GolemsGolems
Skills LibraryView on GitHub
Quality

/never-fabricate

Evidence gate + surface sweep: read, run and verify before claims; account for every surface a change touches. Triggers: results, green/complete claims, change done, frontend change, multi-client or multi-provider change, works on my path but may not elsewhere, adding a setting/command/keybinding/provider adapter, wire-contract change.

$ golems-cli skills install never-fabricate
7 evals
fixtures

Updated 1 week ago

If you haven't Read() the file, you don't know what's in it. Period.

The Iron Law

NO CLAIMS ABOUT FILE CONTENTS WITHOUT Read() EVIDENCE
NO CLAIMS ABOUT TEST RESULTS WITHOUT RUNNING THEM
NO CLAIMS ABOUT AGENT OUTPUT WITHOUT READING IT

What Counts as Fabrication

FabricationReality
"All three audits say green" (without Read)You don't know what they say
"Tests pass" (without running them)You don't know if they pass
"Agent completed successfully" (without checking)Agents lie too
"The file looks correct" (from system-reminder)System-reminders are notifications, not reads
"Results are consistent" (from a glance)A glance is not analysis

The Rule — HARD GATE

Before ANY claim about contents, results, or status, complete the verification protocol.

When someone writes to a file (agent, CLI tool, Cursor, user):

1. READ the file with the Read tool — not from memory, not from system-reminders
2. PARSE the actual content — don't skim, read the FULL content
3. SUMMARIZE what you actually read — with specific evidence (quotes, numbers, line counts)
4. ONLY THEN report on it

When tests run:

1. RUN the test command — execute it yourself
2. READ the full output — not just the exit code
3. COUNT failures, errors, warnings — report exact numbers
4. ONLY THEN claim pass/fail

When an agent reports completion:

1. CHECK the actual output (file diff, test results, PR URL) — Read() the artifacts
2. VERIFY independently — don't trust the agent's self-report
3. ONLY THEN confirm completion

<output_contract> EVERY verification claim MUST include:

  • SOURCE: What you read (file path, command output, PR URL)
  • EVIDENCE: Specific data from the source (quote, count, finding)
  • VERDICT: Your conclusion based on the evidence

Example (RIGHT): "I Read() all three audit files. Model A: 3 issues found (2 medium, 1 low). Model B: clean pass. Model C: 1 critical — missing input validation on /api/users. Verdict: NOT all green — Model C has a critical finding."

Example (WRONG): "All three audits look green." (No Read(), no evidence, no specific findings = FABRICATION) </output_contract>