Load when creating a new Agent Skill from a workflow, project rule, repeated task, SOP, execution trace, success/failure pattern, human office process, Codex/Hermes harness task, or project-specific knowledge that should become a reusable SKILL.md package.
SkillScore91Maintained
Automatic
◆AI Engineer pack
Last verified 8/3/2026
What it changes
Passed 19 of 21 test cases with the skill, and 12 of 21 without it.
Without skill59%
With skill91%
Checks it passed that the model alone missed
Includes an initial repair action.
Classifies transient failures into failure_recovered.
Includes a fallback or handoff action when repair fails.
and 11 more in the full report
7 fixed13 passed either way2 still failing0 broke
Pass-rate lift
+32 pp
Tokens
+68%
Agent turns
0%
Response time
-18%
Model gemini-3.6-flashMeasured 8/3/2026v120 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
We are setting up the evaluation harness for the initial gate check of a newly generated skill package for automated PR review. List the three evaluation arms required for the comparison harness.
What was checked, without and with the skill
Checked
Without skill
With skill
Names the three first-gate evaluation arms as no_skill, candidate_skill, and human_gold.
Missed
Passed
Describes human_gold as the benchmark anchoring quality against expert samples.
Missed
Passed
case-16 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md187 lines3 files
SKILL+ Create
Use this skill to turn a repeatable workflow or project practice into a new Agent Skill that another agent can load, understand, execute, and evaluate.
This skill creates a candidate skill package. It does not claim the skill is production-ready until evaluation evidence exists.
Inputs
Collect or infer:
Workflow goal and target user-agent.
Trigger phrases or task situations that should load the skill.
Existing artifacts: transcripts, task logs, PRs, docs, spreadsheets, screenshots, commands, prompts, or human SOPs.
Success examples, failure examples, and human corrections.
Target harnesses such as Codex, Hermes, Claude Code, OpenCode, or a custom runner.
If evidence is thin, create an experimental skill and mark missing evidence in the creation report.
Workflow
1. Decide Whether A Skill Should Exist
Create a skill only when at least one condition is true:
The workflow repeats across tasks or projects.
The agent repeatedly needs the same background, tool order, checks, or failure recovery.
Human corrections reveal a stable failure mechanism.
The task has an output contract or verification method.
The skill would reduce context explanation for future agents.
Do not create a skill for one-off facts, unverifiable preferences, private details that cannot be sanitized, or tasks that require unstructured real-time human judgment.