bquery-ai-guidance-sync

Documentation Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Refresh bQuery AI guidance and release metadata. Use when version, engines, exports, AGENT.md, llms.txt, copilot-instructions, .…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “When to Use”, “Source of Truth”, “Procedure”, “Project-Specific Guardrails”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name bquery-ai-guidance-sync directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “When to Use / Source of Truth / Procedure” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Documentation
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: macOS · Linux · Windows
Runtime requirements: Node.js · Bun
Detected file/system behavior: Read-only
Write / modify
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview bquery-ai-guidance-sync.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# bQuery AI Guidance Sync

## When to Use

Use this skill when release metadata, supported engines, public exports, or shared AI-facing repo guidance change.

Typical triggers:

- version bump in `package.json`
- engine floor changes for Node.js or Bun
- changes in public module exports
- refreshes to `AGENT.md`, `llms.txt`, or `.github/copilot-instructions.md`
- updates to `.cursorrules` or `.clinerules`
- changes to the guidance sync script
- release sweeps for README, docs, or changelog after a public-surface change

## Source of Truth

Trust these in order:

1. `package.json`
2. `src/*/index.ts`
3. `AGENT.md`
4. `docs/guide/*.md`
5. `CHANGELOG.md` for release deltas and migration context

## Procedure

1. Confirm the real version, engines, scripts, and exports in `package.json`.
2. Verify the current public runtime surface in the relevant `src/*/index.ts` barrels.
3. Update the shared AI-facing files as a synced set:
   - `AGENT.md`
   - `llms.txt`
   - `.github/copilot-instructions.md`
   - `.cursorrules`
   - `.clinerules`
   - `README.md`
   - `CONTRIBUTING.md`
4. If public exports changed, re-check `src/full.ts`.
5. If the release messaging changed, update the relevant docs guides and `CHANGELOG.md`.
6. Run the repo sync check before finishing.

## Project-Specific Guardrails

- Keep the role split clear:
  - `AGENT.md` = deep reference
  - `llms.txt` = compact mirror
  - `.github/copilot-instructions.md` = behavioral and meta guidance
  - `.cursorrules` and `.clinerules` = derived snapshots
- Do not let the guidance files drift from `package.json` version or engine metadata.
- Avoid updating only one guidance file when the change obviously applies to the synced set.

## Required Validation

Run:

- `bun run check:ai-guidance`

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> When to Use → Source of Truth → Procedure → Project-Specific Guardrails → Required Validation
terms    -> Use this skill when release metadata, supported engines, public exports, or shared AI-facing repo guidance change. · 1. package.json 2. · 1. Confirm the real version, engines, scripts, and exports in package.json. · Use additional validation as needed for the actual code or docs touched. · --- > Source: [bQuery/bQuery](https://github.com/bQuery/bQuery) — distributed by [TomeVault](https://tomevault.io).
files/cmd -> package.json · AGENT.md · llms.txt · .github/copilot-instructions.md · .cursorrules · .clinerules · src//index.ts · docs/guide/.md
body sha256 -> 35afbb9264fc

Decide Fit First

Design Intent

How To Use It

Boundaries And Review

bQuery AI Guidance Sync

When to Use

Source of Truth

Procedure

Project-Specific Guardrails

Required Validation

Discussion