Recovery |
|---|---|
| Watching Registry missing | Stop; inform user to create it or run /domain-watch first |
| Domain config missing for registry entry | Log warning; show the slug and offer to remove the orphaned registry entry |
| Slug already exists (seed mode) | Stop; show existing file path |
| No proposals in Watch Log (activate mode) | Report; suggest running /domain-watch to scan domains |
| Proposal already activated (activate mode) | Stop; show the thinking topic it was activated into |
| Domain already paused (pause mode) | Show current pause reason; ask if they want to resume instead |
After completing this skill's primary task, consider tactical improvements:
git add .claude/skills/manage-watching-domains/SKILL.mdgit commit -m "refactor(manage-watching-domains): <brief improvement>"© Abilityai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/manage-watching-domains of Abilityai/cornelius.
Open the folder on GitHubat commit b9bea90
Manage Watching Domains next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Manage Watching Domains this skillAbilityai/cornelius | 109 | — | ~3.5k | Automated safety check: Notes | MIT | |
| Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore | 195 | 40 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Audit Onboarding Proposalhoangnb24/repository-harness | 1.2k | — | ~4k | Automated safety check: Pass | MIT | |
| No Negative EchoLB623/no-negative-echo | 900 | — | ~965 | Automated safety check: Pass | MIT | |
| GEO Service Proposal Generatorzubair-trabzada/geo-seo-claude | 11k | — | ~3k | Automated safety check: Notes | MIT | |
| Architectural ProposalsFritzAndFriends/SharpSite | 145 | 2 repos | ~1.6k | Automated safety check: Pass | MIT |
aws-samples/sample-strands-agent-with-agentcore
Guide users through a structured workflow for co-authoring documentation.
hoangnb24/repository-harness
Use only when the user explicitly invokes $audit-onboarding-proposal.
LB623/no-negative-echo
Prevent 此地无银三百两式 residue: finalize artifacts without echoing rejected session-only alternatives into labels, metadata, commits, PRs, or handoffs.
zubair-trabzada/geo-seo-claude
Builds a client-ready AI-search-optimization proposal from an existing GEO audit, with pricing tiers, an ROI estimate and a markdown document ready to send.
FritzAndFriends/SharpSite
How to write comprehensive architectural proposals that drive alignment before code is written
zubair-trabzada/ai-legal-claude
Generates specific counter-proposals for every unfavorable clause, with replacement language, negotiation talking points, and a ready-to-send email template
Abilityai/cornelius
Generate images using Google's Nano Banana (Gemini 2.5 Flash Image).
Abilityai/cornelius
Systematic benchmarking framework for Local Brain Search memory system with LLM-as-judge scoring
Abilityai/cornelius
Protocol for creating dated changelog files after significant agent sessions.
Abilityai/cornelius
Create long-form articles from knowledge base insights. An agent skill from Abilityai/cornelius.
Abilityai/cornelius
Structure a decision, not just advise on it. An agent skill from Abilityai/cornelius.
Abilityai/cornelius
Framework for distinguishing research findings from hypotheses and speculative synthesis.
Categories
Manage domain-watch surveillance configs — seed new domains, review scan status and proposals, activate Watch Log proposals into thinking topics, pause domains, and update PIRs or watch queries. Manage Watching Domains is an agent skill from Abilityai/cornelius.
Manage Watching Domains fits situations like: tasks that involve Proposals and quotes.
Run `npx skills add Abilityai/cornelius --skill manage-watching-domains -a claude-code`. Or copy the skill folder (.claude/skills/manage-watching-domains in Abilityai/cornelius) into .claude/skills/manage-watching-domains in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Abilityai/cornelius --skill manage-watching-domains -a codex`. Or copy the skill folder (.claude/skills/manage-watching-domains in Abilityai/cornelius) into .agents/skills/manage-watching-domains in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Abilityai/cornelius --skill manage-watching-domains -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manage-watching-domains, .gemini/skills/manage-watching-domains, .github/skills/manage-watching-domains and .opencode/skills/manage-watching-domains in your project.
Going by SKILL.md and its folder, Manage Watching Domains needs the command-line tools its instructions call (git). Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, Bash.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Manage Watching Domains is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Manage Watching Domains: Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Audit Onboarding Proposal (hoangnb24/repository-harness, 1.2k stars), No Negative Echo (LB623/no-negative-echo, 900 stars) and GEO Service Proposal Generator (zubair-trabzada/geo-seo-claude, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Abilityai (a GitHub organization) maintains it in Abilityai/cornelius, which has 109 GitHub stars. The repository holds 54 skills in this directory. The repository was last updated on October 8, 2026.
Source: Abilityai/cornelius on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.