Agent Capabilities

Skills Library

The protocols that keep AI agents sharp across complex, real-world work. Not templates. Actual engineering for founders, coaches, and creators whose standards cannot be reduced to generic prompts.

Featured Protocol

Deep Work Protocol

For any task where the input is large and the risk of quality trail-off is real.

Auto-activating
File-persistent notes
Self-assessing
A large file (PDF, transcript, course content) arrives for analysis
Multi-section research or review tasks
Any task flagged as exhaustive or high-stakes
Course review or large-scale content extraction
1

Setup

Create a persistent notes file before starting. This file IS the continuity. Not memory. Not context window. The file itself.

If the session dies mid-task, the next session picks up from that file. No progress lost. No re-reading the source.

3

Quality Checkpoints

Every 3-4 sections, a mandatory self-assessment fires. Not optional. Not skippable.

? Am I still extracting real substance or just summarizing headers?
? Are my insights getting shallower?
? Am I rushing to finish rather than going deep?
? Would the client look at this and say "you trailed off"?

If the answer to any of these is yes: hard stop. See step 4.

4

Hard Stop Protocol

When quality starts degrading, the correct move is to surface it directly rather than push through with diminishing returns.

Hard Stop
01 Write everything captured so far to the notes file
02 Add a PICKUP POINT section: what's done, what's remaining, patterns noticed
03 Surface it to the client with a clear quality assessment and what remains
5

Expert Knowledge Capture

After completing all sections, key concepts get broken into structured knowledge entries that can be recalled and applied in future conversations.

Each entry carries enough detail to actually advise from, not just reference. The goal is recalled knowledge with real substance, not just pointers to where the info lives.

6

Completion

When genuinely done with quality maintained throughout:

Notes file is comprehensive and standalone
Summary written at top of notes file with key takeaways
Requested deliverables (strategy doc, analysis, etc.) written separately from notes
Expert knowledge capture complete if source material qualifies

Designed around how AI actually fails

"You will probably get tired and confused and lose steam. We need a plan for what you do when that happens."

"I notice you often start work off strong and then sort of trail off."

The protocol exists because quality degradation on long tasks is predictable. Without enforced checkpoints and file-based continuity, agents work well for the first 40% and coast through the rest. This skill changes that default.

Anti-Patterns

The failure modes this protocol is specifically engineered to prevent.

Pattern 1
Trying to hold everything in context instead of writing it down
Pattern 2
Processing linearly without stopping to checkpoint quality
Pattern 3
Pushing through degradation instead of surfacing a hard stop
Pattern 4
Summarizing headers instead of extracting real substance
Pattern 5
Rushing the last 30% to reach "done" rather than staying deep
The protocol addresses all five
Not one. All of them.
Featured Protocol

Intelligence Brief Protocol

For structural questions where you need source-grounded analysis, not news summaries or punditry.

📋 Source-grounded
🔬 Depth-tested
Hypothesis-driven
A structural or geopolitical question needs analysis beyond news coverage
Power dynamics, infrastructure dependency, or narrative control topics
Any question where who controls what matters more than what happened
Recurring intelligence products or deep-dive analysis requests
1

Frame the Question

Start with a live, structural question -- not "what happened" but "what system is being revealed." Define the time horizon (30/60/90 days), audience, and your analytical lens. The question shapes every source decision that follows.

Bad: "What's happening with AI?" Good: "Who controls the infrastructure layer under AI models, and how does that control translate into geopolitical leverage over the next 12 months?"

3

Build the Evidence Base

For each source cluster, build a source and scope ledger: domain, timeframe, search terms, sources consulted, classification, and what the source can and cannot prove. Then identify the primary driver and explain the causal mechanism -- how A leads to B, not just what's happening.

4

Run Competing Hypotheses

Test the central thesis against structured alternatives. H0 is your primary hypothesis. H1 is the null -- the pattern is noise or temporary. H2 names an alternative driver. H3 is a model miscalibration check -- where might you be pattern-matching too aggressively?

H0 Primary hypothesis with evidence for, evidence against, probability, confidence
H1 Null hypothesis -- is the apparent pattern noise, temporary, or overread?
H2 Alternative driver -- what other actor, constraint, or force could explain this?
H3 Miscalibration check -- where is the analyst overfitting a familiar frame?
6

Quality Gate

Before calling a brief finished, answer eight questions. If the answers are weak, the brief is not deep yet.

? What source conflict did this brief preserve?
? What actor incentive is easy to miss?
? What constraint is most likely to become binding first?
? What would make the main thesis wrong?
? What external shock could change the forecast?
? What public story is being used to manage legitimacy?
? What indicator would you check in 30 days?
? What did the model almost overfit?
7

Public Translation

The public version should not look like an intelligence report. Start from the live thing people saw. Name the structure underneath it. Give 2-3 concrete signals. Explain the causal mechanism. Name why the obvious interpretation is too small. Say what to watch next. End on the structure reveal, not a CTA.

A good brief should make the reader feel: "I saw the event. They saw the system." That is the point. The product feels like intelligence because of structure and source transparency, not because of secret information.

Do not perform certainty. Do not flatten the issue. If evidence is thin, say so. Preserve uncertainty without becoming mushy.

Designed around how analysis actually fails

Most "analysis" is news recaps with opinions stapled on. No source ledger. No competing hypotheses. No acknowledgment of what the analyst might be wrong about.

The depth pass exists because first drafts of intelligence always feel done. They aren't. The layers that catch overfit, correlated sources, and missing constraints are the ones that make the brief trustworthy.

This protocol exists because the gap between "I read about it" and "I understand the system" is exactly the gap the depth pass fills. Source transparency plus structured uncertainty plus specific observable indicators. That's the methodology.

Anti-Patterns

The failure modes this protocol is specifically engineered to prevent.

Pattern 1
Echo chamber sourcing -- all sources from the same news cycle citing the same original report
Pattern 2
Performing certainty -- stating conclusions without probability bands or confidence levels
Pattern 3
Skipping the null hypothesis -- never asking "what if this pattern is noise?"
Pattern 4
Vague indicators -- "watch for market shifts" instead of specific, observable thresholds
Pattern 5
Conflating narrative with fact -- treating a public statement as proof of an operational reality
The depth pass catches all five
That's why it's not optional.

Get your personalized AI roadmap for the AI age

Answer a few questions about your business. Get a custom plan that shows where AI fits the work only you can do and what to build first.

Get My AI Roadmap