Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Coding
habit-trigger-detective
Try itUse when someone keeps failing the same habit or falling into the same bad one despite motivation. Turns a trigger journal into a statistical trigger analysis - time-of-day, location, company, device, emotional state, preceding actions - and outputs ranked cues, the habit loop, and reengineered if-then plans.
What it does
"I know what I should do. I just don't do it." The failure of habits is rarely motivation — it's **unidentified triggers**. The cigarette happens after coffee, the doomscroll starts when the phone is on the nightstand, the snack raids happen at 22:47, the skipped workouts cluster on days with early…
The skill document
Habit Trigger Detective
Overview
"I know what I should do. I just don't do it." The failure of habits is rarely motivation — it's unidentified triggers. The cigarette happens after coffee, the doomscroll starts when the phone is on the nightstand, the snack raids happen at 22:47, the skipped workouts cluster on days with early meetings. People try to change the behavior while leaving the cue architecture intact.
Behavioral science ( habit-loop research, implementation-intention studies) says: identify the CUE → understand the REWARD → reengineer the loop. This skill does the boring-but-decisive part: statistics over a trigger journal.
For 5-7 days the user logs each occurrence (wanted or unwanted behavior): time, location, who's around, device in hand, emotional state 1-5, what they were doing in the previous 30 minutes, and subjective urge strength. The analyzer then:
- Computes lift for every factor value — how much more likely the behavior is when that factor is present vs. baseline (like market-basket analysis).
- Finds time-of-day hotspots (binned into morning/afternoon/evening/night).
- Detects the preceding-action chain — the 1-2 step behavioral runway that most reliably precedes the behavior.
- Assembles the habit loop: cue → routine → (inferred) reward.
- Generates reengineered if-then plans (implementation intentions) and cue disruption moves — ranked by expected impact.
When to Use
- "I keep failing to [exercise / meditate / write / practice language]"
- "I can't stop [snacking / vaping / doomscrolling / online shopping / biting nails]"
- Any behavior the user wants more of or less of, occurring 3+ times/week
- After a streak broke: "figure out WHY it broke"
- Pre-building a new habit into an existing routine ("habit stacking" needs to know which anchor routines exist)
Don't use for: addiction-level issues (alcohol, drugs, gambling, eating disorders — refer to professionals; this is a self-tracking tool, not therapy), or one-off behaviors with no repetition.
The method
Phase 1 — Journal (5-7 days, 30 seconds per entry)
The user logs each occurrence with a fixed schema (scripts/trigger_log.py interactive mode, or a paper template in references/journal-template.md):
timestamp | behavior (smoke/scroll/snack/skip-workout...) | wanted/unwanted
location (home/work/commute/other) | alone | with-partner | with-friends | with-colleagues
device (none/phone/laptop/tv) | emotional_state 1-5 | urge 1-5
prev_action: what you were doing in the last 30 min (free text)
Critical: also log 5+ baseline entries — random moments when the urge was NOT present. Without a baseline, "80% of events happened at home" is meaningless (maybe you're home 80% of the time). Lift is computed against this baseline.
Phase 2 — Analysis
For every factor value (e.g., location=commute):
P(behavior | factor) count_events_with_factor / count_all_factor_rows
P(behavior | no factor)
lift = P(behavior|factor) / P(behavior|no factor)
- lift > 1.5 with enough samples = a real cue candidate
- The analyzer flags statistical honesty: values with < 3 samples are marked LOW-CONFIDENCE, never surfaced as top triggers.
Preceding-action chains: normalize prev_action text (lowercase, keyword map), compute P(behavior | prev_action) the same way, and find 2-step chains (A→B→behavior) when the data supports them.
Phase 3 — Intervention design
For each top trigger, two moves:
- Cue disruption — make the cue harder to reach (phone charger out of bedroom; no snacks at home → the 22:47 raid requires a walk to the store).
- If-then reengineering — keep the cue + reward, swap the routine ("IF urge after coffee > 3, THEN 10 squats + gum"). Implementation intentions with a concrete cue roughly double follow-through in the meta-analyses (Gollwitzer & Sheeran 2006: d≈.65).
Files
| File | Purpose |
|---|---|
scripts/trigger_log.py | Interactive 30-second journal entries → JSONL |
scripts/trigger_analysis.py | Lift analysis, hotspots, chains, habit loop, if-then plans |
references/journal-template.md | Paper template + emotion/urge anchors |
references/behavior-science.md | Habit loop, implementation intentions, reward inference, references |
Usage
# Log an occurrence (interactive prompts, 30 seconds)
python3 scripts/trigger_log.py log
# Log a baseline (non-event) moment
python3 scripts/trigger_log.py baseline
# Analyze after 5+ days (needs >= 8 events + 5 baselines)
python3 scripts/trigger_analysis.py journal.jsonl
# Include a specific if-then replacement behavior
python3 scripts/trigger_analysis.py journal.jsonl --replacement "10 squats"
Workflow
- Define ONE behavior with the user. One at a time.
- Have them journal 5-7 days (events + baselines). Nudge daily if you're the agent; accept imperfect entries — the analyzer tolerates free text.
- Run the analysis. Walk through RANKED TRIGGERS with the user — recognition ("yes! it's always after the work call") is the moment the skill pays off.
- Pick the top 1-2 triggers ONLY. Design cue disruption + if-then plan.
- Week 2: journal again; compare lift tables — did the cue decouple?
Common Pitfalls
- No baseline entries → every percentage is noise. The analyzer refuses to rank triggers below 5 baselines.
- Journaling multiple behaviors at once muddies statistics. One behavior per journal file.
- Judging the entries. The journal is a sensor, not a confessional. If the user starts sanitizing ("I'll skip logging the embarrassing ones"), the analysis dies. State this explicitly on day 1.
- Sample size overconfidence. 3 events at location=X with lift 4.0 is a hypothesis, not a trigger. The script marks these LOW-CONFIDENCE — don't build plans on them.
- Attacking the routine, not the cue. "Just resist harder" fails; cue removal succeeds structurally. Prefer environmental changes over willpower prescriptions.
- Week-2 verification skipped. Triggers drift; re-run the analysis after any intervention and compare.
Example Session
6 days of vaping urges, 11 events, 7 baselines. Analysis output:
LIFT 3.1 — location=commute (6/11 events, 0/7 baselines)+LIFT 2.4 — prev_action="coffee"+ hotspot 08:00-09:00. Habit loop: morning commute coffee → vape (nicotine + break from podcast) → alertness ritual. Reengineered: IF coffee on commute, THEN nicotine gum
- podcast continues; car vape pack removed (cue disruption). Week 2 re-analysis: commute lift 3.1 → 1.2. Decoupled.
Verification Checklist
- Journal has events AND baselines (≥5) before analysis
- Top triggers have lift ≥ 1.5 and ≥3 supporting events
- Each recommended if-then plan names the SPECIFIC cue (time/place/state)
- Cue-disruption option given alongside willpower option
- Week-2 re-analysis planned to verify decoupling
Related skills
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
More from voronindenis5
Browse all skillsPryamoy Russkiy (Straight Russian) — AI assistant that tells it like it is. Direct answers, no fluff, occasional profanity. Specializes in honest analysis, t...
Prepare salary negotiations with a structured toolkit: market-rate anchoring math, walk-away floor calculation, total-compensation evaluation (equity, bonuses, benefits), negotiation scripts for offers, raises, and counter-offers, and BATNA analysis. Use when the user has a job offer, is preparing a raise conversation, wants to know if their pay is competitive, or needs scripts and a strategy for negotiating compensation.
Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'we should sync weekly' and you want data, or when auditing which meetings to kill — imports ICS calendar files, measures meeting hours per week/person/meeting-series (including double-bookings and fragmentation), computes focus-time destruction from meeting placement, scores the true cost of each series (hours × attendees × frequency), flags specific meetings to kill/shorten/make-async using explicit rules, and simulates the recovered hours before anyone has to argue about it.
Use when you realize your photos/code/documents exist in exactly one place (or your 'backup' is a external drive in the same room as the computer) — audits your actual data-loss risk against the 3-2-1 rule (3 copies, 2 media, 1 offsite) asset by asset, scores blast radius (ransomware encrypts synced copies too), prices honest recovery (professional recovery lab $300-3000 vs $0), generates the minimum-cost redundancy plan for YOUR asset list, and produces a restore-test drill because an untested backup is a hope, not a backup.
Audit password vault exports (Bitwarden, 1Password, KeePass, Chrome, Firefox) for reuse, weakness, staleness, breach exposure, and 2FA gaps without ever storing or transmitting a plaintext password. Use when the user asks to audit passwords, check password strength/reuse, review vault health, or verify whether credentials appeared in breaches.
Use before any difficult phone call you're anxious about or that has stakes — calling customer service to dispute a fee, negotiating a bill, cold-calling a client, delivering bad news to a vendor, calling a landlord about repairs, insurance disputes, or handling collections calls — builds a branching call script from your situation (goal, leverage, fallback), generates objection→response trees for the specific counter-arguments you'll hear, produces a one-page printable cheat sheet, and includes a practice-drills mode that plays the other side and scores your responses.