A skill is one job, written down once, in a form both a human in a chat window and an agent on a cron can execute identically. 62 are active. They are the unit the whole OS composes from: an agent is a skill plus a trigger, and a fleet is a set of agents sharing a library.
os_skills — 62 status=active.
os_skillsos_skill_agent_mapA prompt is disposable and lives in someone's chat history. Documentation describes what happened. A skill is an executable instruction set with a name, a trigger vocabulary, declared data sources, and a maturity score — so that the fourth time someone needs to classify an account, they run the same thing the agent runs, and both get better together.
Practically, this is what makes the fleet compound. When account_matching_ladder improves, every agent that uses it improves, and so does the analyst doing it by hand. Twenty-nine of the 62 skills are currently human-only — that isn't a gap, it's the pipeline: skills get written for humans first, then wrapped in an agent once the shape is stable.
Three skills carry a p0 priority, and they are all about the same problem: deciding whether two records are the same real-world thing. Everything downstream — account metrics, campaign attribution, engagement tiers, a rep's view of a relationship — is a function of getting this right. They are also the best-engineered skills in the library, and worth reading as the house standard.
CONF_BY_METHOD lookup table.Why it's the standardIt has a negative prior and a corroboration-only ceiling — meaning it can conclude "probably not a match" and it refuses to get confident from a single weak signal. Most scoring code can do neither.
Answers"Why 0.87?" — with a breakdown, not a number.
The two rules that matterMatch before mint (never create a new ID before exhausting the ladder) and never silently discard (an unmatched candidate becomes a proposal, not a deletion).
FeedsMADE-ID CUSTODIAN, RESOLVER.
StatusP0/P1 hardening documented in-skill.
contact_account_rollup (p1) — "the 31% gap." Roughly a third of CRM contacts carry a MADE-ID but resolve to no company, which understates every account-level engagement metric by about a third. It gates campaign attribution. This is a known, quantified, scoped gap — Tier 2, not Tier 1, because nobody is pretending it's solved.
The revenue-facing half of the library, split by function: demand (find and engage), delivery (propose and produce), operations (run the machine), knowledge (how we talk).
| Skill | What it does | Maturity | Agents |
|---|---|---|---|
| outreach_message_composer | Compose A+ outreach messages against the 6-dimension MADE rubric. | 75 | 0 |
| social_listening | Monitor and interpret social signal. | 70 | 2 |
| competitive_battlecard | Per-competitor battle cards for BD conversations. | 65 | 4 |
| campaign_tracker | Track campaign state and performance. | 60 | 1 |
| sfdc_opportunity_brief | One-page exec brief for an SFDC opportunity. | 65 | 1 |
| inside_sales | Inside-sales motion and cadence. | 55 | 0 |
| pipeline_execution | Pipeline execution discipline. | 55 | 1 |
| brand_authority | Brand authority and media positioning. | 45 | 0 |
| campaign_crosswalk | Member-set Jaccard across SFDC / HubSpot / bc_outreach. Records itself as currently cosmetic — 99 groups × 1 system each, zero cross-system merges ever. Blocked on contact_account_rollup. | 45 | 0 |
campaign_crosswalk declares in its own description that it has never produced a cross-system merge and names what it's blocked on. A skill that documents its own uselessness is more valuable than one that quietly returns empty results.| Skill | What it does | Maturity | Agents |
|---|---|---|---|
| proposal_rfp_review | Review a Made proposal against a client RFP for scope, technical accuracy and pricing. | 75 | 2 |
| content_studio | Content studio and outreach generation. | 70 | 2 |
| made_report_template_design | Report template design. | 65 | 0 |
| made_presentation_builder | Branded MADE pptx from a markdown outline. | 60 | 1 |
| proposal_excellence | Proposal quality standard. | 55 | 1 |
| campaign_message_preview_modal | Read-only preview modals for campaign messages in React + Tailwind. | 50 | 0 |
| Skill | What it does | Maturity | Agents |
|---|---|---|---|
| elt_weekly_report | The ELT Weekly Report for the Wednesday LT call. | 80 | 1 |
| crm_field_sync_governance | Which system owns which field, and what may overwrite what. | 75 | 1 |
| news_intelligence | News monitoring and relevance scoring. | 70 | 4 |
| priority_inbox_triage | Triage an inbox using email_insights priority scores. | 70 | 1 |
| buyer_segment_classification | Assign a buyer segment. | 65 | 2 |
| kpi_review | KPI review discipline. | 60 | 2 |
| meeting_intelligence | Extract decisions and actions from meetings. | 60 | 1 |
| portfolio_dashboard | Portfolio-level reporting. | 60 | 1 |
| database_metrics | Standard DB metric definitions. | 55 | 1 |
| demand_planning | Demand and capacity planning. | 55 | 2 |
| pricing_framework | Pricing and costing framework. | 55 | 1 |
| revenue_forecasting | Revenue forecasting method. | 55 | — |
| crm_integration | CRM integration patterns. | 55 | 0 |
| monday_integration | Monday.com board integration. | 55 | 0 |
| data_hygiene | Data hygiene standards. | 55 | 2 |
| account_classification | Classify an account. | 50 | 2 |
| territory_management | Territory definition and assignment. | — | — |
| scorecard_review | Scorecard review cadence. | — | — |
| Skill | What it does | Maturity | Agents |
|---|---|---|---|
| made_commercial_ops | MADE commercial vocabulary, voice registers and anti-patterns. The reason two agents describe the same deal the same way. | 75 | 1 |
Cross-cutting capability: how output gets made to look right, how identity gets resolved, and how engineering work gets done safely. These are the skills any agent or any person can pick up regardless of which fleet they sit in.
| Skill | What it does | Maturity | Agents |
|---|---|---|---|
| made_design_system | Apply @made-sci/design-system to any Lovable/Vite app. | 65 | 0 |
| made_brand_guidelines | Official MADE brand identity for presentations and visual output. | 60 | 2 |
| figma_design_intelligence | Read and reason about Figma design intent. | 55 | 0 |
| excalidraw_diagrams | Diagram creation from natural language. | 55 | 0 |
| image_generation | On-brand images, palette and imagery direction pulled from the brand pack. | 50 | 3 |
| video_generation | Veo clips, HeyGen talking-head, assembled short video. | 50 | 2 |
| landing_page_generation | On-brand landing pages driven by Made v2 tokens. | 50 | 0 |
| brand_pack_scaffolder | Turn a brand bible into a working brand pack. | 50 | 0 |
| ui_scaffolding | React/Tailwind UI that is on-brand by construction. | 50 | 0 |
| social_carousel | Multi-slide LI/IG carousels with a consistent Made look. | 45 | 1 |
| Skill | What it does | Maturity | P |
|---|---|---|---|
| confidence_scoring | Log-odds fusion, 15 signals, 31 tests. See above. | 70 | p0 |
| account_matching_ladder | Eight-rung ladder producing a candidate set. | 65 | p0 |
| contact_matching_ladder | ID-chain-first with role-address filter. | 60 | p0 |
| contact_account_rollup | Closes the ~31% of contacts with a MADE-ID but no company. Gates campaign attribution. | 55 | p1 |
| account_matching | Account matching and deduplication (the general skill). | 60 | — |
| data_hygiene | Hygiene standards, shared with commercial ops. | 55 | — |
| coordinate | Hub-and-spoke multi-agent prompting discipline for complex tasks. | 60 | — |
| Skill | What it does | Maturity |
|---|---|---|
| commit | Structured commit messages that function as long-term memory for the next session. | 80 |
| health_check | Health check across all Supabase databases; updates SYSTEM_STATUS. | 75 |
| prime | Session priming — catch an agent up on codebase state. | 75 |
| session_close | End-of-session protocol: update docs, commit, log outcomes. | 75 |
| plan_with_risk | Risk-classified planning for HIGH-risk changes (the ULTRAPLAN equivalent). | 70 |
| verify | Adversarial self-verification — catch issues before marking work done. | 70 |
| supabase_audit | Security + performance audit against a Supabase project. | 70 |
| lovable_rls_policy_check | Pre-flight RLS check before adding any new Supabase write in a Lovable app. | 70 |
| switch_db | Switch context to a specific Made database for MCP queries. | 70 |
| claim_project_number | Reserve a PROJ-NNN via the registry before creating a new project. | 65 |
commitNot a model call. Not a classifier. A convention for writing commit messages — scored 80, the top of the library. verify, prime, session_close and plan_with_risk sit just behind it.
That ordering is not an accident and it is not a gap. Those five skills are what make everything else repeatable: they encode how work starts, how it is checked, and how it is handed to the next session. An agent fleet without them produces output nobody can audit six weeks later — which is exactly the condition the four red findings describe.
Split the same way as everywhere else on this site: things we believe are working that aren't, versus things we know we haven't built.
Whichcampaign_crosswalk ("currently cosmetic — 99 groups × 1 system each, zero cross-system merges ever") and contact_account_rollup ("the 31% gap").
Why amber and not redBecause they say so themselves, in the registry, in the description field. Anyone querying the library gets the caveat with the record. That is the mechanism working — a skill honest about its own limits cannot mislead.
ActionNone urgent. Both are correctly labelled and correctly blocked.
Whichclinical_trials_monitoring → trialwatch (p1) · vertical_signal_monitoring → sentinel (p1) · quote_win_loss_analysis → VERDICT (p2).
Why this is deliberateSkill first, agent second. Writing the skill forces the thinking — what are the inputs, what is a good output, what would make this wrong — before anyone picks a harness. An agent built before its skill is a prompt with a schedule.
ActionNothing. This is the pipeline in its correct state.
maturity is self-assessed, and agent_count counts wiring, not usage. So nobody can currently answer "which skill actually gets invoked most, and which one fails most often." That is a future item — but it's the one that would make every other number on this page earn its place.