Establishing Project Context
Maintains a canonical CONTEXT.md domain glossary so humans and agents share terms
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 9dc570e
⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 21, 2026; it's queued for a re-test.
Fetched SKILL.md and its referenced CONTEXT-FORMAT.md via raw GitHub (both HTTP 200); frontmatter parses with name+description, paths use <project-root> placeholders, and the body contains explicit anti-prompt-injection guidance rather than any security smell. For output I ran one task (splitting an ambiguous "account" term into Customer/User) twice: a baseline CONTEXT.md and a skill-following one. The baseline carried implementation paths, a timestamp, and a TODO/notes log and kept "Account" as a live entry; following the skill stripped all three (both docs explicitly forbid them), applied the canonical _Avoid_ alias form and a Resolved Ambiguities section, and correctly classified the change as evidence A + fact so it wrote directly without asking. Trigger judgments (3 should-fire, 2 should-not) all resolved correctly.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 5/5
What Establishing Project Context does
Maintains project domain terminology in a canonical CONTEXT.md glossary so humans and coding agents use the same terms, classifying each change by evidence grade and by whether it is a settled fact or an open decision before writing. Triggers when the user asks to establish shared project language, or when work surfaces a resolved, vague, conflicting, renamed, or deprecated domain term needing active semantic modeling. Restricts the file to terms and relationships, excluding code paths, timestamps, and logs.
How to install Establishing Project Context
git clone --depth 1 https://github.com/GanyuanRan/Aegis.git /tmp/establishing-project-context-src
mkdir -p ~/.claude/skills
cp -R /tmp/establishing-project-context-src/skills/establishing-project-context ~/.claude/skills/establishing-project-context
# Self-contained: SKILL.md + CONTEXT-FORMAT.md, no external deps, tools, or API keys.
# Part of the Aegis "method pack"; works standalone as a single skill.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Establishing Project Context
-
/establishing-project-contextMaintains a canonical CONTEXT.md domain glossary so humans and agents share terms
It also activates on plain-language prompts like these:
-
Establish shared language for this new project -
Create a glossary of domain terms for this codebase -
Define our project's key domain terminology together
Frequently asked questions
- Is the Establishing Project Context skill free?
- Yes. The skill itself is free from GanyuanRan/Aegis. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Establishing Project Context work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md and its referenced CONTEXT-FORMAT.md via raw GitHub (both HTTP 200); frontmatter parses with name+description, paths use <project-root> placeholders, and the body contains explicit anti-prompt-injection guidance rather than any security smell. For output I ran one task (splitting an ambiguous "account" term into Customer/User) twice: a baseline CONTEXT.md and a skill-following one. The baseline carried implementation paths, a timestamp, and a TODO/notes log and kept "Account" as a live entry; following the skill stripped all three (both docs explicitly forbid them), applied the canonical _Avoid_ alias form and a Resolved Ambiguities section, and correctly classified the change as evidence A + fact so it wrote directly without asking. Trigger judgments (3 should-fire, 2 should-not) all resolved correctly.
- What is the Establishing Project Context SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
- How do I install Establishing Project Context?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Establishing Project Context with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.