Placeholder skill so the bundle passes plugin-format validation.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Red
Placeholder skill body; the bundle's MCP declaration is the broken string-pointer form.
No `allowed-tools` is declared, so the loader's `None` default stands.
The line at the top of this page pins the label git:20260829.462bd66, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_es7hjtefmad64x5b
GET https://markdownregistry.com/api/v1/resolve?ref=curie-eng/curie/red
GET https://markdownregistry.com/api/v1/blob/d228c2f7de1f5537ce0e29a99787b75a30c7c37ef6c2cf21b22a3d153aff3cda
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
curie-eng/curie · .claude/skills/implement/SKILL.md · Implement a ticket or feature with proportional planning, test first behavior changes, independent review when…
curie-eng/curie · .claude/skills/update-architecture-atlas/SKILL.md · Create or refresh a versioned Curie architecture-atlas JSON snapshot from a git diff, including current and vision…
glebis/claude-skills · confide/skills/red/SKILL.md · Residual re-identification RISK CHECK on text you have ALREADY redacted (defensive, dual-use). Use when the user asks…
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_15-10-20_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_opus-4-7-portkey/.opencode/skills/red/SKILL.md · TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_16-33-19_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_minimax-m2-7/.opencode/skills/red/SKILL.md · TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_15-21-57_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_opus-4-7-portkey/.opencode/skills/red/SKILL.md · TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_16-38-39_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_gemini-3-5-flash/.opencode/skills/red/SKILL.md · TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_18-27-53_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_glm-5-1-2/.opencode/skills/red/SKILL.md · TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_08-16-22_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_opus-4-7-portkey/.opencode/skills/red/SKILL.md · TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_10-00-29_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_minimax-m2-7/.opencode/skills/red/SKILL.md · TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions
