SKILLEMALL.ai
GitHub ↗ RU Sign in

BF research-harness

Cognitive discipline for AI-native scientific experimentation. Trigger when setting up controlled experiments with LLM agents, designing reproducible evaluation pipelines, or structuring research workspaces for long-running agent collaboration. Provides guardrails, not recipes — teaches agents how to reason about experiments, not which commands to run.

ClawHub Agent Skills author: Julian Zhelun Sun v1.3.2 MIT-0 13 files body ≈ 3 160 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 42/100 · Will not run — References files that are not bundled: scripts/validate_<module>.py, scripts/validate_repo_state.py

ProcedureAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
70
Run on models
none yet
Process rating
F
42/100
Will not run
References files that are not bundled: scripts/validate_<module>.py, scripts/validate_repo_state.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/validate_<module>.py
  • warning missing-ref reference to a missing file: scripts/validate_repo_state.py
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 42/100

Will not run. References files that are not bundled: scripts/validate_<module>.py, scripts/validate_repo_state.py
  • 0Tools and files. 2 referenced file(s) missing: scripts/validate_<module>.py, scripts/validate_repo_state.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 7 mutating operations with no state check
  • 40Consistency. Frontmatter name (research-harness) differs from the folder (ai-research-harness)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 58 steps
  • 100When it triggers. States when to use and when not to
  • 100Execution cost. Instruction body is 3160 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +3Description length 354: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 58 items
  • +4Reference files are cited in the instructions (6 of 6)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.

External checks

ClawHub: clean
This is a documentation-only research workflow skill that gives agents guardrails for reproducible experiments and does not include executable code or hidden data access.
LLM: benign (high) · VirusTotal: · 2 Jun 2026