SKILLEMALL.ai
GitHub ↗ RU Sign in

BF harness-engineering

Design, build, diagnose, and evolve agent harnesses: instructions, tools, execution environments, durable state, context management, verification, recovery, and bounded autonomous loops. Use for unreliable coding agents, cross-session drift, premature completion, harness audits, or changes to the runtime around a model. Do not use for prompt rewriting alone, model training, general application architecture, or operating an already evaluated agent in production; route those concerns to their specialist skills.

magnus919/agent-skills Agent Skills author: magnus919 MIT 49 files · 4 scripts body ≈ 2 850 tokens Open the sourcegithub.com↗ analyzed 27 h ago

Design, build, diagnose, and evolve agent harnesses: instructions, tools, execution environments, durable state, context management, verification, recovery…

As a process F 47/100 · Will not run — References files that are not bundled: ../systematic-debugging/SKILL.md, ../langgraph/SKILL.md, ../pydanticai/SKILL.md

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
B
91/100
safety, quality, tests
Safety 60%
100
Quality 40%
78
Run on models
none yet
Process rating
F
47/100
Will not run
References files that are not bundled: ../systematic-debugging/SKILL.md, ../langgraph/SKILL.md, ../pydanticai/SKILL.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
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
  • 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: 41. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../systematic-debugging/SKILL.md
  • warning missing-ref reference to a missing file: ../langgraph/SKILL.md
  • warning missing-ref reference to a missing file: ../pydanticai/SKILL.md
  • warning missing-ref reference to a missing file: ../autogen/SKILL.md
  • warning missing-ref reference to a missing file: ../agent-evals-and-observability/SKILL.md
  • warning missing-ref reference to a missing file: ../agent-production-operations/SKILL.md
  • warning missing-ref reference to a missing file: ../agent-skills/SKILL.md
  • warning missing-ref reference to a missing file: ../secure-software-engineering/SKILL.md
  • warning missing-ref reference to a missing file: ../ai-governance/SKILL.md

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: ../systematic-debugging/SKILL.md, ../langgraph/SKILL.md, ../pydanticai/SKILL.md
  • 0Tools and files. 9 referenced file(s) missing: ../systematic-debugging/SKILL.md, ../langgraph/SKILL.md, ../pydanticai/SKILL.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 12 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2850 tokens
  • low No test case covers injection arriving through data

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
  • +3Output format is not stated: the model decides each time
  • -32 of 4 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 514: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 12 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (16 of 16)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.