Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →notque/workflow-help
Interactive guide to workflow system: agents, skills, routing, execution patterns.
Passed 3 of 8 test cases with the skill, and 2 of 8 without it.
and 5 more in the full report
8 fixed0 passed either way12 still failing5 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.
Before answering any questions regarding repository conventions or workflow commands, what repository file must be consulted first?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies CLAUDE.md as the required repository file to consult before responding | Missed | Passed |
The instructions your model reads when the skill loads.
This skill operates as an educational guide for repository workflows. It answers questions about how the agent/skill/routing architecture works, what tools and components are available, and when to use each workflow phase (brainstorm, plan, execute). The skill prioritizes accuracy over speed by reading actual SKILL.md and agent files rather than relying on memory.
Goal: Determine exactly what the user wants to know about.
Parse the user's topic and $ARGUMENTS. Common categories:
brainstorm / plan / execute - Workflow phasesskills / agents / hooks - Component typesrouting / do - How routing workssubagent - Subagent-driven executionConstraint (Over-Engineering Prevention): Answer only what was asked. Do not dump the entire system architecture when the user asks about one skill. Scope your response to the question asked, then offer to explain related concepts.
Gate: Topic identified. Proceed only when you know what to explain.
Goal: Read actual files before explaining anything.
Step 1: Get authoritative data from the catalog script
This constraint (Accuracy Over Speed) is non-negotiable. Counts and listings come from scripts/list-capabilities.py, which reads the generated INDEX files — deterministic, single source of truth. Match the question to the right subcommand:
| Question | Command | Output |
|---|---|---|
| Overview / "how many skills/agents?" | python3 scripts/list-capabilities.py summary | Skills / Pipelines / Agents counts |
| "what skills exist [in category X]?" | python3 scripts/list-capabilities.py skills [--category X] --brief | Count; drop --brief for the full name/trigger/description table |
| "what agents exist?" | python3 scripts/list-capabilities.py agents --brief | Count; drop --brief for the full table |
| "tell me about " | python3 scripts/list-capabilities.py show <name> | Type, description, triggers, category, file path for a skill/agent/pipeline |
| Fuzzy lookup / "is there a skill for X?" | python3 scripts/list-capabilities.py search <query> | Ranked name/trigger/description matches across skills, pipelines, agents |
test cases passed, vs 2 / 8 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.