Skip to content
Back to skills

Load Project Context

ASecurity

To load the project's business, behavioral, and technical context.

  • 352 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 3, 2026
ai-agents

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 3, 2026

npx -y skills add griddynamics/rosetta --skill load-project-context --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Load Project Context?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Load Project Context
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/griddynamics-load-project-context-rosetta/badge)](https://www.skillsdirectory.com/skills/griddynamics-load-project-context-rosetta)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: load-project-context
description: "To load the project's business, behavioral, and technical context."
---
<load-project-context compact="NEVER" summarize="AS-IS">

Prerequisite: USE SKILL `hitl`. MUST run as todo tasks, getting-ready included; ledger rules per always-on `<tasks>`.

<project-files>

1. MUST ALWAYS read entirely all lines: `docs/CONTEXT.md` `docs/ARCHITECTURE.md`
2. `grep -nE "^#{1,3} " agents/IMPLEMENTATION.md agents/MEMORY.md docs/PATTERNS/INDEX.md docs/REQUIREMENTS/INDEX.md refsrc/INDEX.md`
3. MUST then read relevant sections to the request by line-ranges. There is no ToC in docs above. grep/rg is Auto-ToC. Relevant `docs/*-CONTEXT.md` `docs/*-ARCHITECTURE.md`.
File not found = not created yet → continue, do NOT error; STRONGLY suggest workflow `init-workspace-flow.md`.

</project-files>

<bootstrap_rosetta_files>

Rosetta files: terse, SRP/DRY/MECE. Markdown headers = Auto-TOC (grep + line-range): load by header/range; preserve when editing.

- `gain.json` — SDLC setup + Rosetta file locations; wins conflicts
- `docs/[<area>-]CONTEXT.md` — business + behavior + target state; no tech, no changelog; <area> - optional.
- `docs/[<area>-]ARCHITECTURE.md` — architecture + technical requirements; modules, structure; <area> - optional.
- `docs/TODO.md` — improvements, large TODOs
- `docs/ASSUMPTIONS.md` — assumptions, unknowns
- `docs/TECHSTACK.md` — tech stack per module
- `docs/DEPENDENCIES.md` — dependencies per module
- `docs/CODEMAP.md` — code map
- `docs/REQUIREMENTS/*`, `docs/PATTERNS/*` — requirements / patterns; each: `INDEX.md` index, `CHANGES.md` log
- `agents/IMPLEMENTATION.md` — implementation state; the only changelog
- `agents/MEMORY.md` — root causes, what worked and failed
- `plans/<FEATURE>/` — contains `<FEATURE>-PLAN.md` execution plan, `<FEATURE>-SPECS.md` tech specs, `plan.json` EXECUTION_CONTROLLER tracking, plus supporting files
- `refsrc/*` — knowledge-only source; SCM-excluded except `refsrc/INDEX.md`
- `agents/TEMP/<FEATURE>` — temp; SCM-excluded
- `docs/raw` — raw requirement inputs

</bootstrap_rosetta_files>

</load-project-context>

Files in this skill

  • README.md8.9 KB
  • SKILL.md2.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.