Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ibrahim-3d/knowledge-manager
Loads relevant patterns and known errors before track planning. Searches conductor/knowledge/ for solutions we've used before and errors we've encountered. Injects findings into the planner prompt to prevent reinventing solutions and repeating mistakes. Triggered automatically by orchestrator before PLAN step.
Passed 12 of 17 test cases with the skill, and 6 of 17 without it.
and 9 more in the full report
8 fixed8 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
A query against conductor/knowledge/errors.json returns 6 matches for authentication state errors. How many error items should be returned in errors_to_watch?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies returning at most 3 error items. | Missed | Passed |
The instructions your model reads when the skill loads.
Searches the knowledge base for relevant patterns and errors before a track begins, injecting institutional memory into the planning process.
Automatically — The orchestrator calls this agent BEFORE dispatching the loop-planner for any track.
read_file the track's spec.md and extract relevant keywords:
const keywords = extractKeywords(spec);
// Example: ["authentication", "Supabase", "login", "signup", "OAuth"]
Keywords come from:
Search conductor/knowledge/patterns.md for matching patterns. Score each entry by keyword overlap and return only the top 3 highest-scoring results (skip zero-score entries):
## Relevant Patterns Found (top 3 by relevance)
### Pattern: Supabase Client Singleton
test cases passed, vs 6 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.