capabilities
Skill2 starsChanged 3 months agoMITView on GitHub
The system's self-model — a capability registry (scans every SKILL.md into a layered tree SENSE→DECIDE→ACT→REMEMBER→GOVERN→DEPLOY) plus a "curator" that picks the right capabilities for a goal locally. Use to see the whole toolkit as a system/arborescence, to let an agent discover what botte-secrète can do, or as the data the Conductor reads to compose a plan.
4 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- zedarvates/frugal-skillsedited, first seen Nov 8, 2026
- Celorus/celorus-plugintheir own version, first seen Nov 6, 2026
- telefrek/vallorcinetheir own version, first seen May 10, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- zedarvates/frugal-skills★ 142% same
Wrote their own version · 3
- jskswamy/skills★ 3same name
- Celorus/celorus-plugin★ 0same name
- telefrek/vallorcine★ 0same 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 repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- clean-cacheSkill
- agent-cacheSkill
- app_testSkill
- asset-qualitySkill
- auto_distillSkill
- auto-memorySkill
- auto_routerSkill
- benchSkill
- bootstrapSkill
- botte-proxySkill
- cacheSkill
- cardinalSkill
- cavemanSkill
- checkupSkill
- clarificationSkill
- clusterSkill
- code_fingerprintSkill
- completion_proofSkill
- conductorSkill
- context_budgetSkill
- context_profilerSkill
- context_slicerSkill
- context_windowsSkill
- control_loopSkill
- cost_estimatorSkill
- cwe_kbSkill
- dag_optimizerSkill
- dashboardSkill
- decision-ladderSkill
- demoSkill
- diff_languageSkill
- directives_auditSkill
- docgenSkill
- docs_stewardSkill
- eventsSkill
- fallow_likeSkill
- fast_contextSkill
- fixSkill
- harness_deltaSkill
- hermes-bridgeSkill
- hf_provenanceSkill
- infra_advisorSkill
- ingestSkill
- llm_backendsSkill
- llm_mcpSkill
- loaderSkill
- mcp_gatewaySkill
- meta_harnessSkill
- metricsSkill
- migration_auditSkill
- monte_cristoSkill
- mousquetairesSkill
- nlp_deterministicSkill
- nn_auditSkill
- prefix-prunerSkill
- prefix_treeSkill
- preflightSkill
- prompt_improverSkill
- reportSkill
- The first 60 shown.
The file
Files
capabilities — the system's map of itself (registry + curator)
Turns the 26 modules from a collection into a system: one self-describing tree the rest can reason over.
python -m skills.capabilities.cli map # ASCII layered system tree
python -m skills.capabilities.cli list --json # the registry
python -m skills.capabilities.cli curate "test my desktop app"Layers (the arborescence)
| Layer | Role |
| SENSE | understand project / cluster / task |
| DECIDE | route the work, cheapest capable |
| ACT | do the work, local-first |
| REMEMBER | capitalise (compounding) |
| GOVERN | consistency & cost control |
| DEPLOY | wire into projects & measure |
Each skill's layer comes from a layer: field in its SKILL.md frontmatter, else
a built-in map, else ACT. Generated snapshot: docs/system-map.txt.
The curator
curate(goal) ranks the capabilities most relevant to a goal (local lexical
match, 0 tokens) — the librarian that hands the Conductor (and you) the right
branches of the tree to use. Built on [[skill_finder]].
This registry is the foundation for the Conductor (goal → decision tree → ordered plan of capabilities, executed local-first) and the control loop (measure → adapt). Related: [[skill_finder]], [[auto_router]], [[bootstrap]].
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.