route-task
Skill2 starsChanged 4 months agoMITView on GitHub
Route an incoming transformation-programme task to the right thinker lens (CSO/CFO/CAO/CIO/CPO/etc.) and skill. Use at the start of any task that involves analysis, decision-making, exec output, or skill selection, especially when the task signal is ambiguous (cost lever, data question, contract, headcount, working capital, savings phasing, client approval, ops feasibility, risk, steerco, one-pager).
3 other projects use a version of this.
Adopted by
Most recently taken up by
- allemaar/open-skillstheir own version, first seen Oct 13, 2026
- limoaCatherine/game-studio-harnesstheir own version, first seen Sep 20, 2026
- sepehrbayat/SEPCCtheir own version, first seen May 31, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- sepehrbayat/SEPCC★ 38same name
- allemaar/open-skills★ 15same name
- limoaCatherine/game-studio-harness★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- commercial-insightSkill
- data-requestSkill
- scenario-modelSkill
- duckdbSkill
- intelligence-internal-commsSkill
- market-intelSkill
- sql-reviewSkill
- xlsxSkill
- docxSkill
- pdfSkill
- pptxSkill
- theme-factorySkill
- utility-markitdownSkill
- thinkcellSkill
- clevel-reviewSkill
- exec-commsSkill
- partner-reviewSkill
- working-constructSkill
- pm-customer-journeySkill
- pm-exec-onboardingSkill
- pm-problem-statementSkill
- pm-proto-personaSkill
- pm-storyboardSkill
- pm-user-storySkill
- kanban-curateSkill
- epic-builderSkill
- exec-summarySkill
- steerco-packSkill
- program-trackerSkill
- weekly-reviewSkill
- book-deskSkill
- draw-excalidraw-diagramSkill
- mcp-builderSkill
- notion-workboardSkill
- smartsheetSkill
- utility-transcribeSkill
- writing-humanizerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
When Jacob provides a task, classify it and route to the right thinker lens + skill.
≈ “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
Task Routing — Thinker Lenses + Output Skills
When Jacob provides a task, classify it and route to the right thinker lens + skill. Thinkers CHALLENGE and SHAPE — they don't produce outputs. Skills produce outputs.
| Signal | Load thinker(s) — Read the file | Route to skill |
| Initiative sizing, prioritisation, "should we do this" | context/cso.md | program-tracker, scenario-model |
| Data analysis, methodology, "is this right" | context/cao.md + context/data-landscape.md | category-review, sql-review, data-request |
| Systems feasibility, SAP ECC / S4HANA, Databricks, Novus, VMP, master data, integration, IT dependency, automation feasibility, reporting capability gap, "can we system-enforce this" | context/cio.md + context/data-landscape.md | sql-review, data-request, scenario-model |
| Cost modelling, pricing, inflation, market rates | context/chief-economist.md | scenario-model, commercial-insight |
| Category strategy, vendor, panel, consolidation | context/cpo.md + context/coo.md | category-review, commercial-insight |
| Headcount, leave, restructure, EA, labour cost | context/chief-people-officer.md + context/general-counsel.md | leave-liability-telco, scenario-model |
| Working capital, payment terms, DPO, DSO, cash flow | context/cfo.md | scenario-model, commercial-insight |
| Savings recognition, P&L vs balance sheet, phasing | context/cfo.md | program-tracker, exec-summary |
| Contract terms, EA clauses, procurement policy, legal feasibility | context/general-counsel.md + context/cro.md | commercial-insight |
| Client approval / notification, head contract, SLA/KPI impact, contract reopen, price review, account team, named client (a telco client, a state-government facilities client, Defence, a national network client, state transport), IGET / indigenous / local content, client-specified vendor | context/chief-client-officer.md + context/general-counsel.md | commercial-insight, category-review |
| Operational feasibility, site adoption, change management, mobilisation | context/coo.md + context/delivery-difficulties.md | epic-builder, scenario-model |
| Risk, insurance, WHS, vendor lock-in, regulatory | context/cro.md + context/general-counsel.md | scenario-model, commercial-insight |
| Competitor, tender, contract award, market news | — | market-intel |
| Steerco, ExCo update, program status | context/cso.md + context/cfo.md | steerco-pack, program-tracker |
| One-pager, CFO summary, exec brief | context/cfo.md | exec-summary |
| Smartsheet data, team plan, task tracking | — | smartsheet |
| Web page, frontend, UI design, HTML artifact | context/cdo.md | web-frontend-design, impeccable/*, taste-skill/*, huashu-design, emil-design-eng (precedence rules in frontend-precedence skill) |
| Slide deck, presentation pipeline | — | See context/pipeline.md |
| New project setup / group spend analysis | — | See context/triggers.md |
Rule: When a thinker column is specified, Read the file before responding. Don't rely on memory of its content. Multi-signal tasks load multiple thinkers — don't pick just one. When in doubt between CIO and CAO: CAO challenges "is this analysis right"; CIO challenges "can the system / data actually deliver this." When in doubt between Chief Client and CRO/GC: CRO/GC cover legal enforceability; Chief Client covers relationship reaction and client-side approval path.
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.