Jev Lint Repo
mizchi/jev-lint
A skill your agent uses when changing jev-lint ITSELF — editing src/, shipped rule suites under rules/<language/<id/, or recorded runs in docs/data/.
Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider.
Install System One
$ npx skills add magnus919/agent-skills --skill system-one -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install magnus919/agent-skills system-one --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/system-one .claude/skills/system-one && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "system-one" agent skill from https://github.com/magnus919/agent-skills/tree/main/system-one into .claude/skills/system-one/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-one", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/magnus919/agent-skills/tree/main/system-oneType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add magnus919/agent-skills --skill system-one -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install magnus919/agent-skills system-one --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/system-one .agents/skills/system-one && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "system-one" agent skill from https://github.com/magnus919/agent-skills/tree/main/system-one into .agents/skills/system-one/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-one", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add magnus919/agent-skills --skill system-one -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install magnus919/agent-skills system-one --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/system-one .cursor/skills/system-one && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "system-one" agent skill from https://github.com/magnus919/agent-skills/tree/main/system-one into .cursor/skills/system-one/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-one", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/magnus919/agent-skills.git --path system-one--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add magnus919/agent-skills --skill system-one -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install magnus919/agent-skills system-one --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/system-one .gemini/skills/system-one && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "system-one" agent skill from https://github.com/magnus919/agent-skills/tree/main/system-one into .gemini/skills/system-one/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-one", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install magnus919/agent-skills system-oneInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add magnus919/agent-skills --skill system-one -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/system-one .github/skills/system-one && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "system-one" agent skill from https://github.com/magnus919/agent-skills/tree/main/system-one into .github/skills/system-one/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-one", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add magnus919/agent-skills --skill system-one -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install magnus919/agent-skills system-one --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/system-one .opencode/skills/system-one && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "system-one" agent skill from https://github.com/magnus919/agent-skills/tree/main/system-one into .opencode/skills/system-one/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-one", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
system-one- GitHub stars
- 116
- Token cost
- ~3.7k tokens
- SKILL.md length
- 1,499 words
- Files
- 89 (incl. scripts, references)
- Skills in repo
- 130
- Repo updated
- First seen
- Licence
- MIT
At a glance
Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider.
- Works in 5 steps: Inspect the real application's state… → Fill templates/decision-contract.md:… → Open only the matching reference below.… → …
- Choice/Score/Noul judgments inside deterministic software
- SKILL.md covers Start here, Route by task, Cross-cutting limits and When not to use, plus 1 more section
- Calls python3
What it does
System One is an agent skill from magnus919/agent-skills. Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider. Use for Choice/Score/Noul judgments inside deterministic software, app-control loops, routing, ranking, guardrails, calibration, semantic code linting and post-edit feedback, DevOps decision support, confidence-based escalation, or private open-model inference. Do not use for syntactic/style linting, exact policy or authorization…
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 91 other files, including scripts and reference files (for example `README.md`, `evals/evals.json` and `examples/jev-atomic-assertion-screen.json`). Compatibility notes: Current provider/model documentation needs network access; local open-model operation needs a compatible runtime and model-weight storage.
It sits in Development, covering Linting and formatting and Performance reviews. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.
When your agent uses it
- Choice/Score/Noul judgments inside deterministic software
- App-control loops
- Semantic code linting and post-edit feedback
- DevOps decision support
Example prompts
- “/system-one”
Requirements
- Python 3
- Compatibility (from SKILL.md): Current provider/model documentation needs network access; local open-model operation needs a compatible runtime and model-weight storage.
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Inspect the real application's state source, action boundary, tests, and
- Fill templates/decision-contract.md: trusted state, question IDs/types,
- Open only the matching reference below. Keep exact question instructions,
- Validate response IDs, types, option sets, distributions, score rubric,
- Verify on representative held-out data and the actual delivery boundary;
What it can do on your machine
Read from SKILL.md and the folder at commit c545c2b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Current provider/model documentation needs network access; local open-model operation needs a compatible runtime and model-weight storage.
From compatibility in the SKILL.md frontmatter.
Context cost
System One loads about 3.7k tokens when it runs, and up to ~78k if it reads all its reference files. Until then it costs about 151 tokens; SKILL.md has 1,499 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from magnus919/agent-skills at commit c545c2b, republished under its MIT licence (© magnus919). 1,499 words, ~3,663 tokens.
Download SKILL.mdSave it as
.claude/skills/system-one/SKILL.md (or your agent's skills folder). This skill also uses 88 other files; get the full folder from GitHub.- name
- system-one
- description
- Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider. Use for Choice/Score/Noul judgments inside deterministic software, app-control loops, routing, ranking, guardrails, calibration, semantic code linting and post-edit feedback, DevOps decision support, confidence-based escalation, or private open-model inference. Do not use for syntactic/style linting, exact policy or authorization, open-ended generation, or generic LLM serving without a bounded decision contract.
- compatibility
- Current provider/model documentation needs network access; local open-model operation needs a compatible runtime and model-weight storage.
- license
- MIT
- metadata.author
- system-one contributors
- metadata.version
- 1.1
System One decision models
Use a model for a constrained judgment, not for permissions or side effects:
authorized state + trusted typed questions -> validated model answers
-> deterministic policy -> act / wait / review / abstain -> observed outcomeKeep hard business rules, authority checks, thresholds, action execution, confirmation, and rollback in code or human control. A legal response shape does not imply a correct judgment; a high probability is not permission.
Start here
- Inspect the real application's state source, action boundary, tests, and deployment before changing it. Preserve existing deterministic/no-key behavior unless explicitly changing it is in scope.
- Fill
templates/decision-contract.md: trusted state, question IDs/types, allowed answers, unknown/review lane, side effects, owner, deadlines, and rollback. For tool control, also usetemplates/action-control-contract.md. New to this model class? Start withreferences/worked-decision-pilot.mdto choose one bounded decision, then usereferences/concepts-and-patterns.mdfor primitive semantics and composition. - Open only the matching reference below. Keep exact question instructions,
criteria, state paths, and thresholds in trusted configuration, not
user-supplied state. IDs are for application code; TypeSafe documents that
Jev does not send question IDs to the model, so put complete judgment
meaning in each instruction. Other providers may have different contracts.
For question wording or candidate extraction, read
references/question-design.md. - Validate response IDs, types, option sets, distributions, score rubric, and finite values before policy code; record returned model/version and enforce the pinned deployment identity. Treat malformed, unavailable, stale, or low-evidence results as the specified fallback.
- Verify on representative held-out data and the actual delivery boundary; record provider/model, question/policy revision, outcome, and failure lane without raw secrets or unnecessary personal data.
Before expanding a cross-model battery, complete
templates/decision-battery-design-review.md and review a small varied pilot.
Define whether a test counts a distinct scenario, a question, or a request;
freeze the answer rubric, comparison contract, and timing conditions before
generating more cases. If those definitions or reviewer labels disagree, stop
expansion and revise the design. Keep benchmark outputs outside this skill's
tracked corpus unless publication is explicitly requested.
Route by task
| Task | Read next |
|---|---|
| Design questions, choose candidates, or extract values from source text | references/question-design.md; for broader application compositions, references/use-case-patterns.md |
| Hosted Jev API or SDK integration | references/jev.md; run scripts/decision_demo.py offline first |
| CLM typed decisions, candidate ranking, Qwen3 encoder, fine-tuning, or private serving | references/clm.md |
| Laya checkpoints, routing, language, CPU/GPU/MPS | references/laya.md |
| Fine-tune the English Laya checkpoint on labeled typed decisions | references/laya-fine-tuning.md |
| Native C++ Laya inference, CUDA/Vulkan, or Jev-compatible HTTP | references/laya-cpp.md |
| Local or private/VPC Laya service | references/laya-self-hosting.md, then references/hosting-and-troubleshooting.md |
| Skill suggestions with progressive disclosure and no-fit rejection | references/implementation-audit.md |
| Narration-to-media matching through captions or metadata; catalog answer/component selection | references/use-case-patterns.md |
| Browser/desktop/voice control, agent routing, ranking, guardrails, deadlines | references/use-case-patterns.md |
| Semantic code-lint rule design, local post-edit checks, graph scans, or feedback evaluation | references/semantic-lint-feedback.md; fill templates/semantic-lint-rule.md and templates/feedback-evaluation.md before a pilot |
| First System One pilot or worked evaluation of a decision, QA runner, or semantic CI gate | references/worked-decision-pilot.md |
| Learn from the 1,305-build field survey; identify implementation patterns and anti-patterns | references/field-patterns-and-antipatterns.md |
| Audit original browser, skill-router, supervisory, or moderation implementations | references/implementation-audit.md |
| Production QA step routing, cached replay, selector repair, or model substitution | references/qa-automation-pattern.md, then references/evaluation-and-calibration.md |
| DevOps telemetry routing, diagnostic test ranking, repair evidence, optional CI jobs, deployment transitions, or durable incident decisions | references/devops-decision-patterns.md and templates/decision-execution-record.md; operational procedures remain in SRE/QA/release and tool skills |
| Review the DevOps/escalation eval assertions and their satisfying, contradictory, or missing-evidence challenges | references/devops-escalation-eval-review.md |
| Confidence-based acceptance and escalation to a stronger judge | references/selective-judgment.md and templates/cascade-qualification.md |
| Probability, threshold, calibration, model comparison | references/evaluation-and-calibration.md and templates/benchmark-record.md |
| Design a matched comparison, qualify adapters, separate fixed-contract from model-adapted tracks, or assess equivalence | references/comparison-design.md and templates/benchmark-record.md |
| Compare singleton and batched request quality or calibration | references/request-shape-evaluation.md and templates/benchmark-record.md |
| Replace an LLM rubric judge, diagnose graded scale offsets, or test correlated judge errors | references/rubric-judge-research.md, then references/evaluation-and-calibration.md |
| Measure router ablations and full fallback economics | references/cascade-economics.md and templates/benchmark-record.md |
| Place a typed decision in a harness, define state/authority/recovery, or measure whole-task effects | harness-engineering and its System One placement guide and its offline round-trip examples; harness engineering owns the workflow boundary, while this skill owns typed questions, response validation, calibration, abstention, and model substitution |
| Implement the contract in PydanticAI, LangGraph, or LangChain | Use the matching framework skill for its integration seam; keep this skill's typed model contract and calibration rules authoritative |
| Determine whether a decision model improves an agent harness | agent-evals-and-observability for paired end-to-end tasks, trajectories, side effects, and cost/latency; keep this skill's model-level contract and calibration checks |
| Design or run a portable v1 label battery or provisional v2 cross-domain Choice/Noul/Score battery | references/decision-battery.md and templates/decision-battery-design-review.md; run scripts/decision_battery.py only after the pilot review |
| Synthetic QA pilot for Jev (failure triage, extra-test choice, semantic grading) | references/qa-pilot.md; run scripts/jev_qa_pilot.py offline first |
| Paired-eval semantic assertion audit in CI | references/qa-pilot.md, then scripts/jev_eval_audit.py; treat its verdicts as advisory and preserve exact grader results |
| Reproduce, operate, diagnose, or roll back this repository's Jev CI deployment | references/jev-ci-reference-deployment.md; inspect the current workflow before changing secrets or jobs |
| Screen Jev's advisory eval judgments against real outputs | references/qa-pilot.md and references/evaluation-and-calibration.md; use scripts/jev_eval_calibration.py for a blind packet, then independent labels or scripts/jev_teacher_label.py for model-teacher pseudo-labels |
| Select among Jev, Laya, CLM, GLiNER2.5-Decide, or another candidate | references/ecosystem-radar.md; then the selected model reference |
| Screen newer open typed-decision candidates from primary evidence | references/open-decision-candidates.md; then use references/comparison-design.md before benchmarking |
| Experimental Strands Decider local inference, pointer-head semantics, context limits, or source-only vision | references/strands-decider.md; qualify the native adapter before comparison; eval changes in references/strands-eval-review.md |
| Fastino GLiNER2.5-Decide local classification | references/gliner25-decide.md |
| Fine-tune GLiNER2 for Decide-style classification | references/gliner25-decide-fine-tuning.md |
| Failure, latency, device fallback, upgrade, rollback | references/hosting-and-troubleshooting.md |
For a hosted provider integration, refresh the provider's live documentation
index, then read the current API or selected SDK reference and the nearest
cookbook before coding. references/jev.md contains the Jev-specific route and
fallback procedure; its endpoint and contract details are a dated snapshot.
Run python3 scripts/systemone_probe.py --request examples/request.json for an offline
contract check. Add --live only when the user has authorized transmitting
that state and incurring cost. For local Laya, scripts/laya_service.py
requires a pinned local model directory and a runtime secret; it is a private
reference adapter, not a public Internet service.
Show full SKILL.md (532 more words)Show less
Cross-cutting limits
- Jev is managed/API-only; do not invent a self-hosted Jev weight download.
- Laya, CLM, and Jev can share a typed application interface, but not assumed thresholds, calibration, latency, language behavior, or model quality.
- Before enabling Laya caller traffic, keep ingress private and authenticated;
define finite, application-specific caps for request bytes, question count,
options per Choice, concurrency, queue wait, and total deadline. Readiness waits
for the pinned model, tokenizer, actual device, and any calibration artifact the
application uses. The bundled adapter's
/readyzchecks device residency only; extend it to cover every required artifact before routing production traffic. - For large Laya Choice sets, check tokenized labels against the head-token
budget, verifying coverage and truncation; an option-count transport cap does
not prove quality. If shortlisting, measure recall and treat probabilities as
conditional on exactly the retained candidate set. Prefer
other,unknown, or review when labels are not exhaustive. Seereferences/laya.md. - Independent questions may share one call, but test the exact batched request shape on frozen cases. Dependent questions need another call when the first answer changes their state or candidate set.
- Predeclare whether a comparison holds decision semantics fixed or compares
separately adapted model-plus-adapter systems. Qualify adapter polarity,
schema, and overflow behavior before scoring; a compatible response shape is
not evidence of semantic parity. Record the protocol in
templates/benchmark-record.md. - Validate error discrimination separately from probability calibration before confidence-based escalation. Freeze the route on selection data, then test absolute accepted risk and fallback rescue/regression on untouched units. Unsupported evidence or expired state cannot be overridden by confidence.
- A fallback judge or multi-provider agreement is not independent correctness
evidence. Measure shared errors and held-out rescue/regression before claiming
cascade quality gains; see
references/rubric-judge-research.md. - A semantic lint result is a model judgment, not proof that a code rule is satisfied. Keep syntax/schema checks deterministic, semantic findings reviewable, and gates advisory until independent grouped holdouts measure false passes, false blocks, abstention, drift, and complete task cost.
- A model cannot replace exact arithmetic, provenance, eligibility, safety reflexes, or irreversible approval. A text-generating model may be a separate bounded stage after a typed route, not an implicit source of authority.
Finish an integration only when its contract, held-out evaluation, failure path, deployment/readiness check, and rollback record exist. For diagnosis, stop after the smallest evidence identifies the boundary and one recheck verifies a fix, or after three non-converging passes with evidence for the owner. Do not generalize from a single demo or vendor benchmark.
When not to use
Use ml-engineering for general training strategy; docker-compose or
kubernetes for their serving infrastructure; ai-governance for
organization-wide authority design. Use a generative-model skill for prose,
open-ended planning, or long reasoning without a typed-decision contract.
Framework handoff
The harness provides authorized, versioned state, candidate/route bounds, task goal, deadline, and the outcome to verify. This skill consumes that evidence under a pinned question/rubric/model contract and returns validated typed answers, model identity/revision, and an explicit unknown or failure lane. PydanticAI, LangGraph, and LangChain carry and route the result through their own documented seams; deterministic policy decides the next workflow step. The harness returns observed effects and accepted-task outcomes for end-to-end evaluation. Keep question/model calibration evidence inside this skill, and use harness-engineering for placement, authority, recovery, and whole-task evidence.
© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 88 other files (scripts, references) in system-one of magnus919/agent-skills.
- SKILL.md
- .dockerignore
- .gitignore
- README.md
- evals/evals.json
- examples/batch-request-shape.synthetic.jsonl
- examples/cascade.synthetic.jsonl
- examples/decision-battery-v1.jsonl
- examples/decision-battery-v2.jsonl
- examples/decision-qualification.synthetic.jsonl
- examples/jev-atomic-assertion-screen.json
- examples/jev-ci-coverage.synthetic.json
- examples/jev-eval-benchmark.json
- examples/jev-procedure-conflict.synthetic.json
- examples/noul.synthetic.jsonl
- examples/request.json
- examples/response.synthetic.json
- references/cascade-economics.md
- … and 71 more
Open the folder on GitHubat commit c545c2b
Compare with similar skills
System One next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| System One this skillmagnus919/agent-skills | 116 | — | ~3.7k | Automated safety check: Pass | MIT | |
| Jev Lint Repomizchi/jev-lint | 119 | — | ~942 | Automated safety check: Pass | MIT | |
| Authoring Skillsfriday-platform/friday-studio | 104 | — | ~2.4k | Automated safety check: Pass | Custom licence | |
| Gatingoaustegard/claude-skills | 150 | — | ~3.1k | Automated safety check: Pass | MIT | |
| LobeHub Alint Rule Set Maintenancelobehub/lobehub | 83k | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Cxas Agent FoundryGoogleCloudPlatform/cxas-scrapi | 107 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Authoring Skills
friday-platform/friday-studio
Authors new agent skills that follow the Anthropic + agentskills.io specification.
Gating
oaustegard/claude-skills
Build and audit deterministic verification gates — a check that blocks a pipeline and can be shown to go red.
LobeHub Alint Rule Set Maintenance
lobehub/lobehub
Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.
Cxas Agent Foundry
GoogleCloudPlatform/cxas-scrapi
End-to-end GECX/CXAS/CES conversational agent lifecycle -- build agents from requirements (PRD-to-agent), create and run evals (goldens, simulations, tool tests, callback tests), debug failures, and…
AI Index
mizchi/skills
Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English.
More from magnus919/agent-skills
All 130 skills in this repoArtifact Pyramids
magnus919/agent-skills
Organize durable agent research outputs as summaries, analysis, and evidence dossiers.
Ascii City Engine
magnus919/agent-skills
Build portable, first-person colored ASCII city engines and small GIS-derived city packs.
Color Management
magnus919/agent-skills
Manage color workflows with ICC profiles, working spaces, gamut mapping, and color science.
Data Scientist
magnus919/agent-skills
A skill your agent uses for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research…
Docker Compose
magnus919/agent-skills
Use Docker Compose to define, run, debug, and harden multi-container applications.
Fpga Development
magnus919/agent-skills
Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence.
Related
Categories
Questions about System One
What does System One do?
Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider. System One is an agent skill from magnus919/agent-skills. Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider.
When should I use System One?
System One fits situations like: choice/Score/Noul judgments inside deterministic software; app-control loops; semantic code linting and post-edit feedback; devOps decision support.
How do I install System One in Claude Code?
Run `npx skills add magnus919/agent-skills --skill system-one -a claude-code`. Or copy the skill folder (system-one in magnus919/agent-skills) into .claude/skills/system-one in your project. Claude Code loads it when a task matches its description.
How do I install System One in Codex?
Run `npx skills add magnus919/agent-skills --skill system-one -a codex`. Or copy the skill folder (system-one in magnus919/agent-skills) into .agents/skills/system-one in your project. Codex loads it when a task matches its description.
Can I use System One in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add magnus919/agent-skills --skill system-one -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/system-one, .gemini/skills/system-one, .github/skills/system-one and .opencode/skills/system-one in your project.
What does System One need to run?
Going by SKILL.md and its folder, System One needs the command-line tools its instructions call (python3). Our summary lists: Python 3. Compatibility (from SKILL.md): Current provider/model documentation needs network access; local open-model operation needs a compatible runtime and model-weight storage..
Does System One access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is System One safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does System One use?
System One is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does System One use?
About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 74k tokens, read only when the agent opens those files.
What are the alternatives to System One?
Skills that share tags, products or a category with System One: Jev Lint Repo (mizchi/jev-lint, 119 stars), Authoring Skills (friday-platform/friday-studio, 104 stars), Gating (oaustegard/claude-skills, 150 stars) and LobeHub Alint Rule Set Maintenance (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains System One?
magnus919 (a GitHub user) maintains it in magnus919/agent-skills, which has 116 GitHub stars. The repository holds 130 skills in this directory. The repository was last updated on October 8, 2026.
Source: magnus919/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.