Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/discover
Trigger: vague/unfocused request or solution-without-problem. Also invoked via /discover command. Reframes goal before acting.
Passed 10 of 18 test cases with the skill, and 7 of 18 without it.
and 7 more in the full report
9 fixed5 passed either way6 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
The user has just confirmed the framed problem statement for the payment retry engine. What exact command reference must be provided to the user to begin drafting the buildable spec?
| Checked | Without skill | With skill |
|---|---|---|
| Instructs the user to run /spec to transition to specification drafting. | Missed | Passed |
The instructions your model reads when the skill loads.
You are starting the Discover phase. Your job is to help the user articulate what problem they are actually trying to solve, before jumping to solutions or specs.
CRITICAL: Run HARNESS_DIR=$(epic-harness path) first. NEVER use .harness/ in the project directory.
NO SPEC WITHOUT A PROBLEM STATEMENT. Building the wrong thing well is worse than building the right thing poorly.
HARNESS_DIR=$(epic-harness path)$HARNESS_DIR/specs/PROBLEM-*.mdmem_recall with a hint describing the current topic areadecision or pattern nodes related to this domainWhy: Past context prevents re-exploring ground already covered. The knowledge graph connects today's vague request to yesterday's decisions.
Read the user's request carefully. Repeat it back in your own words and ask:
Categorize the request:
| Category | Signal | Example |
|---|---|---|
| Solution without problem | User names a technology or approach | "Add Redis caching" |
| Feature without context | User describes output, not why | "Build a dashboard" |
| Systemic complaint | Broad negative without specifics | "Everything is slow" |
| Vague ambition | Goal with no boundaries | "Make it better" |
| Clear problem | Observable gap stated | "Login fails for 5% of users" |
Why: Categorization determines the probing technique. Misreading the category leads to wrong questions.
test cases passed, vs 7 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.