New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Weekly Signal Diff

by NateBJones-Projects in NateBJones-Projects/OB1

Turns a noisy week of AI or software market news into a short list of structural changes, weighted by what the user already tracks in Open Brain memory.

Custom licenceAuto-check passedResearch & Science

Install Weekly Signal Diff

skills CLI
$ npx skills add NateBJones-Projects/OB1 --skill weekly-signal-diff -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NateBJones-Projects/OB1 weekly-signal-diff --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/weekly-signal-diff .claude/skills/weekly-signal-diff && rm -rf skills-src

Use ~/.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/

Facts

Skill name
weekly-signal-diff
GitHub stars
4.7k
Token cost
~1.7k tokens
SKILL.md length
877 words
Files
5 (incl. references)
Skills in repo
24
Repo updated
First seen
Licence
Custom licence

At a glance

Turns a noisy week of AI or software market news into a short list of structural changes, weighted by what the user already tracks in Open Brain memory.

  • Works in 7 steps: Establish the frame. → Pull Open Brain context first. → Build the watchlist. → …
  • Running a weekly review of a market the user is actively tracking
  • SKILL.md covers Problem, When to Use, Required Context and Process, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Rather than another headline roundup, the skill is built to surface what structurally changed in a fast-moving market over the last 7 days by default. It first pulls the user's active projects, current priorities and the last two to four weekly digests out of Open Brain memory, since tool names for that search vary by client and must be discovered rather than assumed.

When no watchlist exists, it starts from a bootstrap list of 10 suggested categories and 30 suggested companies in references/starter-universe.md, then re-ranks or replaces entries using what the memory layer shows the user actually cares about, promoting frequently mentioned themes and demoting low-signal ones. If live web access is available, it reads references/live-search-upgrade.md and prefers the Perplexity Sonar family through OpenRouter for fresh, citable retrieval.

When your agent uses it

  • Running a weekly review of a market the user is actively tracking
  • Turning a week of scattered news into a small set of structural shifts
  • Building a first watchlist for a market with no existing tracking set up

Example prompts

  • “Run my weekly signal diff for the AI agent market.”
  • “What changed this week that matters to my current projects?”
  • “Track the enterprise search market and tell me the structural shifts.”

Requirements

  • Open Brain memory tools for search, list and capture
  • OpenRouter access, for the live Perplexity Sonar search upgrade

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Establish the frame.
  2. Pull Open Brain context first.
  3. Build the watchlist.
  4. Gather the week's evidence.
  5. Ask the structural questions on every candidate signal.
  6. Score before writing.
  7. Produce the weekly diff.

What it can do on your machine

Read from SKILL.md and the folder at commit 238df6c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Weekly Signal Diff loads about 1.7k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 152 tokens; SKILL.md has 877 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~152
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

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.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated 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.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 877 words (~1,711 tokens).

“A wall of news does not tell the user what structurally changed. Most weekly roundups over-index on headlines, underweight economics and dependency shifts, and ignore what the user actually cares about. This skill turns a noisy week into a small…”

— opening of SKILL.md by NateBJones-Projects, Custom licence
name
weekly-signal-diff
author
Jonathan Edwards
version
1.0.0

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (references) in skills/weekly-signal-diff of NateBJones-Projects/OB1.

  • SKILL.md
  • README.md
  • metadata.json
  • references/live-search-upgrade.md
  • references/starter-universe.md

Open the folder on GitHubat commit 238df6c

Compare with similar skills

Weekly Signal Diff 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.

Weekly Signal Diff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Weekly Signal Diff this skillNateBJones-Projects/OB14.7k—~1.7kAutomated safety check: PassCustom licence
AI RAG PipelineNeverSight/learn-skills.dev2161 repos~2kAutomated safety check: PassNone
Perplexity Web Searchdavila7/claude-code-templates32k11 repos~3.5kAutomated safety check: NotesMIT
Bmad Deep Recondelorenj/mcp-server-trello445—~2.3kAutomated safety check: PassMIT
Perplexity SearchescapeWu/perplexity-ai170—~1.8kAutomated safety check: PassMIT
Deep Researchjuanandresgs/claude-ctrl193—~3.1kAutomated safety check: NotesNone

Similar skills

  • AI RAG Pipeline

    NeverSight/learn-skills.dev

    Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs.

    216 GitHub starsUsed in 1 repo~2k tokens
    AI & LLM EngineeringAuto-check passed

  • Perplexity Web Search

    davila7/claude-code-templates

    Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.

    32k GitHub starsUsed in 11 repos~3.5k tokens
    Research & ScienceAuto-check: notes

  • Bmad Deep Recon

    delorenj/mcp-server-trello

    Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill…

    445 GitHub stars~2.3k tokensUpdated 15 days ago
    Research & ScienceAuto-check passed

  • Perplexity Search

    escapeWu/perplexity-ai

    Searches the live web with citations through perplexity-mcp v2 tools or a bundled Python REST client, with focused ask, deep research and detached tasks.

    170 GitHub stars~1.8k tokensUpdated 12 days ago
    Productivity & AutomationAuto-check passed

  • Deep Research

    juanandresgs/claude-ctrl

    Multi-model deep research with comparative assessment (OpenAI + Perplexity + Gemini).

    193 GitHub stars~3.1k tokensUpdated 2 mo ago
    Research & ScienceAuto-check: notes

  • Brain-Augmented Web Research

    garrytan/gbrain

    Sends what your notes already know about a topic to Perplexity, so the cited web search reports only what is new, such as entity updates or deal changes.

    31k GitHub stars~2k tokensUpdated today
    Research & ScienceAuto-check: notes

More from NateBJones-Projects/OB1

All 24 skills in this repo

  • Heavy File Ingestion

    NateBJones-Projects/OB1

    Converts large PDF, DOCX, PPTX, XLSX and CSV files into markdown or CSV plus an index before the agent reads them, so tokens go to the compressed copy.

    4.7k GitHub stars~995 tokensUpdated yesterday
    Auto-check passed

  • Aiception Skill Extraction

    NateBJones-Projects/OB1

    Pulls reusable knowledge out of work sessions and turns it into new skills, checking existing notes and skills first to avoid duplicates.

    4.7k GitHub stars~2k tokensUpdated yesterday
    Auto-check: notes

  • Claude Code Auto-Capture Hook

    NateBJones-Projects/OB1

    Fires a Stop hook that captures a Claude Code session transcript automatically when the session ends without a verbal wrap-up.

    4.7k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check: notes

  • Open Brain Local HTTP

    NateBJones-Projects/OB1

    Captures and searches personal notes in a self-hosted Open Brain using plain curl calls over HTTP, for setups where MCP is disabled or blocked.

    4.7k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check: notes

  • Panning for Gold

    NateBJones-Projects/OB1

    Processes voice transcripts and brain dumps in three phases, extracting every idea thread, evaluating the strongest and saving a permanent inventory and synthesis.

    4.7k GitHub stars~5k tokensUpdated yesterday
    Auto-check passed

  • Agentic Harness Design and Review

    NateBJones-Projects/OB1

    Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.

    4.7k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Weekly Signal Diff

What does Weekly Signal Diff do?

Turns a noisy week of AI or software market news into a short list of structural changes, weighted by what the user already tracks in Open Brain memory. Rather than another headline roundup, the skill is built to surface what structurally changed in a fast-moving market over the last 7 days by default. It first pulls the user's active projects, current priorities and the last two to four weekly digests out of Open Brain memory, since tool names for that search vary by client and must be discovered rather than assumed.

When should I use Weekly Signal Diff?

Weekly Signal Diff fits situations like: running a weekly review of a market the user is actively tracking; turning a week of scattered news into a small set of structural shifts; building a first watchlist for a market with no existing tracking set up.

How do I install Weekly Signal Diff in Claude Code?

Run `npx skills add NateBJones-Projects/OB1 --skill weekly-signal-diff -a claude-code`. Or copy the skill folder (skills/weekly-signal-diff in NateBJones-Projects/OB1) into .claude/skills/weekly-signal-diff in your project. Claude Code loads it when a task matches its description.

How do I install Weekly Signal Diff in Codex?

Run `npx skills add NateBJones-Projects/OB1 --skill weekly-signal-diff -a codex`. Or copy the skill folder (skills/weekly-signal-diff in NateBJones-Projects/OB1) into .agents/skills/weekly-signal-diff in your project. Codex loads it when a task matches its description.

Can I use Weekly Signal Diff in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NateBJones-Projects/OB1 --skill weekly-signal-diff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/weekly-signal-diff, .gemini/skills/weekly-signal-diff, .github/skills/weekly-signal-diff and .opencode/skills/weekly-signal-diff in your project.

What does Weekly Signal Diff need to run?

SKILL.md names no scripts, command-line tools or credentials: Weekly Signal Diff is instructions for the agent only. Our summary lists: Open Brain memory tools for search, list and capture; OpenRouter access, for the live Perplexity Sonar search upgrade.

Does Weekly Signal Diff access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Weekly Signal Diff safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Weekly Signal Diff use?

Weekly Signal Diff has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Weekly Signal Diff use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Weekly Signal Diff?

Skills that share tags, products or a category with Weekly Signal Diff: AI RAG Pipeline (NeverSight/learn-skills.dev, 216 stars), Perplexity Web Search (davila7/claude-code-templates, 32k stars), Bmad Deep Recon (delorenj/mcp-server-trello, 445 stars) and Perplexity Search (escapeWu/perplexity-ai, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Weekly Signal Diff?

NateBJones-Projects (a GitHub organization) maintains it in NateBJones-Projects/OB1, which has 4,703 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

Source: NateBJones-Projects/OB1 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.