YOU ASK
“Fix it. Test it. Prove it.”
A normal request. No skill IDs to memorize.
OPEN SKILL INFRASTRUCTURE · v0.1
Give every task
the right skills.
Find reusable procedures for your AI agent. SolKraft now routes by semantic fit and machine-readable skill contracts: inputs, effects, capability requirements, trust, typed dataflow, and verification evidence—while execution stays with your host agent.
Read-only by design / Contract-aware routing / REST + MCP + CLI / Open source
ONE REQUEST. A USEFUL METHOD.ILLUSTRATION
SOLKRAFT ROUTES
The right skills, in order.
Investigate → build → test. Load only what helps.
YOUR AGENT ACTS
Real work. Checked results.
The host applies the method using its own tools.
WHAT CHANGED · CONTRACT ARCHITECTURE
Skills are no longer opaque superpowers.
SolKraft now treats each skill as a compact, inspectable capability contract. The router can reason about what a skill needs, what it may affect, what authority a host would need, how skills connect through typed inputs and outputs, and what evidence would verify success—before loading the full procedure.
Inputs, outputs, effects, verification.
Skills can carry typed contract.yaml sidecars with namespaced effects, capability/resource requirements, declarative checks, digests, provenance, and trust state.
Admissibility before composition.
Known-inadmissible skills are filtered before they shape a route. Whole routes are validated, broken dependencies are exposed, and one bounded repair pass can substitute a safe alternative.
Capabilities can compose by type.
Typed outputs can satisfy downstream inputs. A unique compatible producer can be inserted automatically; missing or ambiguous inputs remain visible instead of being guessed.
Verification is evidence-bound.
Execution evidence is bound to exact contract and SKILL.md digests. Trust comes from external digest-bound review, never from a skill declaring itself trusted.
REST, MCP, CLI, OpenAPI.
Contract metadata is available over REST, MCP and CLI. Portable import/export and conservative MCP/OpenAPI adapters carry declarations only—never authority.
Pre-build a skill before the PR.
Contributors can run the same reusable full gate locally or from GitHub before opening a PR, including the 100,000-route regression, packaging, installed MCP checks, contract indexing, and hardening receipts.
Hardened public defaults Opaque skills fail closed over REST, MCP, and CLI.
Lazy by design The route/index hot path still avoids loading full skill bodies.
Execution stays external
execution_authorized remains false.
RECORDED CONTRACT VALIDATION · HISTORICAL REPLAY
100,000 contract checks.
Watch the historical replay.
This is a recorded replay of the historical 100k contract/hardening run. It is not the new broad-semantic proof and does not run tests in your browser.
Historical contract replay Retained to show hardened policy, blocking, boundaries, and advisory execution behavior.
New semantic proof 1,000 distinct prompts per skill + 100,000 multi-skill compositions + 100,000 stability executions.
Proof gate New semantic results are only treated as proven when the aggregate CI receipt passes its thresholds.
FROM A REQUEST TO USEFUL WORK
Your agent does the work. SolKraft supplies the method.
A skill is a reusable procedure with instructions and supporting resources. The solforge skill contains the orchestration and semantic routing machinery; it is also a node in the selection graph. Specialist skills supply the methods for research, building, testing, writing, and engineering. Capability-preserving execution supplies the adaptive execution loop: frame the outcome, map dependencies, schedule safe work, preserve evidence, repair failures, and verify completion. It is an instruction-based execution layer, not a hidden Python scheduler.
FOLLOW THE REQUEST · A WALKTHROUGH, NOT A LIVE JOB
YOUR INTENT
Describe the outcome.
“Inspect the codebase, fix the bug, add a regression test, and verify the release build.”
SEMANTIC ROUTING
Turn language into a route.
SolForge reads actions, context, and exclusions. The selection graph supplies workflow relationships.
SELECTED PROCEDURES
Choose methods that matter.
Codebase investigation → software build → software test. The agent checks the route against your actual intent.
CONTEXT ON DEMAND
Retrieve just the next skill.
MCP or REST returns the selected instructions and needed references. The entire catalog stays out of the conversation.
CAPABILITY-PRESERVING EXECUTION
Your agent does the work.
The host preserves requirements, follows dependencies, applies the specialist procedure, and adapts when evidence changes.
VERIFICATION
Show what actually holds.
The agent runs relevant checks, repairs failures, and reports evidence and remaining limits. SolKraft does not certify the result.
Discover a procedure
Browse the paginated catalog or search names and descriptions. Inspect a skill, then copy its instructions into your agent. This works here without an account or API key.
Understand the route
Try the worked example below. For your own request, connect a SolKraft API and use Compose a route. The result shows stages, selected skills, reasons, and unresolved work.
Execute with preserved capability
Copy instructions manually, or let an MCP or REST client retrieve them. Your agent reads the selected procedures, uses its own tools, and verifies the requested result.
TRY IT · NO CONNECTION NEEDED
A bug fix with a release check
Inspect the codebase, fix the bug, add a regression test, and verify the release build. Do not deploy or publish anything.
See the actual parser output generated from this request, inspect its selected procedures, and copy the request for your agent.
How the semantic parser and graph actually work
Identify the capability
The deterministic parser still understands scoped rules, concept aliases, domain context, exclusions, quoted instructions, and completed or deferred work. It also matches published capability identity using distinctive tokens and unique capability signatures, preserving a high-confidence whole-request identity across multi-stage decomposition.
Filter, compose, validate
Hardened routing prefilters candidates through the ContractIndex before composition. The composer orders the requested stages, then whole-route validation checks contract admissibility, dependencies, and typed input/output dataflow. Bounded repair can recompose or repair a broken route instead of silently accepting an invalid chain.
Keep the limits visible
This is deterministic routing, not an LLM call. Scores are relative rankings, not probability estimates. Contract filtering, whole-route validation, and typed dataflow repair improve selection safety; a proposed route still never grants permission or executes a job.
Catalog search on this static site is keyword filtering. Custom semantic composition runs in your connected server. The example is real, precomputed parser output and is labelled separately from a live response.
Read the orchestration skill ↗ · Set up REST or MCP ↗PUT IT TO WORK
Install once. Ask normally.
Using Codex? Install the private plugin included with SolKraft. It lets Codex find useful skills, read their instructions, and use them while helping with your work. Install it directly from our GitHub repository using the steps below. You do not need Render, a hosted API, or a SolKraft API key.
Install the included Codex plugin
python -m pip install "git+https://github.com/halthinks/SolKraft.git"
codex plugin marketplace add halthinks/SolKraft --sparse .agents/plugins --sparse plugins/solkraft
codex plugin add solkraft@solkraftYou need Python 3.11 or newer, Git, and Codex with plugin support. Run these commands in your terminal. The first installs the skill library; the next two add our GitHub repository to Codex and install its private plugin. Start Codex from the same terminal, then open a new chat. Do not search the public plugin directory for SolKraft.
Installation and troubleshooting ↗Connect from another app or computer
Host SolKraft on Render when you want another app or agent to connect to SolKraft over the internet. The included Codex plugin runs locally and does not need this.
Direct ChatGPT connection has not been tested. To use a skill in ChatGPT, open it in Explore, copy its instructions, and paste them into your chat.
Show me the hosting steps“Fix this bug and test it.”
The agent searches or routes the request, retrieves useful procedures, then edits and tests with its existing tools. For a release gate, pass that context so “draft PR” routes to software testing.
This page is an explorer and setup console. It does not run your repository or claim to have fixed anything.
Download the plugin ZIP ↓How it compares with other projects
skills.sh focuses on discovering and installing skills. Superpowers supplies an opinionated development methodology and agent workflows. SolKraft combines a multi-domain catalog, deterministic compound-request routing, inspectable relationships, and selective retrieval through REST and MCP. These approaches can coexist; there is no measured claim here that SolKraft beats either project.
FROM ZERO TO CONNECTED
Pick your path.
See every connection.
Explore the steps, watch the signal move, and copy the settings you need. These are illustrated instructions; only the console’s Connect button makes a real API connection.
ILLUSTRATED GUIDE
WHAT SHOULD I USE?
Plugin for Codex. MCP for agents. API for apps.
The included plugin is the easiest way to use SolKraft in Codex. The API and MCP let other software use the same skill library. The plugin already uses MCP behind the scenes.
Install the included plugin
The plugin sets up SolKraft’s tools and tells Codex when they are useful. Codex can find skills, read their instructions, and apply them while working on your task.
Install the Python package and plugin on your computer. You do not need Render or a SolKraft API key.
Show me the plugin stepsUse MCP
MCP is a standard way for an AI agent to discover and call tools. SolKraft’s tools let the agent search for skills, choose useful procedures, and retrieve their instructions.
The local Codex plugin sets this connection up for you. Other agents need their own MCP setup. To connect to a SolKraft server over the internet, give your agent the server’s HTTPS /mcp/ address and private API key.
Show me the agent connection stepsUse the API
The API lets your website, app, or script ask SolKraft for skills through ordinary web requests. You can build a skill browser, retrieve instructions, or send a task to /v1/route to get suggested skills.
This website uses the API when you connect a server and compose a route for your own request.
Show me the API stepsHost on Render
Render hosts your SolKraft server so apps and agents on other computers can connect over the internet. That one service provides both the API and remote MCP connection.
Choose this when another app or agent needs to connect over the internet. The local Codex plugin runs without it.
Show me the hosting stepsWhat happens when I ask for help?
Say: “Find this bug, fix it, and test the result.” With the plugin installed, Codex can ask SolKraft for investigation, implementation, and testing skills through MCP. SolKraft returns the instructions. Codex reads them, edits your project, runs tests, and explains the result.
SolKraft supplies the methods. Your agent does the work. You do not need to set up the plugin, API, and MCP separately. For local Codex use, install the included plugin and its required Python package.
YOUR APIConnect to a SolKraft serverOptional · enables custom routing · your key stays in this tab
THE WORKSPACE
What are you working on?
Connect to load catalog
POPULAR SKILLSSELECT TO INSPECT
✳Your skill catalog is ready when you are.
The bundled catalog loads automatically. An API connection is optional.
ADVISORY ROUTING
Describe the outcome. Get a sequence.
Connect your API to compose a custom request, or load the worked example without connecting. Select a suggested skill to read and copy its procedure.
↗
Custom requests require a connected API. The worked example is available without one.
WORKFLOW RELATIONSHIPS
See how skills connect.
Loading graph…
BUILT FOR AGENTS
Small context.
Full capability.
Search compact descriptions first. Pull the full instructions only when a skill earns its place in the workflow.
Read the agent guide ↗ONE INTERFACE
REST for apps.
MCP for agents.
One catalog serves a clean API and seven read-only MCP tools, including contract metadata and index inspection. Routing never grants execution authority.
Connect your client ↗PROJECT STATUS COMMUNITY BUILT
Early, open,
ready to shape.
Bring a skill, a bug report, or a better idea for how agents find their tools.
Get support ↗$ solkraft --what-changed
- Added machine-readable
contract.yamlskill contracts with typed inputs/outputs, namespaced effects, capability/resource requirements, verification checks, provenance, and digests. - Added explicit contract states: declared, legacy, opaque, unsupported, invalid.
- Changed routing so inadmissible skills are filtered before composition instead of being deleted afterward.
- Added whole-route validation, blocked/partially-blocked route states, dependency-break detection, and bounded safe repair.
- Added typed dataflow composition so skill outputs can satisfy downstream inputs.
- Added capability/resource grants instead of relying on the old scalar authorization ladder.
- Removed old
AUTH_ORDERenforcement for Contract v1 skills. - Removed the old post-hoc
apply_contracts()/violates()filtering path. - Added declarative verification over structured execution evidence.
- Added execution states: executed-unverified, verified, verification-failed.
- Added digest-bound trust so a skill cannot simply declare itself trusted.
- Added trust states including bundled-reviewed, signed, operator-trusted, local-unreviewed, legacy-inferred, opaque, invalid.
- Added deterministic route and verification audit receipts.
- Added a defined sandbox boundary while keeping SolKraft core non-executing.
- Migrated 111 safe legacy skills to inferred Contract v1 sidecars while keeping them explicitly legacy-inferred.
- Left 10 consequential legacy skills manual-only rather than fabricating safe contracts.
- Added a compact ContractIndex for effects, capabilities, inputs, outputs, trust, digests, caching, and incremental refresh.
- Added REST contract endpoints for contract metadata, schema, validation, filtering, import, and export.
- Added MCP tools:
get_skill_contractandget_contract_index. - Added read-only/idempotent MCP annotations.
- Added CLI commands for contract init, validate, lint, show, schema, migrate, export, and import.
- Added conservative MCP and OpenAPI metadata adapters that import declarations without granting trust or authority.
- Added portable Contract v1 import/export with unknown effects failing closed.
- Changed REST, MCP, and CLI routing to hardened defaults so opaque skills fail closed.
- Kept the Python library backward-compatible unless a stricter policy is explicitly requested.
- Added one reusable CI pipeline for normal PRs and pre-PR skill contribution validation.
- Added local/pre-PR evidence bundles with receipts, routing results, wheel/plugin artifacts, hashes, and contract-index evidence.
- Added contract schema/index/hardening CI receipts.
- Added the advanced 100,000-request routing benchmark.
- Expanded benchmark coverage from 25 ask families to 100 ask families per skill.
- Added adversarial near-neighbor confusion, ambiguity, compound context, and capability-disambiguation cases.
- Added a capability-identity matcher using published descriptions, distinctive tokens, and unique description signatures.
- Changed routing precedence so high-confidence whole-request capability identity is preserved across multi-stage decomposition.
- Final local acceptance: 100,000 / 100,000 passed.
- Eligible target recall: 64,158 / 64,158 — 100%.
- Hardened blocking: 30,062 / 30,062 — 100%.
- Consequential boundary: 5,780 / 5,780 — 100%.
execution_authorized:falseheld for 100,000 / 100,000 requests.- Added a durable local validation receipt and updated
VALIDATION.md. - Added the public Recorded Validation · Reenactment module for the 100k result.
- Added a Contributors page that recognizes community impact beyond pull requests, with Cozy (@Cozy2054934) as Contributor 001 for high-impact executable skill-contract idea work.
- Added a public 1–5 star contributor rating rubric and a guided contributor nomination form for code and non-code community impact.
- Added contributor badges, a public nominations archive, a visual README hero, and a contributions showcase for high-level community impact.
- Added interactive showcase filters and a public contributor badge legend covering all five recognition levels and impact tags.
- Added text-first contributor profile cards to the Contributions Showcase with earned badges, contribution areas, impact summaries, and links to public work—without profile images.
[status] contract-aware routing hardened · validation 100.000% · execution remains external