Skip to content
SkillModel-led4,505 tokens in use

Personal Strategic Signal Intelligence

Reads your bookmarks, notes and applied work, separates attention from conviction, and produces source-cited decision briefs, contradictions and experiments.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · personal-strategic-signal-intelligence
npx skills add ericosiu/ai-marketing-skills -s personal-strategic-signal-intelligence
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Personal Strategic Signal Intelligence costs

32tokens idle
4,505tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance44
  • Community56
  • Maturity28
  • Momentum40

Personal Strategic Signal Intelligence (PSSI) turns a person’s information trail into decision support. It normalizes sources such as read-later saves, bookmarks, highlights, notes and shipped experiments, weights each by how strong a signal it is, and links every claim back to its sources.

It runs seven modules, including attention drift, a pre-decision oracle and a decision court for contradictions, and ends each promoted insight in a decision question, an experiment or a build brief.

What You Get

  • A weekly signal brief with attention and conviction scored separately for each theme
  • Candidate decisions written as questions, with evidence for acting, evidence for waiting and the smallest reversible test
  • A decision court write-up for a contradiction, with the strongest case on each side
  • Bookmark-to-build briefs, founder framework recombinations, offer hypotheses and a content gap map
  • Recommendation records with an owner, status and review date

Common Use Cases

  • Reviewing how your reading and saving have shifted over the past weeks
  • Checking whether a stated belief matches recent notes and applied work
  • Turning a cluster of saved ideas into a bounded experiment with a metric and a stop condition

What Makes It Unique

The skill uses an eight-level signal ladder that runs from a simple save up to a repeated, measured application, and it never lets many weak signals add up to a strong claim. Inferred beliefs are labeled private and provisional, earlier summaries cannot be counted as new evidence, and every material claim carries source IDs. Synthesis runs weekly or on an event, and an expert panel with a default pass mark of 90 gates what gets promoted.

Under The Hood

The skill is one long instructions file with no scripts or reference files. It tells the agent to read from whatever personal sources the user connects, such as read-later tools, bookmarks and notes, using read-only access and minimal fields, and to keep tokens out of prompts and outputs. It has no commands of its own to run. The agent writes briefs and records as documents or files and must ask for explicit approval before publishing, sending anything or changing an external system.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers