enablement-router
Skill14 starsChanged 8 months agoMITView on GitHub
Route revenue enablement requests to the smallest coherent skill or sequence. Use when the user asks which skill to use, combines multiple enablement jobs, needs a staged workflow, or describes a performance problem without knowing the right enablement response. Route clear single-artifact requests directly to the corresponding specialist skill.
In this repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- account-brief-builderSkill
- battlecard-builderSkill
- call-insights-to-objectionsSkill
- call-review-coachSkill
- case-study-extractorSkill
- certification-program-builderSkill
- content-gap-analysisSkill
- content-governance-systemSkill
- deal-inspection-coachSkill
- discovery-and-demo-structureSkill
- discovery-rubric-auditorSkill
- enablement-house-styleSkill
- enablement-impact-storySkill
- enablement-metrics-and-instrumentationSkill
- enablement-program-designSkill
- executive-briefing-builderSkill
- field-feedback-synthesizerSkill
- forecast-risk-briefSkill
- manager-coaching-cadenceSkill
- mutual-action-plan-builderSkill
- objection-library-builderSkill
- onboarding-program-builderSkill
- onboarding-to-value-playbookSkill
- one-pager-and-slide-outlineSkill
- partner-enablement-packageSkill
- pipeline-stage-definition-and-exit-criteriaSkill
- product-launch-enablementSkill
- proposal-rfp-orchestratorSkill
- qbr-ebr-builderSkill
- quarterly-enablement-plannerSkill
- release-notes-to-seller-updatesSkill
- renewal-and-expansion-enablementSkill
- revenue-enablement-contextSkill
- roleplay-scenario-builderSkill
- talk-track-builderSkill
- value-prop-and-positioningSkill
- win-loss-synthesisSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
If the user asked for a battlecard, do not send them through context, positioning, and a launch plan first.
- Very specific: line 24
Add revenue-enablement-context only when missing or stale assumptions would weaken the first step.
- Distinctive: line 33
Use one skill when it can complete the request.
- Distinctive: line 34
Keep long sequences manageable.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Enablement router
Help the user choose the skill or short sequence that produces the result they need.
If the user asked for a battlecard, do not send them through context, positioning, and a launch plan first.
Direct. "Build the card with battlecard-builder. You already have the competitor and the claim limits."
Tour. "First we should establish context, then positioning, then a program charter, then the battlecard."
Route only, unless the user also asked you to do the work. Read references/route-map.md when two skills look alike.
When to route
Derive the job from the request before asking. Ask one question only when the answer changes the primary skill, the order, or the audience mode.
A performance problem with no diagnosed cause goes to enablement-program-design in discovery mode. If evidence points to product, incentives, capacity, or territory, identify the responsible owner and any limited enablement support that would still help.
Add revenue-enablement-context only when missing or stale assumptions would weaken the first step.
How to pick
- Translate the request into jobs and one observable end result. Done when you can name the artifact they will actually use.
- Drop related work nobody asked for.
- Match jobs to the route map. Use the boundary column when two skills look alike.
- Mark each step
Available noworAdditional skill needed. Do not invent install commands. - Use one skill when it can complete the request. Add another only for a distinct requested deliverable or a genuinely required dependency.
- Keep long sequences manageable. Show the immediate phase, its completion evidence, and what would trigger the next phase rather than starting every related workflow at once.
What to return
Direct route: what to do next, primary skill and availability, nearest boundary, first input.
Sequence: a short table with order, skill, availability, job, handoff, and expected output. Not for a single-skill route.
Include assumptions, deferred work, and one starting action. A handoff packet is facts, conflicts, blocking unknowns, sources, requested output, and stop condition.
Done when
- A direct specialist request reaches the relevant skill without unnecessary setup.
- Unavailable skills are not presented as runnable.
- The user can start immediately.
- Related work stays deferred.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.