Diesel Guard
ayarotsky/diesel-guard
Lints Diesel and SQLx Postgres migrations for unsafe schema changes that lock tables or cause downtime, and authors custom Rhai checks.
Design or audit formal Paro performance claims: release acceptance, cross-engine parity, model calibration certification or non-inferiority.
Install Paro Evidence
$ npx skills add zunor/paro --skill paro-evidence -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zunor/paro paro-evidence --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/zunor/paro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/paro-evidence .claude/skills/paro-evidence && 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 "paro-evidence" agent skill from https://github.com/zunor/paro/tree/main/.agents/skills/paro-evidence into .claude/skills/paro-evidence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paro-evidence", 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/zunor/paro/tree/main/.agents/skills/paro-evidenceType 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 zunor/paro --skill paro-evidence -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zunor/paro paro-evidence --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zunor/paro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/paro-evidence .agents/skills/paro-evidence && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "paro-evidence" agent skill from https://github.com/zunor/paro/tree/main/.agents/skills/paro-evidence into .agents/skills/paro-evidence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paro-evidence", 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 zunor/paro --skill paro-evidence -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zunor/paro paro-evidence --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zunor/paro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/paro-evidence .cursor/skills/paro-evidence && 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 "paro-evidence" agent skill from https://github.com/zunor/paro/tree/main/.agents/skills/paro-evidence into .cursor/skills/paro-evidence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paro-evidence", 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/zunor/paro.git --path .agents/skills/paro-evidence--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 zunor/paro --skill paro-evidence -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zunor/paro paro-evidence --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zunor/paro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/paro-evidence .gemini/skills/paro-evidence && 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 "paro-evidence" agent skill from https://github.com/zunor/paro/tree/main/.agents/skills/paro-evidence into .gemini/skills/paro-evidence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paro-evidence", 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 zunor/paro paro-evidenceInstalls 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 zunor/paro --skill paro-evidence -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zunor/paro.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/paro-evidence .github/skills/paro-evidence && 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 "paro-evidence" agent skill from https://github.com/zunor/paro/tree/main/.agents/skills/paro-evidence into .github/skills/paro-evidence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paro-evidence", 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 zunor/paro --skill paro-evidence -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zunor/paro paro-evidence --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zunor/paro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/paro-evidence .opencode/skills/paro-evidence && 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 "paro-evidence" agent skill from https://github.com/zunor/paro/tree/main/.agents/skills/paro-evidence into .opencode/skills/paro-evidence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paro-evidence", 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
paro-evidence- GitHub stars
- 105
- Token cost
- ~1k tokens
- SKILL.md length
- 465 words
- Files
- 2
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Design or audit formal Paro performance claims: release acceptance, cross-engine parity, model calibration certification or non-inferiority.
- Works in 5 steps: Inspect the selected checkout and… → Pin source/dirty content, binary/build,… → Use maintained collectors with… → …
- Tasks that involve Performance reviews
- SKILL.md covers Register, collect, decide, Comparison validity and Bounded local evidence, small…
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Paro Evidence is an agent skill from zunor/paro. Design or audit formal Paro performance claims: release acceptance, cross-engine parity, model calibration certification or non-inferiority. Not for routine exploration; use paro-benchmark there.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Databases, covering Performance reviews and Vector databases. It works with SQL, PostgreSQL and Rust. The repository describes itself as: An AI-native multi-model database unifying SQL, vector, full-text, graph, and sandboxed Python — for transactional, analytical, and agent workloads. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Performance reviews
- Tasks that involve Vector databases
Example prompts
- “/paro-evidence”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Inspect the selected checkout and existing evidence. Before confirmatory
- Pin source/dirty content, binary/build, harness, SQL/schema/data/metadata,
- Use maintained collectors with balanced/interleaved blocks. Treat the fresh
- Validate complete types, multiplicities and required ordering outside timing.
- Evaluate the registered rule, including uncertainty/tails/coverage. A small
What it can do on your machine
Read from SKILL.md and the folder at commit 4afe117. 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
No scripts in the folder and no shell commands in SKILL.md.
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.
Context cost
Paro Evidence loads about 1k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 465 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from zunor/paro at commit 4afe117, republished under its Apache-2.0 licence (© zunor). 465 words, ~1,027 tokens.
Download SKILL.mdSave it as
.claude/skills/paro-evidence/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- paro-evidence
- description
- Design or audit formal Paro performance claims: release acceptance, cross-engine parity, model calibration certification or non-inferiority. Not for routine exploration; use paro-benchmark there.
Paro formal evidence
Daily iteration uses paro-benchmark. Use this workflow only for a requested formal claim or its audit. Review-only work does not authorize new runs. Never bless results or evolve a policy here.
Register, collect, decide
- Inspect the selected checkout and existing evidence. Before confirmatory sampling, version a short registration: hypothesis/intervention, arms, independent sampling unit, sample size/power, numeric thresholds, exclusions, uncertainty, coverage/held-out rules, resources and finite storage budget. Existing pilots cannot be retrospectively preregistered.
- Pin source/dirty content, binary/build, harness, SQL/schema/data/metadata, protocol, cache regime, DOP/memory and actual verification/observers. Follow declared competitor baseline: requirements constrain the version; the registration also identifies actual native binaries/extensions/settings. Upgrades create a new comparison.
- Use maintained collectors with balanced/interleaved blocks. Treat the fresh process/block as the independent unit when appropriate, not each repeated warm timing. Normal measurements and diagnostic captures remain separate.
- Validate complete types, multiplicities and required ordering outside timing. Keep every failure, retry, valid slow sample and exclusion. Explicitly bounded independent numerical certificates are not strict equality.
- Evaluate the registered rule, including uncertainty/tails/coverage. A small median alone is not certification. Report missing evidence or confounding as Uncovered/Incomparable/NotCertified, not zero or an invented receipt.
Comparison validity
- Do not infer causal speedups from unrelated report ratios or sums/differences of cohort medians. A decomposition needs direct same-lifecycle observations.
- Match inputs, admitted plan/resources, node/port/phase and units. Equal plan fingerprints locate artifacts; they are not semantic equivalence proofs. A diagnostic mismatch blocks joint attribution, not preservation of valid time.
- Model comparisons must share an applicable objective/fact/resource context. A partial order has incomparable candidates: rank correlation is descriptive, not a pruning proof. Use independent small-region enumeration, measured dominance violations and selection regret for the decisions actually made.
- Changing a threshold/exclusion after seeing outcomes requires a disclosed amendment and fresh confirmation where it changes the decision.
Show full SKILL.md (165 more words)Show less
Bounded local evidence, small durable decisions
Keep raw runs in ignored benchmark/runs/<run-id>/ or a declared external root,
not in Git. Share campaign identities, retain samples/receipts per query/arm
cell and reference each bounded compile capture once. Use the actual typed
RunOutput/validator limits; don't duplicate a capacity formula in prose.
Register a finite total budget and stop collection when exhausted; don't
discard slow samples or gzip an oversized event stream to pass a limit.
Preserve the complete raw run through review. If long-term reproducibility needs retention, explicitly name an approved artifact location, checksum and retention owner; without retained raw data, a historical decision is not a currently re-auditable certification. Git normally gets at most a page of conclusion/registration with identities, uncertainty, commands and limitations. Correctness fixtures belong in maintained tests/corpora, not historical reports.
Stop confirmatory collection on result errors, identity drift, uncontrolled interference or missing required evidence. Report partial results honestly. Neither this workflow nor a successful check authorizes baseline changes, history rewriting, automatic deletion, or publication.
© zunor, Apache-2.0. 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 1 other file in .agents/skills/paro-evidence of zunor/paro.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 4afe117
Compare with similar skills
Paro Evidence 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 |
|---|---|---|---|---|---|---|
| Paro Evidence this skillzunor/paro | 105 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Diesel Guardayarotsky/diesel-guard | 121 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Querying Tempotempoxyz/tidx | 108 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Neon Postgresneondatabase/agent-skills | 100 | — | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Ron Databasebionic-gpt/bionic-gpt | 2.4k | — | ~721 | Automated safety check: Pass | Apache-2.0 | |
| Rust On Nailsbionic-gpt/bionic-gpt | 2.4k | — | ~706 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Querying Tempo
tempoxyz/tidx
Query indexed Tempo chain data via tidx HTTP API and CLI. An agent skill from tempoxyz/tidx.
- Official
Neon Postgres
neondatabase/agent-skills
Guides and best practices for working with Lakebase Postgres on Neon: connections, pooled vs direct, schema migrations, branching, autoscaling, scale-to-zero, instant restore, read replicas, IP…
Ron Database
bionic-gpt/bionic-gpt
Manage PostgreSQL migrations, typed SQL queries, generated Rust bindings, and database authorization in Rust on Nails applications.
Rust On Nails
bionic-gpt/bionic-gpt
Design Rust on Nails applications and cross-layer features using Axum, server-rendered Dioxus, PostgreSQL, and typed SQL.
Golem Add Postgres Rust
golemcloud/golem
Using golem:rdbms/postgres from a Rust Golem agent. An agent skill from golemcloud/golem.
More from zunor/paro
Paro Optimizer
zunor/paro
Design, refactor and diagnose Paro's staged optimizer, using EXPLAIN COMPILE for planning and EXPLAIN ANALYZE for execution.
Paro Benchmark
zunor/paro
Run Paro engineering performance gates and exploratory cold/warm, cross-engine or operator comparisons.
Related
Works with
Categories
Questions about Paro Evidence
What does Paro Evidence do?
Design or audit formal Paro performance claims: release acceptance, cross-engine parity, model calibration certification or non-inferiority. Paro Evidence is an agent skill from zunor/paro. Design or audit formal Paro performance claims: release acceptance, cross-engine parity, model calibration certification or non-inferiority.
When should I use Paro Evidence?
Paro Evidence fits situations like: tasks that involve Performance reviews; tasks that involve Vector databases.
How do I install Paro Evidence in Claude Code?
Run `npx skills add zunor/paro --skill paro-evidence -a claude-code`. Or copy the skill folder (.agents/skills/paro-evidence in zunor/paro) into .claude/skills/paro-evidence in your project. Claude Code loads it when a task matches its description.
How do I install Paro Evidence in Codex?
Run `npx skills add zunor/paro --skill paro-evidence -a codex`. Or copy the skill folder (.agents/skills/paro-evidence in zunor/paro) into .agents/skills/paro-evidence in your project. Codex loads it when a task matches its description.
Can I use Paro Evidence 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 zunor/paro --skill paro-evidence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paro-evidence, .gemini/skills/paro-evidence, .github/skills/paro-evidence and .opencode/skills/paro-evidence in your project.
What does Paro Evidence need to run?
SKILL.md names no scripts, command-line tools or credentials: Paro Evidence is instructions for the agent only.
Does Paro Evidence 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 Paro Evidence 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. Review the folder before installing.
What licence does Paro Evidence use?
Paro Evidence is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Paro Evidence use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Paro Evidence?
Skills that share tags, products or a category with Paro Evidence: Diesel Guard (ayarotsky/diesel-guard, 121 stars), Querying Tempo (tempoxyz/tidx, 108 stars), Neon Postgres (neondatabase/agent-skills, 100 stars) and Ron Database (bionic-gpt/bionic-gpt, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Paro Evidence?
zunor (a GitHub user) maintains it in zunor/paro, which has 105 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.
Source: zunor/paro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.