AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Docs Workflow Style Review

skill-abhatt-rh-redhat-docs-agent-tools-docs-workflow-style-review · by abhatt-rh

Style guide compliance review of documentation drafts. Dispatches the docs-tools:docs-reviewer agent with Vale linting and 18+ style guide review skills.

No reviews yet
0 installs
32 views
0.0% view→install

Install

$ agentstack add skill-abhatt-rh-redhat-docs-agent-tools-docs-workflow-style-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-abhatt-rh-redhat-docs-agent-tools-docs-workflow-style-review)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Docs Workflow Style Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Style Review Step

Step skill for the docs-orchestrator pipeline. Follows the step skill contract: parse args → dispatch agent → write output.

Arguments

  • $1 — JIRA ticket ID (required)
  • --base-path — Base output path (e.g., .agent_workspace/proj-123)
  • --format — Documentation format (default: adoc)

Input

/writing/

Output

/style-review/review.md

Execution

1. Parse arguments

Extract the ticket ID, --base-path, and --format from the args string.

Set the paths:

OUTPUT_DIR="${BASE_PATH}/style-review"
OUTPUT_FILE="${OUTPUT_DIR}/review.md"
mkdir -p "$OUTPUT_DIR"

2. Determine source files

Read the writing step's sidecar at ${BASE_PATH}/writing/step-result.json to determine the writing mode and file list.

If the sidecar exists and mode is "update-in-place" with a non-empty files array:

Build a `` listing the files explicitly:

**Source files** — review and edit each of these files:
- `/absolute/path/to/file1.adoc`
- `/absolute/path/to/file2.adoc`

**Edit files in place** at their current paths. Do NOT create copies or move files.

Otherwise (draft mode, missing sidecar, or empty files array):

Set DRAFTS_DIR="${BASE_PATH}/writing" and build the block as:

**Source files**: `/` — review and edit files at this location only.

**Edit files in place** at the source path above. Do NOT create copies or write to a drafts/ subfolder.

3. Dispatch agent

You MUST use the Agent tool to invoke the docs-tools:docs-reviewer subagent. Do NOT read the agent's markdown file or attempt to perform the agent's work yourself — the agent has a specialized system prompt and must run as an isolated subagent.

Select the prompt below based on the --format flag. Substitute `` with the block built in step 2.

Agent tool parameters:

  • subagent_type: docs-tools:docs-reviewer
  • description: Review documentation for

Prompt for AsciiDoc (--format adoc):

> Review the AsciiDoc documentation drafts for ticket `. > > > > **Report output**: — you MUST save the review report to exactly this path. Do NOT write to any other location. > > For each file: > 1. Run Vale linting once (use the lint-with-vale` skill) > 2. Fix obvious errors where the fix is clear and unambiguous > 3. Run documentation review skills: > - Red Hat docs: docs-review-modular-docs, docs-review-content-quality > - IBM Style Guide: ibm-sg-audience-and-medium, ibm-sg-language-and-grammar, ibm-sg-punctuation, ibm-sg-numbers-and-measurement, ibm-sg-structure-and-format, ibm-sg-references, ibm-sg-technical-elements, ibm-sg-legal-information > - Red Hat SSG: rh-ssg-grammar-and-language, rh-ssg-formatting, rh-ssg-structure, rh-ssg-technical-examples, rh-ssg-gui-and-links, rh-ssg-legal-and-support, rh-ssg-accessibility, rh-ssg-release-notes (if applicable) > 4. Skip ambiguous issues requiring broader context

Prompt for MkDocs (--format mkdocs):

> Review the Material for MkDocs Markdown documentation drafts for ticket `. > > > > **Report output**: — you MUST save the review report to exactly this path. Do NOT write to any other location. > > For each file: > 1. Run Vale linting once (use the lint-with-vale` skill) > 2. Fix obvious errors where the fix is clear and unambiguous > 3. Run documentation review skills: > - Content quality: docs-review-content-quality > - IBM Style Guide: ibm-sg-audience-and-medium, ibm-sg-language-and-grammar, ibm-sg-punctuation, ibm-sg-numbers-and-measurement, ibm-sg-structure-and-format, ibm-sg-references, ibm-sg-technical-elements, ibm-sg-legal-information > - Red Hat SSG: rh-ssg-grammar-and-language, rh-ssg-formatting, rh-ssg-structure, rh-ssg-technical-examples, rh-ssg-gui-and-links, rh-ssg-legal-and-support, rh-ssg-accessibility > 4. Skip ambiguous issues requiring broader context

Note: MkDocs review omits docs-review-modular-docs (AsciiDoc-specific) and rh-ssg-release-notes.

4. Verify output

After the agent completes, verify the review report exists at ``.

5. Write step-result.json

Write the sidecar to /step-result.json:

{
  "schema_version": 1,
  "step": "style-review",
  "ticket": "",
  "completed_at": ""
}

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.