New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pre Session Portrait

by glebis in glebis/claude-skills

Build a compressed, visualizable "portrait" of a consulting/coaching client before a session, so the paid hour is spent solving, not scoping.

MITAuto-check passedProduct & Project Management

Install Pre Session Portrait

skills CLI
$ npx skills add glebis/claude-skills --skill pre-session-portrait -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install glebis/claude-skills pre-session-portrait --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pre-session-portrait .claude/skills/pre-session-portrait && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pre-session-portrait
GitHub stars
390
Token cost
~1.5k tokens
SKILL.md length
708 words
Files
5 (incl. assets)
Skills in repo
92
Repo updated
First seen
Licence
MIT

At a glance

Build a compressed, visualizable "portrait" of a consulting/coaching client before a session, so the paid hour is spent solving, not scoping.

  • Works in 5 steps: Gather context. Client name, consultant… → Fill the template. Copy… → Pick a delivery (ask the user) → …
  • Preparing for an upcoming client call
  • SKILL.md covers The seven lenses, Output schema, How it visualizes and Workflow, plus 3 more sections
  • Calls gh and codex

What it does

Pre Session Portrait is an agent skill from glebis/claude-skills. Build a compressed, visualizable "portrait" of a consulting/coaching client before a session, so the paid hour is spent solving, not scoping. Runs a 7-lens JTBD-inspired interview (where / how / what / problem / ideal / tension / jobs-to-be-done) that takes rich open answers in and compresses them to an 11-field YAML portrait out. Delivers three ways: raw paste-into-a-clean-chat prompt, a secret GitHub gist link, or a Codex CLI one-liner. Use when preparing for an upcoming client call, when the user says "prep an…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including assets (for example `assets/intake-form.md` and `assets/interview-prompt.md`).

It sits in Product & Project Management, covering User stories and Interview preparation. It works with GitHub. The repository describes itself as: Collection of Claude Code skills for enhanced AI workflows. The licence is MIT.

When your agent uses it

  • Preparing for an upcoming client call
  • The user says prep an intake
  • Portrait interview
  • Questions before our session

Example prompts

  • “portrait”
  • “prep an intake”
  • “portrait interview”
  • “/pre-session-portrait”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Gather context. Client name, consultant name, session date, and (if known) the topic. Pull prior history from vault/email/Fathom if…
  2. Fill the template. Copy assets/interview-prompt.md and substitute {{CONSULTANT}} (and topic if narrowing lens 4). Leave the seven lenses…
  3. Pick a delivery (ask the user)
  4. Optional preview. Before sending, generate a synthetic filled-in version (answers simulated from known context) so the consultant judges…
  5. After the session. Fold the returned portrait: YAML into the client's People/Session note; diff against any prior portrait to show movement.

What it can do on your machine

Read from SKILL.md and the folder at commit 3b88261. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • codex

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pre Session Portrait loads about 1.5k tokens when it runs. Until then it costs about 173 tokens; SKILL.md has 708 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~173
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from glebis/claude-skills at commit 3b88261, republished under its MIT licence (© glebis). 708 words, ~1,539 tokens.

Download SKILL.mdSave it as .claude/skills/pre-session-portrait/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
pre-session-portrait
description
Build a compressed, visualizable "portrait" of a consulting/coaching client before a session, so the paid hour is spent solving, not scoping. Runs a 7-lens JTBD-inspired interview (where / how / what / problem / ideal / tension / jobs-to-be-done) that takes rich open answers in and compresses them to an 11-field YAML portrait out. Delivers three ways: raw paste-into-a-clean-chat prompt, a secret GitHub gist link, or a Codex CLI one-liner. Use when preparing for an upcoming client call, when the user says "prep an intake", "portrait interview", "questions before our session", "send a client a pre-session questionnaire", or wants a reusable client-intake instrument.

Pre-Session Portrait

Turn "help me with X" into a decision-grade brief before the session starts. The instrument asks the client open, voice-note-friendly questions across seven fixed lenses; the consultant (or an LLM) compresses each answer to one line, yielding a portrait that is iterable, compressible, and easy to visualize.

Design principle: rich in, compressed out. The client talks freely; compression happens after, not in their head.

The seven lenses

#LensElicitsCompresses to
0ANCHORthe topic — what the call is for (referent for every later "this")the topic in one line
1WHEREwhat's been tried, where it stallscurrent state in one line
2HOWcognitive style — fast/slow, visual/verbal, systems/storieshow they think
3WHATlive preoccupations, open loopscurrent focus
4PROBLEMthe problem under the problemthe core job
5IDEALconcrete "solved" state (day/feeling, not tool)desired outcome
6TENSIONwhat holds them back / worries themdominant anxiety
7JTBDPush · Pull · Habit · Anxiety · Triggerswitching forces

Output schema

yaml
portrait:
  where: ""
  how: ""
  what: ""
  problem: ""
  ideal: ""
  tension: ""
  jtbd:
    push: ""
    pull: ""
    habit: ""
    anxiety: ""
    trigger: ""

How it visualizes

  • 7-spoke radial / hexad map — one label per lens, the capture line as the value.
  • JTBD 2×2 — Push+Pull (energy toward change) vs Habit+Anxiety (energy against). The gap = leverage.
  • Iterable — re-run any lens next session; watch the capture line drift over time.

Workflow

  1. Gather context. Client name, consultant name, session date, and (if known) the topic. Pull prior history from vault/email/Fathom if available so the consultant-only prep notes are grounded.
  2. Fill the template. Copy assets/interview-prompt.md and substitute {{CONSULTANT}} (and topic if narrowing lens 4). Leave the seven lenses intact.
  3. Pick a delivery (ask the user):
    • Raw text — paste the substituted prompt into a message; client runs it in any clean Claude/ChatGPT.
    • Secret gist — gh gist create --desc "Pre-session portrait interview (for <name>)" interview-prompt.md. Share the gist link. Use the unpinned raw URL (/raw/<filename>) so edits propagate.
    • Codex one-liner — see assets/codex-bootstrap.txt; fetches the raw gist URL and runs the interview interactively.
  4. Optional preview. Before sending, generate a synthetic filled-in version (answers simulated from known context) so the consultant judges the deliverable's shape. Mark it clearly as synthetic.
  5. After the session. Fold the returned portrait: YAML into the client's People/Session note; diff against any prior portrait to show movement.

Delivery notes

  • Secret gist ≠ auth-private: anyone with the link can read it. Fine for a benign intake; don't put client PII in the gist itself.
  • Codex: run interactive codex (not codex exec), and include the "do not write code / touch files — this is a conversation" guard so it stays in interview mode.
  • Framing line to prepend when sending: "Paste this into a fresh Claude or ChatGPT chat — it'll ask you 7 quick questions and give you a block to send back to me before our call."
Show full SKILL.md (255 more words)Show less

Call cockpit (interactive HTML)

Once a portrait is back, generate an interactive prep cockpit the consultant runs live during the session. Start from assets/cockpit-template.html — a self-contained, theme-aware single file (no external deps).

Tabs: Setup (structured stack/facts fields + a paste box for the portrait: block) · Framework (six-station pipeline with per-station AUTO/ASSIST/HUMAN + quality-gate inputs) · Questions (per-section bank, each with an autosaved answer field; add-your-own) · Decisions & Actions (dynamic add/delete rows; actions carry an owner) + a build/demo box and show-don't-tell cues · Agenda (accordion of time-blocks that expand into checkable sub-steps + per-block notes; a live timer auto-opens the current block and fills a progress bar) · Notes.

Key properties:

  • Autosaved to localStorage, namespaced by the Client-name field — so multiple cockpit files opened from the same folder (same file:// origin) never clobber each other's data.
  • Filled instances: copy the template and inject a const SEED = {fields, decisions, actions} object just before // init; a one-time guard (prep::<ns>::__seeded) writes the seed into the client's namespace on first load, then the consultant's edits persist. Use this to pre-populate a cockpit from a known portrait + prior-session facts.

Also generate a client-facing recap after the session (same visual language): what we covered, current→target pipeline, decisions, what we built live, their next steps (autosaved checkboxes + fields), tech notes. Deliver as a file or publish as an Artifact URL to share a link.

Assets

  • assets/interview-prompt.md — the self-contained interviewer prompt (template).
  • assets/intake-form.md — human-readable version with per-lens capture: fields, if the consultant prefers to interview live.
  • assets/codex-bootstrap.txt — the Codex CLI one-liner template.
  • assets/cockpit-template.html — the interactive prep cockpit (blank, reusable; autosaved + client-namespaced).

© glebis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (assets) in pre-session-portrait of glebis/claude-skills.

  • SKILL.md
  • assets/cockpit-template.html
  • assets/codex-bootstrap.txt
  • assets/intake-form.md
  • assets/interview-prompt.md

Open the folder on GitHubat commit 3b88261

Compare with similar skills

Pre Session Portrait next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pre Session Portrait compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pre Session Portrait this skillglebis/claude-skills390—~1.5kAutomated safety check: PassMIT
Create Issuetradingstrategy-ai/frontend150—~607Automated safety check: PassNone
Specgetsentry/sentry-react-native1.8k—~1.1kAutomated safety check: PassMIT
Abo Issue Watcherjeeftor/audiobook-organizer190—~417Automated safety check: PassMIT
SpecifyRafaelGB/Obsidian-ZettelFlow174—~759Automated safety check: PassMIT
Execute Issuelbedner/aegis-stack143—~1.1kAutomated safety check: PassMIT

Similar skills

  • Create Issue

    tradingstrategy-ai/frontend

    Creates a new GitHub issue with structured user story format, acceptance criteria, and project integration.

    150 GitHub stars~607 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • Spec

    getsentry/sentry-react-native

    Official

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building.

    1.8k GitHub stars~1.1k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Abo Issue Watcher

    jeeftor/audiobook-organizer

    Inspect Audiobook Organizer GitHub issues, comments, acceptance criteria, linked PRs, and next steps.

    190 GitHub stars~417 tokensUpdated 28 days ago
    Product & Project ManagementAuto-check passed

  • Specify

    RafaelGB/Obsidian-ZettelFlow

    Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope).

    174 GitHub stars~759 tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Execute Issue

    lbedner/aegis-stack

    A skill your agent uses when handed a GitHub issue (number or URL) to execute end to end.

    143 GitHub stars~1.1k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Zoonk Issue Planning

    zoonk/zoonk

    Break work into GitHub issues, epics, or dependencies when the user explicitly requests an issue breakdown.

    157 GitHub stars~707 tokensUpdated today
    Product & Project ManagementAuto-check passed

More from glebis/claude-skills

All 92 skills in this repo

  • PII Annotation and Agreement Scorer

    glebis/claude-skills

    Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.

    390 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Non-Destructive Chrome Automation

    glebis/claude-skills

    Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.

    390 GitHub stars~973 tokensUpdated today
    Auto-check passed

  • Deep Research

    glebis/claude-skills

    This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API.

    390 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes

  • Elimination Research

    glebis/claude-skills

    This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…

    390 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Narrated HTML Presentations

    glebis/claude-skills

    Generates a self-contained HTML presentation with article and slides modes, ElevenLabs voiceover narration and optional GPT Image 2 illustrations.

    390 GitHub stars~2.3k tokensUpdated today
    Auto-check: notes

  • Synthetic Coaching Session Generator

    glebis/claude-skills

    Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

    390 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Pre Session Portrait

What does Pre Session Portrait do?

Build a compressed, visualizable "portrait" of a consulting/coaching client before a session, so the paid hour is spent solving, not scoping. Pre Session Portrait is an agent skill from glebis/claude-skills. Build a compressed, visualizable "portrait" of a consulting/coaching client before a session, so the paid hour is spent solving, not scoping.

When should I use Pre Session Portrait?

Pre Session Portrait fits situations like: preparing for an upcoming client call; the user says prep an intake; portrait interview; questions before our session.

How do I install Pre Session Portrait in Claude Code?

Run `npx skills add glebis/claude-skills --skill pre-session-portrait -a claude-code`. Or copy the skill folder (pre-session-portrait in glebis/claude-skills) into .claude/skills/pre-session-portrait in your project. Claude Code loads it when a task matches its description.

How do I install Pre Session Portrait in Codex?

Run `npx skills add glebis/claude-skills --skill pre-session-portrait -a codex`. Or copy the skill folder (pre-session-portrait in glebis/claude-skills) into .agents/skills/pre-session-portrait in your project. Codex loads it when a task matches its description.

Can I use Pre Session Portrait in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add glebis/claude-skills --skill pre-session-portrait -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pre-session-portrait, .gemini/skills/pre-session-portrait, .github/skills/pre-session-portrait and .opencode/skills/pre-session-portrait in your project.

What does Pre Session Portrait need to run?

Going by SKILL.md and its folder, Pre Session Portrait needs the command-line tools its instructions call (gh and codex).

Does Pre Session Portrait access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Pre Session Portrait safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pre Session Portrait use?

Pre Session Portrait is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pre Session Portrait use?

About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pre Session Portrait?

Skills that share tags, products or a category with Pre Session Portrait: Create Issue (tradingstrategy-ai/frontend, 150 stars), Spec (getsentry/sentry-react-native, 1.8k stars), Abo Issue Watcher (jeeftor/audiobook-organizer, 190 stars) and Specify (RafaelGB/Obsidian-ZettelFlow, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pre Session Portrait?

glebis (a GitHub user) maintains it in glebis/claude-skills, which has 390 GitHub stars. The repository holds 92 skills in this directory. The repository was last updated on October 8, 2026.

Source: glebis/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.