Use when implementing or changing observable behavior test-first, fixing a bug with regression evidence, choosing a test seam for a planned slice, or when a test is hard to write, passes immediately, conflicts with source truth, or starts driving architecture.
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
# Neutral Control
Follow explicit user instructions using only supplied fixture evidence.
The line at the top of this page pins the label git:20260908.9097a1e, 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_k6k6v4ho2v4sisr3
GET https://markdownregistry.com/api/v1/resolve?ref=hassan-mohiddin/freeflow/tdd
GET https://markdownregistry.com/api/v1/blob/7ab4795b7c19b044426b20fb8a0a1b00950a42b918fe260a16da038b0bef3a0d
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.
hassan-mohiddin/freeflow · .deprecated/legacy-context/capabilities/context-virtualization/SKILL.md · Use after broad or noisy tool evidence has been safely narrowed or exhausted, or when an activity boundary leaves raw…
hassan-mohiddin/freeflow · .deprecated/legacy-context/capabilities/conversation-history/SKILL.md · Use when the next decision requires exact prior conversation wording, rationale, chronology, or provenance that is…
hassan-mohiddin/freeflow · .deprecated/modes/qualification/subjects/neutral/mode-contract/SKILL.md · Use when a user asks to set, change, infer, or discuss conversation/workflow/strict-workflow mode, or when task risk…
hassan-mohiddin/freeflow · .deprecated/modes/skills/mode-contract/SKILL.md · Use when choosing, changing, or explaining how Freeflow mode applies to current work.
hassan-mohiddin/freeflow · .deprecated/output-router/skill-eval/qualification/subjects/neutral/output-router/SKILL.md · Use after the Workflow, Decision Gate, or Discuss route is clear when choosing between native tools and Freeflow routed…
hassan-mohiddin/freeflow · .deprecated/skill-evals-v1/fixtures/tiny-eval-method-app/skills/review-pr/SKILL.md · Use when reviewing a pull request or local diff before merge.
hassan-mohiddin/freeflow · .deprecated/skill-evals-v1/fixtures/tiny-eval-method-app/skills/triage-question/SKILL.md · Use when the user asks whether an issue, task, or product decision already exists.
cursor/plugins · pstack/skills/tdd/SKILL.md · Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious…
cursor/plugins · harness/pstack/claude-code/skills/tdd/SKILL.md · Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious…
michael-denyer/pstack-claude · plugins/pstack/skills/tdd/SKILL.md · Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious…
rohitg00/pro-workflow · skills/tdd/SKILL.md · Drive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when…
backnotprop/pstack · skills/tdd/SKILL.md · Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious…
