Platform · Building · new here
Task-as-Skill-Evidence — verifiable skills from completed work (US20210035048A1 free)
Derives a VERIFIABLE, evidence-grounded skill profile from the work a person actually completed — not self-report. Given completed-task records (description, outcome, difficulty, completedAt) + a skill ontology, tags each task to the skills it evidences by dense-embedding cosine, calibrates per-skill proficiency by NOISY-OR over evidence weighted by recency × outcome × difficulty, returns a Bayesian confidence interval (tightening with corroboration), the supporting tasks as PROVENANCE, honest unevidenced-skill gaps (never claimed), and co-occurrence skill adjacencies. Skill is demonstrated, not declared. Embedding-provider agnostic (deterministic in-repo feature-hashing mock, no API key); deterministic, stateless, pure compute. US20210035048A1 (project & skill-set verification) is ABANDONED → free to implement, no design-around. Complements: output FEEDS Principia competency-rollup as evidence; the missing tasks→skills inference that skill-trajectory-matching (skill SEQUENCES) does not do.
- Cluster
- Platform
- Type
- algo
- Status
- Building
- Used by
- principia:competency-rollup
Maturity evidence
- Functioning
- core/skill-evidence.ts (embedding tagging → recency/outcome/difficulty-weighted noisy-OR proficiency + Bayesian confidence + co-occurrence adjacencies + honest gaps) + core/embedder.ts (feature-hashing mock, no API key) + REST (POST /api/spokes/skill-evidence/derive, service-key; GET /health) + MCP (skill-evidence.derive/health) from one contract; 7/7 core tests incl. tagging+provenance, noisy-OR proficiency rises with corroboration, recency decay, outcome weighting, adjacencies, honest unevidenced gaps.
- Valuable
- Routed from the patent-radar sweep (rank #10, Tier-A free). No live consumer yet; default embedder is a deterministic lexical mock (swap a real model at the port seam for semantic task→skill tagging). Output is designed to feed Principia competency-rollup as evidence.
- Understood
- spoke README (use case: evidence-derived profile vs inflated self-report, engineer task-history example; flow mermaid tasks → tagging → calibration → profile + provenance) + docs/SURFACE.md + CHANGELOG.
- Integrated
- REST + MCP from one declaration; registered in lib/mcp/register-tools.ts + db barrel. No live consumer wiring yet; coordinate with skill-trajectory-matching owner (adjacent, distinct unit).
How to use it
- REST
- /api/spokes/skill-evidence/derive
- MCP
- skill-evidence.derive
- Data
- src/spokes/skill-evidence/core/skill-evidence.ts
Other Platform capabilities
- Comp audit self-serve — CSV intake, free validate, commerce-gated watermarked run (HO-155)
- Gift pass — gifted ownership on the entitlement store (magic-link claim)
- JobFrame canonical Job Family × Focus × Level taxonomy + classifier
- SMB pay-system wizard — chocolate/vanilla over the pay-system catalog
- Support channel — portfolio-wide /support form → ticket store → operator email
- Ask-your-data — generalizable NL→rank→tier→cite spoke (HO-378)
- Diagnostic acquisition — next-best-ask over a live hypothesis set
- Executive-Priorities Elicitation Instruments (static catalog)
Capability detail sourced from the People Analytics Toolbox capability feed (source of truth), snapshot retrieved 2026-07-23.