# Identity Votes > Use when a user explicitly asks for an identity-vote analysis, provides several days or weeks of behavior, or wants to compare who their repeated choices are reinforcing over time. Produces an evidence-calibrated identity trajectory and one high-ROI next vote. For a lightweight read at the end of one ordinary conversation, use identity-vote-translator instead. - Skill: `myfeng10/identity-votes` (Agent Skill, multi-file: 3 files) - Install (CLI): `npx skillmds@latest add myfeng10/identity-votes` - Raw SKILL.md: https://api.skillmd.com/api/skills/myfeng10/identity-votes/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: myfeng10 (https://skillmd.com/u/myfeng10) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/myfeng10/identity-votes --- # Identity Votes Use this skill for an explicit identity review or a multi-day trajectory analysis. Core principle: behavior disappears, identity accumulates. Every repeated action is a vote for a kind of person. This is inspired by James Clear's identity-based habits framework from Atomic Habits. Do not summarize the book unless asked; use the framework as practical grounding for the skill. ## Core Advantage The agent can turn several behaviors into an evidence ledger, compare competing identity trajectories, and identify the next action that would change the pattern. High ROI: replace vague personality language with a behavior-grounded trajectory and one next action. ## Who This Is For Use this for people who want behavior-level self-awareness without vague personality analysis. Especially useful for users with ADHD or scattered attention: they can talk naturally, and the agent extracts the identity signal. The skill should be usable by any person. Do not assume Michelle's private ontology unless someone provides it. ## Trigger Phrases - "What identity am I reinforcing?" - "What am I becoming?" - "Analyze my routine." - "Turn this day into identity votes." - "What pattern does my week show?" - "Am I becoming the person I want to be?" ## Implicit Triggers Also use this skill when the user asks for analysis of: - a repeated routine or habit loop - avoidance, procrastination, or drifting - conflict, confrontation, or emotional escalation - a good day or bad day with concrete behaviors - a desired future self - a mismatch between stated goals and actual actions - a sequence of choices across work, relationships, body care, learning, or rest Do not invoke this full review for every casual behavior description. Use `identity-vote-translator` for a lightweight end-of-conversation read. ## Inputs Accept any of: - Daily routine logs - Calendar summaries - Journal reflections - Weekly activity summaries - Messy notes about habits, relationships, work, learning, recovery, or consumption Do not require rigid formatting. If duration is available, use it. If duration is missing, weigh by intentionality, effort, emotional salience, and repetition. Treat one day or one week as limited evidence. Use conditional trajectory language and never present an identity inference as a fixed trait. ## Vote Ledger During conversation, maintain a temporary ledger: ```text Behavior observed: Identity vote: Direction: reinforces | weakens | redirects Strength: low | medium | high Evidence: Next vote candidate: ``` Only present the ledger if useful. Usually summarize the top 2-3 decision-relevant votes instead of showing everything. ## Identity Lens Prefer grounded identity types over generic traits. Examples: - someone who builds original systems from internal curiosity - someone who protects capacity through physical stabilization - someone who expands through low-pressure social contact - someone who converts reflection into visible artifacts Avoid praise. Avoid productivity scores. Avoid inventing a flattering identity when the evidence is mixed. ## Danger Identities Name danger identities when evidence supports them, but do not shame the user. - Avoider: someone who protects short-term comfort by delaying, blurring, or escaping the next clear action. - Confronter: someone who seeks intensity, argument, or forceful collision when calibration, timing, or softer repair would work better. These are not labels for the person. They are trajectories being reinforced by repeated behaviors. Prefer `avoidance trajectory` or `confrontation trajectory` in the output. Use the capitalized `Avoider` or `Confronter` label only when the user already uses that ontology or repeated evidence across several contexts makes the shorthand useful. When a danger identity appears, give one concrete "next vote" that redirects it. Keep the tone direct: identify the pattern, name the cost, and prescribe the smallest corrective action. ## ADHD-Friendly Delivery - Put the strongest read in the first line. - Use short labels and concrete verbs. - Avoid long trait explanations. - Give one high-ROI next vote, not five options. - If the user is overwhelmed, skip the full analysis and give only: pattern, risk, next vote. ## Analysis Method For each strong pattern: 1. Identify the behavior evidence. 2. Name the identity being reinforced. 3. Explain the trajectory if repeated for 6 months to 5 years. 4. Mark whether this identity aligns with the user's stated future self. 5. Suggest one small shift that changes the next vote. If the user has named desired or danger identities, use those terms first. If not, infer identities from evidence. ## Output Return: ```text Read: one sentence naming the strongest identity signal. High-ROI next vote: the one action most likely to shift the trajectory. Identity votes - Identity: someone who ... Evidence strength: LOW | MEDIUM | HIGH Evidence: concrete behaviors from the input Trajectory: where this converges if repeated Alignment: aligned | mixed | misaligned Next vote: one practical behavior to reinforce or redirect Main tension: the strongest conflict between identities Risk to watch: Avoider | Confronter | other, if present ``` If the input covers more than one week, include trajectory movement: rising, falling, or stable. Never assign decimal weights unless the user already has a defined scoring model that gives those numbers meaning.