Capability Atlas
The public catalog of reusable knowledge entities created or applied during the Talomnia launch. It is a graph, not a tree: roles reference skills, skills reference blueprints, blueprints are reused across tasks.
Overview
The catalog separates what is published from what is demonstrably applied: the applied figure counts only explicit workflow-ledger evidence that resolves to a published identity.
- capabilities published
- 128
- created for Talomnia
- 86
- used in a published workflow
- 77
| type | published | withheld |
|---|---|---|
| blueprint | 16 | 5 |
| competency | 8 | 0 |
| constraint | 12 | 3 |
| policy | 8 | 1 |
| prompt registered gap | 0 | 1 |
| resolution receipt | 7 | 0 |
| role | 27 | 3 |
| script registered gap | 0 | 4 |
| skill | 43 | 89 |
| acceptance criterion | 7 | 0 |
| template registered gap | 0 | 2 |
A registered gap is a recorded absence, not an oversight: artifacts of this type exist and work in the repository — the accounting counts them from the Git inventory — but the knowledge graph holds no published typed revision for them yet. We record that absence explicitly instead of fabricating a revision after the fact; the gap stays a gap until a revision passes the lifecycle to publication.
- created for Talomnia
- 86
- reused from Arcanada and Datarim
- 42
- published (public-sanitized lifecycle)
- 128
- withheld (internal and experimental)
- 108
- total inventory entities
- 236
- published
- 128
- withheld pending lifecycle
- 108
Everything created for Talomnia was created in this launch — Talomnia has had no other launch; the reused capabilities come from the Arcanada ecosystem and the Datarim framework.
The catalog does not silently show a subset: for every entity type the table states how many artifacts the knowledge inventory holds and how many are withheld from publication. An artifact stays withheld until it has passed the full lifecycle to public-sanitized status: most withheld skills and roles are Datarim framework definitions imported as graph-grade records without contract-grade payloads, or artifacts carrying no execution evidence from the launch tasks; the rest are drafts and internal artifacts. Publication happens only through lifecycle promotion with evidence at every transition — the visibility gate is never widened to make the catalog look fuller.
Catalog filtered to the neighbours of · show the whole catalog
- created for Talomnia
- 86
- reused from Arcanada and Datarim
- 42
-
Talomnia Component Library
blueprint · v0.7.0 · published, public-sanitizedSeventeen framework-neutral component specifications covering every site surface, from buttons and navigation to the load-bearing evidence set.
View capability -
Design System as Atlas Artifacts
blueprint · v0.1.6 · published, public-sanitizedA staged path that turns digest-pinned design research into an enforceable design system: tokens, typography, spacing, navigation, imagery, tables and bilingual discipline authored as versioned…
View capability -
Design-to-Code Loop Blueprint
blueprint · v0.1.0 · published, public-sanitizedA staged, gated loop that carries accepted design decisions into verifiable product code: frozen context projection, digest-pinned research, multiple directions, independent selection, visual asset…
View capability -
Editorial Evidence Atlas — Long-Form Document Blueprint
blueprint · v0.2.1 · published, public-sanitizedReusable proof-first long-form page blueprint with semantic locale registries, an evidence spine, conditional chapter navigation, full-shell figure bands, and source-backed provenance.
View capability -
Evidence-Bearing Verification
blueprint · v0.1.5 · published, public-sanitizedA reuse pattern for building verifications whose results count as evidence, not claims.
View capability -
Evidence Spine Blueprint
blueprint · v0.1.0 · published, public-sanitizedDefines Claim, Capability, Execution evidence, and Verification evidence as linked reusable types with honest absent and target states.
View capability -
Knowledge Evolution
blueprint · v0.1.5 · published, public-sanitizedA pattern for revising an existing knowledge artifact when evidence attributes a deficiency to it; an unsuccessful run alone is not enough, and ambiguous attribution is recorded as an unresolved…
View capability -
Knowledge Expansion
blueprint · v0.1.5 · published, public-sanitizedA pattern for adding a genuinely new knowledge artifact when a recorded Gap proves that no existing one covers a requirement; taste or a low-ranked candidate is never a starting point.
View capability -
Knowledge Repository Bootstrap
blueprint · v0.1.3 · published, public-sanitizedA repeatable procedure for standing up a private knowledge repository for a product layer: targeted spec intake, format research against real exemplars, an architecture decision record, a scaffold…
View capability -
Lane Handoff
blueprint · v0.1.0 · published, public-sanitizedA reuse pattern for replacing a running agent lane with a fresh session without losing what the lane established.
View capability -
Long-Form Document Page
blueprint · v0.1.0 · published, public-sanitizedThe page type for a document that is read rather than scanned: a research study, a white paper, a long argument with tables, graded claims and a source manifest.
View capability -
Site Page Templates
blueprint · v0.3.0 · published, public-sanitizedFourteen page templates covering every section of talomnia.com, from the home page and workflow case pages to the investor room, pricing and forms.
View capability -
Payment Provider Adapter
blueprint · v0.1.5 · published, public-sanitizedIsolates all payment logic behind a single PaymentProvider interface with a Stripe test-mode implementation, guarded by a feature flag that is off by default.
View capability -
One-Way Projection Pipeline
blueprint · v0.1.3 · published, public-sanitizedA one-way, reproducible pipeline from the Git knowledge repository into the site database and the Capability Atlas.
View capability -
Sanitized Repository Provisioning
blueprint · v0.1.5 · published, public-sanitizedProvisions the public showcase repository and the private site and backend repositories with the sanitization discipline built in from the first commit.
View capability -
Task-to-Contract Resolution
blueprint · v0.1.5 · published, public-sanitizedThe pattern that turns a task intent into an issued Knowledge Contract through five stages, propose, validate, select, assemble and issue, run over a pinned repository snapshot.
View capability -
Bilingual Content Competency
competency · v0.1.5 · published, public-sanitizedThe ability to produce and maintain Russian and English content with full parity of meaning and a single glossary-backed terminology across the site, the White Paper, the Pitch Deck and research…
View capability -
Data Modeling and Projection Competency
competency · v0.1.5 · published, public-sanitizedThe ability to design the Talomnia data layer: the minimum entity set for workflows, research, Atlas entities and requests, with bilingual site-facing fields and graph relations rather than a tree;…
View capability -
Design Systems Competency
competency · v0.1.5 · published, public-sanitizedThe ability to research, define and ship a design system: concept, style guide, component set, page templates, mobile adaptation and accessibility criteria, authored as knowledge-repository entities…
View capability -
DevOps Operations Competency
competency · v0.1.5 · published, public-sanitizedThe ability to provision and operate the production hosting path for talomnia.com: DNS and Cloudflare with TLS and cache invalidation, versioned web-server configuration, CI/CD with…
View capability -
Integration Engineering Competency
competency · v0.1.5 · published, public-sanitizedThe ability to connect two services contract-first, exercised on the link between Talomnia forms and the Arcanada Support Center: native UI without an iframe, status sync via webhooks or polling,…
View capability -
Market Research Competency
competency · v0.1.5 · published, public-sanitizedThe ability to produce decision-grade market research: ideal customer profile, pains, competitor landscape, price points, alternatives and a first sellable service, answered from verifiable external…
View capability -
Technical Research and ADR Competency
competency · v0.1.5 · published, public-sanitizedThe ability to run the research-to-decision cycle for technology choices: inventory what the ecosystem already runs, prefer the existing supported option unless it fails the requirements, evaluate…
View capability -
Web Full-Stack Delivery Competency
competency · v0.1.5 · published, public-sanitizedThe ability to deliver a production bilingual database-driven website end to end: pages where repeated content is rendered from a database, full RU/EN parity, dark and light themes without a flash of…
View capability -
Design anti-patterns — adopted registry
constraint · v0.1.0 · published, public-sanitizedOur adopted registry of design anti-patterns, each attributed to the primary source it was read from and each marked enforced or advisory.
View capability -
Design Context Projection
constraint · v0.1.0 · published, public-sanitizedBinds product intent, audience, current component and content inventory, existing design artifacts, locale, accessibility, performance, viewport geometry, visual tokens, asset provenance, acceptance…
View capability -
Editorial Evidence Tokens
constraint · v0.1.0 · published, public-sanitizedDefines the semantic token layer for the Editorial Evidence Atlas shell, prose, rail, figure bands, captions, provenance, and light/dark states without inventing new colors or fonts.
View capability -
Editorial Reading and Reflow
constraint · v0.1.0 · published, public-sanitizedFixes the Editorial Evidence Atlas canvas, readable prose measure, conditional chapter rail, mobile collapse, text-spacing behavior, and zero page-overflow requirement.
View capability -
An Evidence Surface Declares Its Coverage
constraint · v0.1.0 · published, public-sanitizedRequires that an evidence surface either cover the whole source it is derived from or declare, in a form a check can read, the part it does not cover.
View capability -
Lane Context Threshold
constraint · v0.1.0 · published, public-sanitizedForbids an orchestrated lane from running above the declared share of its context window without a recorded, bounded decision about it.
View capability -
Locale Semantic Parity
constraint · v0.1.0 · published, public-sanitizedTreats RU and EN as honest independent editions joined only by explicit semantic keys, never by position, numbering, pixel geometry, or normalized versions.
View capability -
Motion Frequency Budget
constraint · v0.1.1 · published, public-sanitizedBinds the admissibility of a motion to how often the reader will see it.
View capability -
Sanitized Public Projection Constraint
constraint · v0.2.2 · published, public-sanitizedDefines what may never appear in any public projection of Talomnia knowledge: secrets and tokens, personal data, real filesystem paths, internal hostnames and IP addresses, and internal tracker…
View capability -
Stripe Sandbox-Only Constraint
constraint · v0.1.5 · published, public-sanitizedA hard operator boundary: the Stripe integration runs in test mode only, and no agent may enable live payment collection under any circumstances.
View capability -
Talomnia Style Guide
constraint · v0.2.5 · published, public-sanitizedThe single source of design tokens and voice rules every Talomnia surface must consume: light and dark color pairs with measured WCAG 2.1 contrast ratios, a three-face type system with full Cyrillic…
View capability -
Unknown Is Not Zero
constraint · v0.1.0 · published, public-sanitizedForbids publishing a zero, an empty table or an absent row where the truth is «not measured» or «not yet reconstructed».
View capability -
Artifact Lifecycle Policy
policy · v0.1.4 · published, public-sanitizedEvery knowledge artifact carries a maturity status and moves through a fixed promotion path: draft, reviewed, validated, shared-internal, public-sanitized, deprecated.
View capability -
Declared Human Rate
policy · v0.1.0 · published, public-sanitizedDeclares the rate at which human time is converted into money in Talomnia's published accounting, records that the rate is an operator decision rather than a measured or billed price, and binds every…
View capability -
Evidence-First Editorial Design Concept
policy · v0.3.0 · published, public-sanitizedNine binding design principles that shape talomnia.com as the published record of verifiable work rather than a product brochure.
View capability -
Honesty of Presentation Policy
policy · v0.1.5 · published, public-sanitizedA blocking content policy for everything Talomnia publishes.
View capability -
Lane Context Observation
policy · v0.1.0 · published, public-sanitizedThe orchestrator's operating rule for context across a fleet of lanes.
View capability -
Request Data Minimization Policy
policy · v0.1.3 · published, public-sanitizedThe Talomnia site database stores only reference identifiers and bounded technical sync fields for incoming requests; all personal data lives solely in the Arcanada Support Center.
View capability -
Review-to-Evolution Policy
policy · v0.1.0 · published, public-sanitizedEvery customer remark becomes a GitHub issue in the public trace repository, and every issue triggers an artifact-evolution step: closing the defect is not closing the issue.
View capability -
Source-Backed Figures
policy · v0.1.0 · published, public-sanitizedEvery rendered figure must be traceable to a versioned source artifact through a figure manifest; targets may never be shown as traction, and decoration may never be shown as evidence.
View capability -
Resolution Receipt — Support Center Integration
resolution receipt · v1.0.3 · published, public-sanitizedRecords how the resolver answered the question of which knowledge should govern integrating talomnia.com forms with the Arcanada Support Center: a sender-side HTTP client over a digest-attested…
View capability -
Resolution Receipt — Evidence Gate Verification
resolution receipt · v1.0.3 · published, public-sanitizedRecords how the resolver assembled the knowledge contract for verifying the launch Evidence Gate with facts and, on a pass, publishing talomnia.com to production through the deploy broker.
View capability -
Resolution Receipt — Launch Validation Report
resolution receipt · v1.0.3 · published, public-sanitizedRecords how the resolver assembled the knowledge contract for producing the Talomnia Launch Validation Report: every launch criterion marked pass, fail or not applicable, stop-factors listed…
View capability -
Resolution Receipt — Workflow 0 Evidence Surface
resolution receipt · v1.0.3 · published, public-sanitizedRecords how the resolver assembled the knowledge contract for publishing the Talomnia evidence surface: a Workflow 0 case page at a permanent URL with the artifact matrix, timing and cost taken from…
View capability -
Resolution Receipt — Design Knowledge (first bound design capability)
resolution receipt · v1.0.0 · published, public-sanitizedRecords the first resolution in the project's history that binds a design capability.
View capability -
Resolution Receipt — Motion Layer (the animation's contract)
resolution receipt · v1.0.0 · published, public-sanitizedRecords the resolution that makes the site's ambient motion layer buildable.
View capability -
Resolution Receipt — Context Lifecycle (the fleet's operating contract)
resolution receipt · v1.0.0 · published, public-sanitizedRecords the resolution that binds the fleet's context-lifecycle contract.
View capability -
Chief Architect
role · v0.1.5 · published, public-sanitizedThe role that keeps a system coherent as it grows.
View capability -
Autonomous Executive Lane
role · v0.1.4 · published, public-sanitizedRuns a single epic stage end-to-end from a written brief, without operator interaction, inside one execution context.
View capability -
Code Simplifier
role · v0.1.0 · published, public-sanitizedThe role that makes freshly written code clearer without changing what it does: less nesting, no redundancy, honest names, project style — and a hard boundary against cleverness, merged concerns, and…
View capability -
Compliance Runner
role · v0.1.0 · published, public-sanitizedThe role that hardens a change after QA: the full seven-step workflow — re-validation against the requirement, simplification of what the change touched, references, coverage, lint, tests — closed by…
View capability -
Customer Acceptance
role · v0.1.6 · published, public-sanitizedThe customer-side role that decides whether delivered work is accepted in the two-sided execution model.
View capability -
Customer Task Author
role · v0.1.6 · published, public-sanitizedThe role that opens work on the customer side of the two-sided execution model: it authors the task issue in the public trace repository with the task statement, its boundaries, and acceptance…
View capability -
Deployment Operator
role · v0.1.6 · published, public-sanitizedThe role that takes a verified release bundle from committed repository state to a healthy target contour through the deploy-broker channel, with staging rolled out and verified before production.
View capability -
Design Lead
role · v0.2.0 · published, public-sanitizedOwns the visual and interaction design of every Talomnia surface, executing design work only against an issued knowledge contract that selects the design capability.
View capability -
Senior Developer
role · v0.1.5 · published, public-sanitizedThe implementing role: it turns an approved plan into code under test-driven discipline, where the failing test precedes the production code.
View capability -
DevOps Engineer
role · v0.1.5 · published, public-sanitizedThe delivery role: it owns the path from a commit to a service running in production.
View capability -
Content Editor
role · v0.1.0 · published, public-sanitizedThe role that brings written content to publication-ready quality through structured editorial review — fact verification, removal of machine-writing patterns, terminology and style consistency,…
View capability -
Editorial Evidence Architect
role · v0.1.0 · published, public-sanitizedOwns the structural, visual, and evidence architecture of Talomnia long-form public documents while product claims and publication remain governed elsewhere.
View capability -
Evidence Auditor
role · v0.1.5 · published, public-sanitizedThe role that judges whether checks and their outputs actually count as evidence.
View capability -
Fleet Orchestrator
role · v0.1.0 · published, public-sanitizedRuns a fleet of autonomous lanes: decides what each lane works on, observes every lane on a fixed cycle, and is answerable for the condition the lanes are working in as well as for what they produce.
View capability -
Knowledge Curator
role · v0.1.5 · published, public-sanitizedThe role that owns the lifecycle of artifacts in the Professional Knowledge Graph.
View capability -
Knowledge Base Librarian
role · v0.1.5 · published, public-sanitizedThe caretaker of institutional memory.
View capability -
Adversarial Peer Reviewer
role · v0.1.0 · published, public-sanitizedThe role that reviews an artifact the way an outsider with no stake in it would: isolated context, a different checkpoint from the author's, a mandatory floor of two substantive concerns or proof it…
View capability -
Lead Project Manager
role · v0.1.0 · published, public-sanitizedThe role that turns complex requirements into actionable, tracked tasks: detailed designs that carry their security design, implementation plans that carry rollback and validation, explicit…
View capability -
Research Analyst
role · v0.1.5 · published, public-sanitizedThe role that grounds work in the world outside the repository.
View capability -
Resolver Operator
role · v0.1.5 · published, public-sanitizedThe role that runs the resolution of a task intent into a Knowledge Contract: from a pinned repository snapshot through propose, validate, select, assemble and issue, with a frozen Resolution Receipt…
View capability -
QA and Security Lead
role · v0.1.5 · published, public-sanitizedThe verdict role at the end of implementation.
View capability -
Security Analyst
role · v0.1.5 · published, public-sanitizedThe adversarial-thinking role: it treats every feature as an attack surface and asks what can go wrong before an attacker does.
View capability -
Skill Creator
role · v0.1.0 · published, public-sanitizedThe role that closes named gaps in the framework: research before creation, audit before duplication, an explicit model assignment on everything it ships, quality criteria that make skills trigger…
View capability -
Site Reliability Engineer
role · v0.1.5 · published, public-sanitizedThe role that asks whether a system will survive production.
View capability -
Strategic Advisor
role · v0.1.0 · published, public-sanitizedThe role that asks whether the task is worth building before anyone builds it: value, risk and cost on every assessment, a cheaper alternative before any full plan, hard pushback on schema, API,…
View capability -
Platform QA Tester
role · v0.1.5 · published, public-sanitizedThe verification role: it finds out whether a change actually works, using the most efficient method the project supports.
View capability -
Content Writer
role · v0.1.5 · published, public-sanitizedThe voice of the project in prose: technical documentation, articles, social posts, research and business writing, native in English and Russian.
View capability -
ADR Set Acceptance Criteria
acceptance criterion · v0.1.5 · published, public-sanitizedAcceptance checklist for the set of architecture decision records covering technology stack, database and site analytics.
View capability -
Accessibility Acceptance Criteria
acceptance criterion · v0.1.6 · published, public-sanitizedFifteen binary accessibility criteria targeting WCAG 2.1 AA for every Talomnia surface, each paired with a check that can actually fail: measured token contrast in both themes, full keyboard paths…
View capability -
Design System Acceptance Criteria
acceptance criterion · v0.2.0 · published, public-sanitizedAcceptance checklist for the Talomnia design system, serving two consumers: the lane that builds the system and the lane that builds the site from it.
View capability -
Editorial Evidence Atlas Success Criteria
acceptance criterion · v0.2.0 · published, public-sanitizedBinary release criteria for semantic RU/EN White Paper editions, accessible source-backed figures, responsive editorial layout, performance budgets, exact deployment identity, rollback, and preserved…
View capability -
Knowledge Repository Acceptance Criteria
acceptance criterion · v0.1.3 · published, public-sanitizedAcceptance checklist for the private knowledge repository deliverable: the repository verifiably exists with private visibility, the folder structure covers all ten entity types, the artifact…
View capability -
Capability Discovery Acceptance Criteria
acceptance criterion · v0.1.3 · published, public-sanitizedThe gate no implementation lane may start before: acceptance criteria for the capability map.
View capability -
Project Repositories Acceptance Criteria
acceptance criterion · v0.1.3 · published, public-sanitizedAcceptance criteria for the three project repositories and the sanitization gate.
View capability -
Acceptance by Pull Request Decision
skill · v0.1.6 · published, public-sanitizedA procedure that ends every delivery in a recorded pull-request decision.
View capability -
Accessible Evidence Diagrams
skill · v0.1.0 · published, public-sanitizedRebuilds source-backed figures as typed semantic HTML with supplemental safe SVG, stable IDs, localized alternatives, visible long descriptions, machine provenance, and red-capable checks.
View capability -
Admissibility Check
skill · v0.1.5 · published, public-sanitizedA procedure that decides whether a candidate set may enter a Knowledge Contract by evaluating six compatibility conditions in full: eligibility, coverage, exclusion freedom, dependency closure,…
View capability -
Architecture Decision Record Authoring
skill · v0.1.5 · published, public-sanitizedA procedure for writing an Architecture Decision Record before implementation starts, so a decision is recorded rather than rationalized after the fact.
View capability -
AI Development Quality Discipline
skill · v0.1.5 · published, public-sanitizedFive working disciplines for AI-assisted development: decomposition into methods of at most fifty lines, tests before code with edge-only mocking, an approved architecture skeleton before…
View capability -
Context-Window Lifecycle
skill · v0.1.0 · published, public-sanitizedManages the context window of an orchestrated agent lane as a quality property rather than as capacity.
View capability -
Customer-Facing Service Copy
skill · v0.1.0 · published, public-sanitizedA method for authoring customer-facing service copy on commercial surfaces.
View capability -
Task Ledger Doctor
skill · v0.1.5 · published, public-sanitizedDiagnoses and migrates the framework's operational task files to a strict machine-parseable schema: thin one-line indexes, per-task description files with a closed twelve-key header, and canonical…
View capability -
Datarim Core System Rules
skill · v0.1.5 · published, public-sanitizedThe always-loaded core rulebook of the Datarim workflow: where state lives, how task identifiers are formed, why operational files stay machine-parseable one-line ledgers with a per-task description…
View capability -
Database Migration Execution
skill · v0.1.6 · published, public-sanitizedA procedure that brings a target database to the exact state of the committed migration chain.
View capability -
Deploy Broker Operation
skill · v0.1.6 · published, public-sanitizedA procedure for shipping a release through the deploy broker, the only channel allowed to mutate the host.
View capability -
Design Direction Exploration
skill · v0.1.0 · published, public-sanitizedProduces three to five materially distinct directions, compares them against one evidence-backed matrix, records dissent and rejection reasons, and freezes an independently reviewed selection by…
View capability -
Pre-Design Landscape Research
skill · v0.1.6 · published, public-sanitizedA method for grounding design work in verifiable external evidence before any visual decision is made.
View capability -
Four-Category Documentation Taxonomy
skill · v0.1.5 · published, public-sanitizedMandates the Diátaxis taxonomy for every managed repository and product site: documentation splits into exactly four categories by reader intent — tutorials, how-to, reference, explanation — through…
View capability -
Digest Pinning
skill · v0.1.5 · published, public-sanitizedA procedure that turns any reference into a closed, immutable pin.
View capability -
Explanatory Affordance
skill · v0.1.1 · published, public-sanitizedHow a Talomnia surface explains its own vocabulary at the point of use.
View capability -
Pre-Publication Fact Verification
skill · v0.1.5 · published, public-sanitizedVerifies a text before publication without rewriting it.
View capability -
Frontend Interface Quality Checklist
skill · v0.1.5 · published, public-sanitizedA defect-catching checklist for any change to HTML, CSS, templates, or visual components.
View capability -
Plain-Language Operator Recap
skill · v0.1.5 · published, public-sanitizedEnds each verification and archive stage with a recap a non-programmer can read: what was asked and done, what worked, what remains open, and what happens next — 150 to 400 words in a fixed…
View capability -
Pipeline Artifact Immutability Contract
skill · v0.1.5 · published, public-sanitizedThe contract that keeps pipeline artifacts honest: requirements, plans, design decisions, tests, checklists, and visual baselines must never be weakened to let a failing deliverable pass, and every…
View capability -
Server Fleet Operations Playbook
skill · v0.1.5 · published, public-sanitizedOperational patterns for running commands safely across a server fleet: host keys verified and mesh reachability checked before any batch, non-interactive fail-fast SSH, a one-server trial before…
View capability -
Long-Form Content Typesetting
skill · v0.1.0 · published, public-sanitizedDefines how authored prose becomes typeset HTML on a Talomnia surface, which until now nothing did: the closed inline subset a renderer converts, the heading-and-label discipline that keeps a…
View capability -
Motion Design
skill · v0.2.0 · published, public-sanitizedGoverns every motion on a Talomnia surface beyond the theme swap: the declared easing and duration, how staggering is bounded, how a reduced-motion request is honoured by removal rather than by…
View capability -
Nginx Version Compatibility Probe
skill · v0.1.5 · published, public-sanitizedA planning checklist for any task that edits nginx configuration.
View capability -
Node Release Bundle Assembly
skill · v0.1.6 · published, public-sanitizedA procedure that assembles a self-contained Node release bundle from a committed repository checkout with a frozen lockfile; any lockfile drift aborts the build.
View capability -
Browser QA Evidence Pass
skill · v0.1.5 · published, public-sanitizedA QA contract that adds real-browser evidence to frontend changes.
View capability -
Pre-Ledger Accounting Reconstruction
skill · v0.1.0 · published, public-sanitizedA procedure for restoring the accounting of work that happened before it was being metered, without inventing measurements.
View capability -
Structured External Research Workflow
skill · v0.1.5 · published, public-sanitizedA structured method for investigating external context before planning or during implementation.
View capability -
Resolution Receipt
skill · v0.1.5 · published, public-sanitizedA procedure that freezes an immutable receipt for every resolution, successful or not.
View capability -
Publication Sanitization Gate
skill · v0.1.5 · published, public-sanitizedTurns the sanitization rules into an automatic, blocking CI check on every public publication path.
View capability -
Shipped-Artifact Security Baseline
skill · v0.1.5 · published, public-sanitizedThe canonical security floor for shipped artifacts: eleven rule clusters covering shell and Python hygiene, secrets, supply chain, documentation treated as code, repo hygiene, CI gating, drift…
View capability -
Semantic Editorial Composition
skill · v0.1.0 · published, public-sanitizedBuilds deterministic locale-specific long-form documents from stable authored keys, with editorial rhythm and semantic rather than pixel parity.
View capability -
Bilingual SEO and Hreflang Discipline
skill · v0.1.5 · published, public-sanitizedHow to give a bilingual, path-prefixed site a correct search surface so the Russian and English trees never compete.
View capability -
Success Criterion Measurement
skill · v0.1.5 · published, public-sanitizedA procedure that decides a success criterion strictly from evidence.
View capability -
Root-Cause-First Debugging Method
skill · v0.1.5 · published, public-sanitizedA four-phase discipline that forbids proposing fixes before the root cause is understood.
View capability -
Technology Stack Selection Procedure
skill · v0.1.5 · published, public-sanitizedA selection method for technology stacks in new projects, services, and modules.
View capability -
Testing Discipline and False-Green Gates
skill · v0.1.5 · published, public-sanitizedThe testing contract for implementation and QA flows: a pyramid of mostly unit tests with fewer integration and end-to-end flows, plus a set of gates against false-green suites.
View capability -
Flicker-Free Theming and Preference Persistence
skill · v0.3.0 · published, public-sanitizedImplements dark and light theming and language persistence with no flash of the wrong theme at load.
View capability -
UI Source Selection
skill · v0.1.1 · published, public-sanitizedDecides, before a component is written, whether it should be taken from an existing trusted source, adapted from one, or authored here — and records the decision with the evidence that justified it.
View capability -
Native Shell Utility Recipes
skill · v0.1.5 · published, public-sanitizedAn index of native shell recipes for routine operations: dates and time zones, hashing and random values, encoding, text case conversion, validation, JSON and YAML handling, formatting, remote…
View capability -
Evidence-Backed Completion Gate
skill · v0.1.5 · published, public-sanitizedA gate that forbids claiming work complete, fixed, or passing without fresh verification evidence alongside the claim.
View capability -
Visual Asset Direction
skill · v0.1.0 · published, public-sanitizedInventories canonical assets and concepts, then records exactly one honest reuse/adapt/generate/reject decision per needed visual — preserving source revision, digest, license and provenance;…
View capability -
Visual Design Critique
skill · v0.2.0 · published, public-sanitizedHow an agent judges a rendered surface rather than a stylesheet, and does it the same way twice.
View capability