---
name: cognitive-behavioral-toolkit
description: Use this skill when a request calls for applied cognitive-behavioral techniques to manage stress, decision pressure, or unhelpful thinking patterns in a high-pressure work setting. Use it to structure a first-pass self-management plan quickly while keeping a qualified professional in the loop for anything clinical.
---

# Cognitive-Behavioral Toolkit

> **What this is** — a repeatable, AI-assisted working method for taking a request in applied cognitive-behavioral techniques for personal effectiveness and stress management under high-pressure work, often beyond one's own formal training, and producing a rigorous, well-structured first pass quickly, with a qualified professional kept in the loop.
> **What this is NOT** — not clinical treatment, therapy, or a mental-health diagnosis, and not a substitute for a licensed mental-health professional. If you are experiencing significant distress, a crisis, or persistent symptoms, seek a qualified clinician. Every output is a draft for review before it is relied on.

## When to use this
- Preparing for a high-stakes presentation, review, or negotiation and noticing anxious or catastrophic thinking that needs to be examined rather than acted on.
- Working through a recurring workplace worry (an unanswered email, an ambiguous signal from a manager) that is consuming attention out of proportion to its likely impact.
- Testing a self-limiting assumption at work ("if I ask for help they will think I am incompetent") with a small, safe, real-world check.
- Regulating acute stress in the moment — before a difficult conversation or during a demanding sprint — with standard grounding and breathing techniques.
- Building a lightweight, personal stress-management routine that can be reviewed with a professional if patterns persist.

## Operating principle
AI plus structure produce the legwork and the first draft fast: the thought record is laid out, distortions are named, an experiment is designed, and a regulation technique is selected in minutes. Human judgment governs what is relied on, and where distress is significant or persistent, a licensed professional governs the clinical decisions. The aim is speed to a defensible, self-management draft — not replacing the clinician.

## Capability 1 — Thought recording & cognitive reframing
**Goal.** Turn an anxious, automatic reaction into a written, examinable record and a more balanced alternative thought.
**Inputs.** A specific triggering situation, the automatic thought(s) it produced, and the felt emotion with a rough 0–100 intensity rating.
**Method.**
1. Capture the **situation** in one factual sentence (who, what, when — no interpretation).
2. Record the **automatic thought(s)** verbatim and rate belief in each (0–100%).
3. Name the **emotion(s)** and intensity (0–100).
4. Screen the thought against a **cognitive-distortions checklist**: all-or-nothing thinking, overgeneralization, mental filter, mind-reading, fortune-telling, catastrophizing, emotional reasoning, "should" statements, labeling, personalization.
5. List concrete **evidence for** the thought — observable facts only.
6. List concrete **evidence against** the thought — facts, counter-examples, prior outcomes.
7. Write a **balanced reframe** that accounts for both columns (not forced positivity; a fair, defensible reading).
8. Re-rate belief and emotion intensity to see what shifted.
**Output.** A completed thought record (situation → automatic thought → distortions flagged → evidence for/against → balanced reframe → re-rating).
**Quality bar.** The reframe is grounded in the evidence columns, names at least one specific distortion if present, and would read as fair to a neutral third party. If the thought concerns self-harm, hopelessness, or safety, the record is stopped and routed to a professional.

## Capability 2 — Behavioral experiment design
**Goal.** Test an anxious prediction against reality with a small, safe, real-world experiment rather than avoiding or ruminating.
**Inputs.** The belief or prediction to test, a rough confidence level, and the situations where it could realistically be checked.
**Method.**
1. State the **hypothesis** as a testable belief ("if I ask a clarifying question in the meeting, I will be judged as unprepared").
2. Make a **specific prediction** with an observable outcome and a confidence rating (0–100%).
3. Design the **smallest safe experiment** that would produce evidence — low-stakes, reversible, within your control.
4. Define in advance what result would **confirm** and what would **disconfirm** the prediction.
5. Note **safety behaviors** to drop (over-preparing, hedging) so the test is clean.
6. Run the experiment once.
7. Record the **actual outcome** factually.
8. **Review** outcome against prediction and update the belief accordingly.
**Output.** A one-page experiment card (hypothesis → prediction + confidence → experiment → confirm/disconfirm criteria → actual outcome → updated belief).
**Quality bar.** The experiment is genuinely small and safe, the prediction was written before running it, and the review compares result to prediction honestly. Anything involving real risk to wellbeing, employment, or relationships is escalated for human review first.

## Capability 3 — Emotion-regulation techniques
**Goal.** Reduce acute stress or rumination in the moment using standard, evidence-based techniques so a clearer decision can follow.
**Inputs.** Current state (activated, ruminating, avoidant) and how much time is available (seconds vs. minutes).
**Method.**
1. **Grounding (5-4-3-2-1):** name five things seen, four heard, three touched, two smelled, one tasted — to reorient to the present.
2. **Cognitive distancing / defusion:** restate the thought as "I am having the thought that…" to observe it rather than fuse with it (an ACT technique).
3. **Scheduled worry / decision window:** postpone a recurring worry to a fixed 15-minute slot later, freeing attention now and containing rumination.
4. **Paced breathing:** slow, even breaths with a longer exhale than inhale for a few minutes, at a comfortable pace.
5. **Select the fit:** grounding for acute activation, defusion for sticky thoughts, scheduled worry for rumination, paced breathing to settle physiologically.
6. **Note the effect** (0–100 before/after) to learn which technique works for which state.
**Output.** A short, personalized regulation menu mapping states to techniques, with before/after ratings.
**Quality bar.** Every technique is standard and physically safe; none involves pain, self-harm, sensory shock, or disordered eating/exercise. If distress does not ease or recurs, the menu explicitly points to professional support.

## Worked example (illustrative)
*Illustrative only.* A designer is anxious before presenting a system to a C-level stakeholder and keeps thinking, "they will realize I don't belong here." **Capability 1:** a thought record flags mind-reading and fortune-telling; evidence-against includes prior approved presentations and an explicit invite to present. The reframe: "I am prepared on the parts that matter; some questions may stump me, and that is normal and recoverable." Belief drops from 85% to 40%. **Capability 2:** the prediction "if I say 'I'll confirm that number and follow up,' I'll look incompetent" is tested by doing exactly that once; the actual outcome is a neutral nod and a follow-up thanked later — belief updated. **Capability 3:** before walking in, 4 rounds of paced breathing plus one round of grounding bring activation from 70 to 45. The whole packet is a self-management draft; if the anxiety were persistent or impairing, it would be routed to a clinician.

## Guardrails & escalation
- STOP and hand to a licensed mental-health professional if there is any sign of self-harm, harm to others, hopelessness, a crisis, or symptoms that are persistent, worsening, or impairing daily functioning.
- Nothing here diagnoses or treats a condition; no output should be acted on as clinical care without professional review.
- Techniques are restricted to standard, safe CBT/ACT self-help methods — never anything involving physical pain, self-harm, sensory shock, or disordered eating or exercise.
- Uncertainty and limits are flagged in the output itself: every artifact is labelled a draft, notes that it is workplace self-management rather than therapy, and states when professional help is the correct next step.

## References & frameworks
- Beck's cognitive model (cognitive therapy) — the situation → automatic thought → emotion → evaluation structure underlying the thought record.
- Standard CBT thought-record method (evidence-for / evidence-against / balanced alternative), as taught in cognitive-behavioral self-help.
- Behavioral experiments as used in CBT to test predictions against real outcomes.
- Acceptance and Commitment Therapy (ACT) cognitive defusion (e.g., "I am having the thought that…").
- Grounding (5-4-3-2-1) and paced breathing as widely-used stress-regulation techniques.
- These are self-help adaptations of clinically-developed methods; they are not a clinical protocol and do not replace assessment or treatment by a licensed professional.

---
*Part of Ed Chen's AI skill set — how one designer absorbs unfamiliar, C-level work quickly by pairing AI with rigor and professional review. https://edwson.com*