create-context
Build or refine a CONTEXT.md glossary through a question/answer session.
Skill by will-wright-eng
Chalk Labs
Need help deploying create-context?
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/will-wright-eng-create-context
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
Use cases: writing
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/create-context
What's inside
- Skill name
create-context- Description
- Build or refine a CONTEXT.md glossary through a question/answer session. Explores the codebase for candidate domain terms, then confirms each term, relationship, and ambiguity with the user one at a time — writing to CONTEXT.md only on confirmation. Use when a project's ubiquitous language needs capturing, or an existing CONTEXT.md needs auditing.
- License
- unknown
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (2)
- CONTEXT-FORMAT.md
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from will-wright-eng/skills
- 0.559score
blog-antipatterns
will-wright-eng
Review a markdown software blog post against Michael Lynch's "Anti-Patterns in Software Blogging" — the meandering intro and preamble, assuming the reader…
SkillAFreshness: AClaude Code +9 - 0.519score
prune-comments
will-wright-eng
Aggressively remove redundant comments from code files — deletes narration that restates the code, "pseudo-why" comments whose reason is already visible in…
SkillBFreshness: BClaude Code +9 - 0.469score
autoresearch-program
will-wright-eng
Generate `program.md` at the repo root from the autoresearch program template, with mutable/immutable scope and verifier commands baked in via light templating.
SkillCFreshness: CClaude Code +9 - 0.469score
design-readiness
will-wright-eng
Audit a design/implementation/proposal markdown document for consistency with the codebase and its documented context (ADRs in docs/adr/, CONTEXT.md) and…
SkillCFreshness: CClaude Code +9 - 0.469score
distill-adrs
will-wright-eng
Distill existing implementation markdown documents (plans, design docs, RFCs) into Architecture Decision Records (ADRs).
SkillCFreshness: CClaude Code +9 - 0.469score
autoresearch-verify
will-wright-eng
Build a repo-specific verifier script for an autoresearch loop.
SkillCFreshness: CClaude Code +9 - 0.469score
autoresearch-method
will-wright-eng
Explain the autoresearch methodology — a verifiable autonomous experiment loop — and evaluate whether the current repo is a good fit before running the…
SkillCFreshness: CClaude Code +9 - 0.469score
anneal
will-wright-eng
Decompose a god module into stable and volatile pieces whose boundaries match how the code actually changes.
SkillCFreshness: CClaude Code +9 - 0.445score
caveman
will-wright-eng
Ultra-compressed communication mode.
SkillCFreshness: CClaude Code +9 - 0.445score
improve-codebase-architecture
will-wright-eng
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 25, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/will-wright-eng/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from will-wright-eng
- 0.559score
blog-antipatterns
will-wright-eng
Review a markdown software blog post against Michael Lynch's "Anti-Patterns in Software Blogging" — the meandering intro and preamble, assuming the reader…
SkillAFreshness: AClaude Code +9 - 0.519score
prune-comments
will-wright-eng
Aggressively remove redundant comments from code files — deletes narration that restates the code, "pseudo-why" comments whose reason is already visible in…
SkillBFreshness: BClaude Code +9 - 0.469score
autoresearch-program
will-wright-eng
Generate `program.md` at the repo root from the autoresearch program template, with mutable/immutable scope and verifier commands baked in via light templating.
SkillCFreshness: CClaude Code +9 - 0.469score
design-readiness
will-wright-eng
Audit a design/implementation/proposal markdown document for consistency with the codebase and its documented context (ADRs in docs/adr/, CONTEXT.md) and…
SkillCFreshness: CClaude Code +9 - 0.469score
distill-adrs
will-wright-eng
Distill existing implementation markdown documents (plans, design docs, RFCs) into Architecture Decision Records (ADRs).
SkillCFreshness: CClaude Code +9 - 0.469score
autoresearch-verify
will-wright-eng
Build a repo-specific verifier script for an autoresearch loop.
SkillCFreshness: CClaude 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 create-context 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
create-context skill. Agent Mart. https://agentmart.dev/skills/will-wright-eng-create-context (last updated 2026-10-24)