tkersey/operationalizing-expertise
codex/skills/operationalizing-expertise/SKILL.md
Operationalize expert methods into corpus, quote bank, triangulated kernel, operator library, and validators. Use when distilling a methodology or mining session history into executable rules.
$ install --global
skillsauthnpx skillsauth add tkersey/dotfiles operationalizing-expertiseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:50 PM1.9s1 file scanned
SKILL.md
- name:
- operationalizing-expertise
- description:
- >-
Operationalizing Expertise
Goal: turn tacit method into executable, auditable artifacts.
Quick Start (pick a track)
Track A: Static Distillation (corpus -> kernel)
Use when you only need a stable, parseable methodology (Lemelson-style).
Summary: corpus + quote bank + triangulated kernel + operator library + validators.
Full steps: references/WORKFLOWS.md.
Track B: Orchestrated Loop (kickoff -> deltas -> artifact)
Use when you want multi-agent sessions that compile into structured artifacts (Brenner-style).
Summary: kickoff -> deltas -> deterministic merge + lint -> artifacts.
Full steps: references/WORKFLOWS.md and references/ARTIFACTS.md.
Track C: Session Mining (your own practice)
Use when operationalizing your own repeated behaviors into a reusable skill.
- Find repeated prompts/actions in history (cass search).
- Extract triggers, actions, and avoided failures.
- Generalize into rules: "When X, do Y because Z."
- Validate against counter-examples.
If unsure, start with Track A then add Track B only if you need orchestration.
Deliverables (non-negotiable)
corpus/primary_sources/with source transcripts or paperscorpus/quote_bank/quote_bank.mdwith stable anchors + tagscorpus/distillations/{gpt,opus,gemini}/...corpus/specs/triangulated_kernel.mdwith START/END markerscorpus/specs/operator_library.mdwith operator cards + prompt modulescorpus/specs/session_kickoff*.md(role prompts or kickoff templates)scripts/validate-corpus.py,scripts/validate-operators.py,scripts/extract-kernel.pyartifacts/for compiled outputs (if Track B)
Core Invariants (must hold)
- Evidence-first: every rule cites anchors in the quote bank.
- Deterministic parsing: kernel/operator sections must be marker-bounded.
- Triangulation: kernel contains consensus only; disagreements go to DISPUTED/UNIQUE.
- Operator cards must include triggers, failure modes, and a prompt module.
- Validation gates are required; failing them blocks release.
- Provenance must be auditable (quote IDs, source file, page/section).
- Join-key contract: thread_id ties mail thread, tmux session, and artifact file.
- Memory feedback is opt-in and must be hygiene-gated.
Canonical Markers and Formats
See references/FORMATS.md (kernel markers, quote bank entries, operator cards, delta blocks).
Workflow A + B (full)
See references/WORKFLOWS.md for detailed steps.
Validation Gates (minimum)
See references/VALIDATION.md (includes the minimum gate list verbatim).
Anti-patterns
See references/ANTI-PATTERNS.md (includes the minimum list verbatim).
Output Contract (what you produce)
See references/OUTPUT.md.
Reference Index
- Corpus structure:
references/CORPUS.md - Distillation prompts:
references/DISTILLATION.md - Triangulation rules:
references/TRIANGULATION.md - Operator cards:
references/OPERATORS.md - Kickoff prompts:
references/KICKOFF.md - Artifacts and deltas:
references/ARTIFACTS.md - Validation gates:
references/VALIDATION.md - Jargon/terms:
references/JARGON.md - Anti-patterns:
references/ANTI-PATTERNS.md - End-to-end case:
references/CASE-STUDY.md
Related Skills
tkersey/fm
tools
VerifiedTrustedCommunity
Invokes Apple's macOS 27 fm command-line tool from a local Mac to use the on-device system model or Private Cloud Compute, including instructions, image prompts, schema-constrained JSON, and noninteractive automation. Use when the user asks to run Apple Foundation Models through fm, compare system versus pcc, generate structured output, or automate fm without Swift or an app.
64SKILL.mdUpdated Jul 20, 2026
tkersey/hylo
development
VerifiedTrustedCommunity
Compile historical Codex sessions into governed counterfactual evidence, evaluate an existing owner-applied candidate through blinded paired HCTP trials, and fold observable evidence into RUN, OBSERVE, or STOP. Use for `$hylo`, CRF extraction, counterfactual replay, source-governed direct or historical trials, sealed evidence, paired baseline/candidate evaluation, causal frontiers, or evidence-governed improvement.
64SKILL.mdUpdated Jul 13, 2026
tkersey/ledger
testing
VerifiedTrustedCommunity
Ensure a `ledger` command is available on PATH; materialize, validate, record, replay, and project requested Actuating artifacts without taking semantic or execution authority; coordinate the shared Learnings/Synesthesia/Negative Ledger lifecycle checkpoint and repo-local source-memory reconciliation; address Universalist plans and receipts; and perform pure artifact validation.
64SKILL.mdUpdated Jun 29, 2026
tkersey/review-fold
testing
VerifiedTrustedCommunity
Classify and quotient review findings, failing tests, incidents, bug reports, migration failures, and other witnessed falsifiers against accepted intent and the current Construction. Author counterexample-set/v1 without selecting repairs, counting review credit, or granting mutation.
64SKILL.mdUpdated Jun 28, 2026