Install
$ agentstack add skill-tonysina-claude-skills-strategic-persuasion-writing ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Strategic Persuasion Writing
Create messaging that drives action by targeting psychological drivers beneath conscious awareness. Effective persuasion works because our ancestors needed to survive — the brain responds to focus, authority, tribal belonging, and emotion before it engages rational thought. The closer your technique reaches to these primal systems, the more powerful the result.
Core Principle
All persuasion operates through three layers, from deepest to shallowest: impulse (ancestral scripts hardwired in DNA), emotion (neurochemical cascades), and thought (rational processing). Most people only target thought. This skill targets all three.
5-Step Strategic Writing Workflow
Step 1: ANALYZE & PROFILE
Gather or review the subject's behavioral profile. See references/behavior-profile-template.md for the full template.
If the user provides a complete profile: Identify the subject's core vulnerability by cross-referencing their primary Need (what they're chemically addicted to getting from social interactions), their Decision Map filter (how they make choices), and priority states on the Six-Axis Model.
If the user provides partial information: Work with what's available. At minimum, you need:
- The desired action (what should the subject do?)
- The communication format (email, script, presentation, etc.)
- Any context about the subject (role, situation, relationship)
Infer likely Need, Decision style, and priority states from context clues. State your assumptions to the user.
If the user provides no profile: Ask for the desired action and subject context, then use the guided interview in the profile template to gather key data points. Prioritize: primary Need, sensory preference, and 2-3 positive/negative adjectives.
Step 2: STRUCTURAL DESIGN
Design the message architecture using the PCP Model (Perception → Context → Permission). This sequence works because people must first see the situation differently before they'll accept new behavioral norms, and they need psychological permission before they'll act.
Read references/structural-models.md for the full PCP framework, FATE application, and Six-Axis state definitions.
Step 3: LIAISON ACTIVATION
Layer ancestral triggers (FATE) into early and late stages of the message. Focus and Emotion open the message; Authority and Tribe reinforce the middle; Emotion closes. These triggers activate scripts inherited from ancestors — automatic responses that bypass rational filtering.
Four rules of behavioral scripts (from source material):
- If a script is interrupted, focus is created
- If borrowed from someone's past experience, predictability is created
- If borrowed from ancestors, automation is created
- If openly discussed, its power is lessened
Step 4: LINGUISTIC HACKING
Apply targeted linguistic tools to reinforce the core message. Read references/linguistic-techniques.md for:
- Embedded commands and presupposition patterns
- Right-branching sentence structure (emotional reveals at end)
- Associative hacking (needs/adjective/sensory matching)
- Scarcity and regret triggers
- Dissociative linguistics and identity hacking
- Metaphor as an influence vehicle
- Journey → Connection → Reveal narrative pattern
Step 5: IMPACT REVIEW
Verify the output meets the Three Cs:
- Captivating: Opens with novelty, pattern interrupts, or emotional triggers that capture ancestral focus
- Confident: Uses authoritative language, presuppositions, and certainty (no filter words: "maybe," "perhaps," "might")
- Concise: Every word serves a strategic purpose; no filler that dilutes impact
Also verify:
- Core emotional reveals use right-branching structure (reveal at end of statement)
- Subject's positive adjectives describe desired actions; negative adjectives describe inaction
- Sensory language matches subject's primary mode (visual/auditory/kinesthetic)
- Core Need is referenced 4-6 times throughout
- At least 6-8 techniques from linguistic-techniques.md are layered in
- Embedded commands appear multiple times, marked with emphasis
Quick Example
Input: "Write a persuasive email to close a deal with a CFO who values data and ROI. She's analytical, uses visual language, and is comparing us to a competitor."
Inferred profile: Need = Intelligence, Decision = Investment, Sensory = Visual, Priority States = Focus + Expectancy + Compliance, Positive adj = "clear/proven/strategic", Negative adj = "risky/unclear"
Output approach: Open with unexpected data point (Focus via FATE). Shift perception with ROI comparison (PCP-Perception). Normalize with peer adoption stats (PCP-Context + FATE-Tribe). Future-pace the board presentation she'll give (6AM-Expectancy). Close with double-bind timing (6AM-Compliance). Thread visual language and "clear/proven" adjectives throughout.
Key Resources
| File | Read when... | |------|-------------| | references/structural-models.md | Designing message architecture (Step 2-3). Contains FATE, PCP, and Six-Axis frameworks with layering sequences. | | references/linguistic-techniques.md | Applying linguistic tools (Step 4). Contains embedded commands, right-branching, scarcity, dissociation, metaphor, and narrative patterns. | | references/examples.md | Looking for pattern inspiration. Contains 5 complete examples with behavior profiles and annotated outputs. | | references/behavior-profile-template.md | Gathering subject information (Step 1). Complete input template with Needs Map, Decision Map, Values Map, and linguistic preferences. |
Ethical Boundaries
These techniques are powerful. Use them for win-win outcomes where the subject genuinely benefits from taking the desired action. Never use for manipulating vulnerable populations, concealing material information, bypassing informed consent, or coercing harmful decisions.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: tonysina
- Source: tonysina/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.