qprisma-doc-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: Keep QPrisma documentation, Copilot instructions, agents, skills, PR templates, and changelog synchronized with implementation a…
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 “Required reads”, “Primary documentation targets”, “Guardrails”, “Process”, 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 qprisma-doc-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 “Required reads / Primary documentation targets / Guardrails” 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 / env-read; 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.

QPrisma Documentation Sync Skill

Use this skill when code, APIs, workflows, architecture, evaluation behavior, or maintainer process changes.

Required reads

AGENTS.md
.github/instructions/docs.instructions.md
Changed implementation/workflow files
Existing docs that mention the changed behavior
CHANGELOG.md when the change is user-visible, operator-visible, release-facing, or workflow-facing

Primary documentation targets

README.md
API_DOCUMENTATION.md
TESTING.md
CHANGELOG.md
docs/ARCHITECTURE.md
docs/BACKEND_ARCHITECTURE.md
docs/INFRASTRUCTURE.md
docs/MEMORY_ARCHITECTURE.md
backend/agent/ARCHITECTURE.md
.github/copilot-instructions.md
.github/agents/*.agent.md
.github/skills/*/SKILL.md
.github/PULL_REQUEST_TEMPLATE.md

Guardrails

Prefer edits to existing docs over creating new files.
Do not document aspirational behavior; document shipped or explicitly planned workflow only.
Do not duplicate large sections. Cross-reference the source of truth.
Keep examples runnable and aligned with current repository commands.
Explicitly note external prerequisites such as Azure, Neo4j, PostgreSQL, Foundry, or deployed hosted agent.
Redact private values in examples and evidence.

Process

Identify impacted docs from changed files and user-visible/operator-visible behavior.
Search for stale references across docs, Copilot instructions, agents, skills, and PR templates.
Update existing sections with precise paths, commands, environment variables, and constraints.
Add changelog entries only when the behavior or workflow matters to users, operators, or maintainers.
Verify there are no contradictory statements across docs.

Validation

Run git diff --check for text formatting issues.
Inspect Markdown headings, links, commands, and examples touched by the change.
For docs generated from implementation, run the existing generator/check command if one exists.

Output format

### Updated docs
- `path`: change summary

### Consistency checks
- ...

### Remaining gaps
- ...

Source: alexandergg/QPrisma — distributed by TomeVault.

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: Plug-and-play
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Env read
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 qprisma-doc-sync.preview

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

SKILL.md SKILL.md

# QPrisma Documentation Sync Skill

Use this skill when code, APIs, workflows, architecture, evaluation behavior, or maintainer process
changes.

## Required reads

1. `AGENTS.md`
2. `.github/instructions/docs.instructions.md`
3. Changed implementation/workflow files
4. Existing docs that mention the changed behavior
5. `CHANGELOG.md` when the change is user-visible, operator-visible, release-facing, or workflow-facing

## Primary documentation targets

- `README.md`
- `API_DOCUMENTATION.md`
- `TESTING.md`
- `CHANGELOG.md`
- `docs/ARCHITECTURE.md`
- `docs/BACKEND_ARCHITECTURE.md`
- `docs/INFRASTRUCTURE.md`
- `docs/MEMORY_ARCHITECTURE.md`
- `backend/agent/ARCHITECTURE.md`
- `.github/copilot-instructions.md`
- `.github/agents/*.agent.md`
- `.github/skills/*/SKILL.md`
- `.github/PULL_REQUEST_TEMPLATE.md`

## Guardrails

- Prefer edits to existing docs over creating new files.
- Do not document aspirational behavior; document shipped or explicitly planned workflow only.
- Do not duplicate large sections. Cross-reference the source of truth.
- Keep examples runnable and aligned with current repository commands.
- Explicitly note external prerequisites such as Azure, Neo4j, PostgreSQL, Foundry, or deployed hosted
  agent.
- Redact private values in examples and evidence.

## Process

1. Identify impacted docs from changed files and user-visible/operator-visible behavior.
2. Search for stale references across docs, Copilot instructions, agents, skills, and PR templates.
3. Update existing sections with precise paths, commands, environment variables, and constraints.
4. Add changelog entries only when the behavior or workflow matters to users, operators, or maintainers.
5. Verify there are no contradictory statements across docs.

## Validation

…

Evidence boundary and execution chain

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

sections -> Required reads → Primary documentation targets → Guardrails → Process → Validation → Output format
terms    -> Use this skill when code, APIs, workflows, architecture, evaluation behavior, or maintainer process changes. · 1. AGENTS.md 2. · - Prefer edits to existing docs over creating new files. · 1. Identify impacted docs from changed files and user-visible/operator-visible behavior. · - Run git diff --check for text formatting issues. · --- > Source: [alexandergg/QPrisma](https://github.com/alexandergg/QPrisma) — distributed by [TomeVault](https://tomevault.io).
files/cmd -> AGENTS.md · .github/instructions/docs.instructions.md · CHANGELOG.md · README.md · APIDOCUMENTATION.md · TESTING.md · docs/ARCHITECTURE.md · docs/BACKENDARCHITECTURE.md
body sha256 -> 211f0c523005