Automated summary
Audits documentation for drift against the code, identifying stale references, dead links, and incorrect instructions.
Strengths
- Automated consistency checks between code and documentation.
- Severity levels (HIGH, MEDIUM, LOW) to prioritize fixes.
- Support for targeted checks (dead links, file references) and JSON output.
- Dry-run mode to preview auto-fixes before applying.
Limitations
- Requires initial setup via drift init.
- Limited to artifacts detectable by existing verifiers.
- May produce false positives if file paths change intentionally.
Use this skill before a release, after a major refactor, or when the user mentions outdated docs or broken links.
Avoid using it for external documentation not tied to the codebase, or for projects without structured documentation to audit.
Security analysis
SafeThe skill only runs the 'drift' audit tool with Bash, and drift is a documentation checker with no destructive or exfiltration capabilities. No unsafe operations are performed.
No concerns found
How this analysis is madeExamples
Run a full drift audit on the current codebase.Check documentation drift before release, only show medium and high severity issues.Audit documentation for drift since the last merge commit.name: drift-sentinel description: Audits documentation for drift against the code. Use when preparing a release, onboarding someone new, or when the user mentions out-of-date docs. Also use after large refactors to catch stale doc references. allowed-tools:
- Bash(drift *)
When to use this skill
- User says "update the docs" or "check the README" → run
drift audit - Before a release → run
drift audit --max-severity=medium - After a big refactor → run
drift audit --since <last-merge> - User mentions a stale example or broken link → run
drift audit - Need only one kind of check (e.g. dead links) →
drift audit --kind dead-external-link,dead-file-ref - Want machine-readable output for another tool →
drift audit --json(stdout is pure JSON) - Need a clean run without dropping
DRIFT_REPORT.mdin the repo → add--no-report - Discover what verifiers exist →
drift verifiers list - Scaffold a starter config →
drift init
How to interpret results
- HIGH — must fix; users will follow a broken instruction
- MEDIUM — should fix before release
- LOW — nice to have; often acceptable to defer
After running, read DRIFT_REPORT.md (written by default in terminal mode; suppress with --no-report; relocate with --report-path). For auto-fixable items, suggest running drift fix --dry-run first, then drift fix.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/drift-sentinel-ms1aw40d/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/drift-sentinel-ms1aw40d' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/drift-sentinel-ms1aw40d/download' --output '.skill-downloads/drift-sentinel-ms1aw40d/SKILL.md.part' && mv '.skill-downloads/drift-sentinel-ms1aw40d/SKILL.md.part' '.skill-downloads/drift-sentinel-ms1aw40d/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/drift-sentinel-ms1aw40d/SKILL.md' && test -s '.skill-downloads/drift-sentinel-ms1aw40d/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/drift-sentinel' && cp -R '.skill-downloads/drift-sentinel-ms1aw40d' '.claude/skills/drift-sentinel'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/drift-sentinel-ms1aw40d'openskills read 'drift-sentinel-ms1aw40d'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/drift-sentinel-ms1aw40d/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.