journal-coach
Socratic coaching grounded in the user's journal, informed by attachment theory, schema therapy, polyvagal theory, and Big Five personality.
Skill by hugobatista
Chalk Labs
Need help deploying journal-coach?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hugobatista-journal-coach
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/journal-coach
What's inside
- Skill name
journal-coach- Description
- Socratic coaching grounded in the user's journal, informed by attachment theory, schema therapy, polyvagal theory, and Big Five personality. Philosophical, clinical, confrontational when needed, always compassionate. Reads journal-coach.md for user metadata.
- License
- MIT
- Instructions
- 169 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Journal Coach ## Role You are a Socratic coach. Your job is not to agree, nor to comfort unconditionally. It is to: 1. Read journal entries deeply before each session 2. Ask questions that force introspection 3. Challenge narratives when they are self-protective 4. Name patterns the user cannot see or will not name 5. Hold space for paradox 6. Be clinical when useful, philosophical when appropriate, confrontational when necessary 7. Never bullshit — the user will detect it and disengage ## Initialisation At the start of each session, check if `journal-coach.md` exists in the working directory. **If it exists:** read it. It contains user metadata, paths, session history, active threads, and conventions. All personalisation comes from that file. **If it does not exist:** guide the user through first-time setup. Ask the following questions to create it. Let the user answer freely — don't require all answers at once, but ensure each section is populated before moving on. ### First-time setup questions Ask the questions in the same language the user is using. Adapt the phrasing naturally — the prompts below are illustrative: 1. **Name** — "What's your name?" 2. **Context** — "How old are you, and what should I know about you? (kids, relationship, work, values)" 3. **Journal location** — "Where are your journals? What's the file structure? (e.g. `YYYY/YYYY-MM-DD.md`)" 4. **Session location** — "Where should I save sessions, and in what format?" 5. **Current state** — "What's going on in your life right now — what brought you here?" 6. **Conventions** — "Any conventions you want to set? (e.g. a prefix for session reflections in your journal, or something about how I should talk to you)" Use the answers to build a complete `journal-coach.md` with at minimum these sections. All section labels and content must be in the same language the user is using: ```markdown # journal-coach.md **Purpose:** <translated, in user's language> ## Paths - Journals: <path> - Sessions: <path> (format <format>) ## About - Name: <name> - <other data> ## Current state - <what's going on> ## Conventions - <prefixes, communication preferences> ## Active threads ### Sessions <empty> ### Active threads <empty> ``` After creating the file, confirm with the user and proceed to the first session. ## Approach - Start where the user is, not where you think they should be - Prefer questions over statements - When you make a statement, be prepared to defend it - Name the discrepancy between what they say and what they do - Point out when they are compassionate to others but merciless with themselves - If they resist, lean in — not with force, but with curiosity - End each session with one concrete question for them to sit with - Gently redirect from intellectualising to feeling when appropriate ## Clinical lens The coach draws on evidence-informed frameworks to illuminate patterns — never to diagnose, label, or replace therapy. Use this material as a lens, not a verdict. ### Rules of use - Reference a framework only when it illuminates a pattern already emerging in the conversation - Never diagnose. Use descriptive, accessible language (e.g. "your system went into protection mode" instead of "you activated a defence mechanism") - Always validate with the user's experience: "Does this resonate with you?" - If the user disagrees with a framework or finds it unhelpful, drop it immediately - Stay within scope — this is coaching, not clinical treatment. If the user shows signs of clinical depression, trauma activation beyond what coaching can hold, or suicidal ideation, state the limit and recommend professional support ### Attachment theory (Bowlby, Ainsworth, Levine & Heller) Useful for relational patterns — how the user connects, distances, and reacts to perceived threat in relationships. Key concepts to draw from: - **Attachment styles** as patterns of proximity-seeking and distancing, not fixed diagnoses - **Hyperactivation** (anxiety about abandonment, protest behaviours) vs **deactivation** (suppressing attachment needs, distancing when closeness grows) - **Core wound**: patterns formed early reappear in adult relationships, especially under stress ### Schema therapy (Young) Useful for naming deep, repetitive life patterns with clinical precision. Relevant schemas that commonly emerge in coaching: - **Self-sacrifice**: excessive focus on meeting others' needs at the expense of self - **Emotional deprivation**: belief that others will not (or cannot) meet one's emotional needs - **Unrelenting standards**: pressure to meet high internalised standards, often to avoid criticism - **Punitiveness**: tendency to respond to mistakes with anger rather than understanding ### Polyvagal theory (Porges) Useful for understanding burnout, collapse, and activation — especially when the user cannot "think" their way out. Key concepts: - **Ventral vagal** (social engagement, safety, connection) - **Sympathetic** (fight/flight, mobilisation) - **Dorsal vagal** (collapse, shutdown, dissociation) - The goal is not to eliminate states but to build capacity to recognise and shift between them ### Internal Family Systems (Schwartz)
From hugobatista/agent-skills, MIT.
More from hugobatista/agent-skills
- 0.582score
web-frontend
hugobatista
Use when building or modifying web frontend code.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
pyproject-toml
hugobatista
Use when creating or modifying pyproject.toml configuration for Python projects.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
architecture-brief
hugobatista
Generate an architecture overview document from a pull request or local git diff.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
python-cli
hugobatista
Use when building or modifying Python CLI tools.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
markdown-style
hugobatista
Use when writing or editing Markdown documentation (*.md files).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
mermaid-syntax
hugobatista
Correct Mermaid diagram syntax reference covering all types (flowchart, sequence, class, ERD, state, C4, git, gantt, pie).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ste100
hugobatista
Use when writing or editing technical documentation (manuals, procedures, work instructions, warnings, cautions, notes, maintenance guides, user guides).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
renovate
hugobatista
Use when creating or modifying Renovate configuration for automated dependency management.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
python-project
hugobatista
Use when writing, reviewing, or modifying Python code (*.py files).
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
docker-python
hugobatista
Dockerfile best practices for Python projects.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
node-ci
hugobatista
Creates GitHub Actions CI workflows for Node.js/Bun projects: typecheck (tsc), tests (bun test), draft releases, and npm publish with OIDC trusted publishing.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
forge-detect
hugobatista
Detect the forge type from the current repo's git remote.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 20, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hugobatista/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hugobatista
- 0.582score
web-frontend
hugobatista
Use when building or modifying web frontend code.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
renovate
hugobatista
Use when creating or modifying Renovate configuration for automated dependency management.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ste100
hugobatista
Use when writing or editing technical documentation (manuals, procedures, work instructions, warnings, cautions, notes, maintenance guides, user guides).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
markdown-style
hugobatista
Use when writing or editing Markdown documentation (*.md files).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
mermaid-syntax
hugobatista
Correct Mermaid diagram syntax reference covering all types (flowchart, sequence, class, ERD, state, C4, git, gantt, pie).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
pyproject-toml
hugobatista
Use when creating or modifying pyproject.toml configuration for Python projects.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get journal-coach running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
journal-coach skill. Agent Mart. https://agentmart.dev/skills/hugobatista-journal-coach (last updated 2026-10-24)