Validate Skills
Validate that commands documented in skill files actually work. Use when creating, updating, or reviewing skills to ensure all documented commands exit with code 0.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/microsoft/vstest --skill validate-skillsWhat it tells the agent to use
found in the instruction textThe instruction itself
11 sections, as written by the authorValidating Skills
Verify every executable command in a skill runs successfully on the current OS.
When to Use
- After creating or updating a skill that contains executable commands
- During skill review to catch stale or broken instructions
- When switching OS (e.g. Windows → Linux) to confirm cross-platform commands
Procedure
1. Detect Current OS
Determine which platform commands to extract:
# PowerShell (Windows)
$os = "Windows"
# Bash (Linux / macOS)
OS=$(uname -s) # "Linux" or "Darwin"
2. Extract Commands
Parse the target skill's SKILL.md and list every shell command for the detected OS:
- Many skills document commands in tables with Windows and Linux / macOS columns. Pick the column matching your OS.
- If a command contains comments like
# Windowsor# Linux / macOS, only run the one for your OS. - Placeholder substitution: Replace obvious placeholders (e.g.
<path-to-csproj>,<skill-name>) with real values from the repo. If no sensible value exists, skip the command. - Adapt cross-platform commands: Commands like
ls -lashould be adapted to PowerShell equivalents (Get-ChildItem) on Windows when no native Windows command is documented.
3. Track Results
Use the SQL tool to create a tracking table:
CREATE TABLE skill_commands (
id INTEGER PRIMARY KEY AUTOINCREMENT,
skill TEXT NOT NULL,
command TEXT NOT NULL,
expected_exit INTEGER DEFAULT 0,
actual_exit INTEGER,
status TEXT DEFAULT 'pending',
notes TEXT
);
4. Run Each Command
For every extracted command:
- Run it from the repo root
- Record the exit code
- Classify the result:
- Exit 0 → PASS
- Non-zero + environment issue (missing SDK, no internet) → ENV_ISSUE
- Non-zero + command/docs wrong → ERROR
5. Safety Rules
> CRITICAL: Never run unfiltered integration/acceptance tests. They take hours.
> - test.sh --integrationTest or test.cmd -Integration MUST include a --filter or -p flag.
> - test.sh -p smoke is acceptable (scoped to smoke tests), but expect it to be slow.
6. Report
After all commands finish, print a summary:
=== Skill Validation Report ===
Skill: <skill-name>
OS: <Linux|Darwin|Windows>
Commands tested: N
PASS: X
ENV_ISSUE: Y (list with reasons)
ERROR: Z (list failed commands with exit codes)
7. Fix or Flag
- ERROR (documentation bug): Update the skill's
SKILL.mdto fix the command. - ENV_ISSUE: Add a troubleshooting note to the skill if the environment prerequisite is not already documented.
- PASS: No action needed.
Ordering Tips
- Run restore/build before tests (tests depend on build output)
- Run the cheapest commands first to fail fast
- Batch independent test commands in parallel when possible
Other skills for the same job
different authors, same section of the catalogue
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes.
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
Standardize how an AI-collaboration project turns work into reusable knowledge. Use when initializing or retrofitting Project Cairn in a project, recording progress after meaningful work, maintaining AGENTS/CLAUDE/cairn docs, auditing project knowledge for drift or missing records, pulling and citing external knowledge, or graduating validated project experience into a reusable knowledge base.
Persistent memory and context management for AI agents using OpenContext. Keep context across sessions/repos/dates, store conclusions, and provide document search workflows.
> PARA method knowledge management for Obsidian vaults. Use this skill whenever the user wants to organize notes using PARA (Projects, Areas, Resources, Archive), classify a note into a PARA category, route a note to the right vault folder, normalize frontmatter fields, run a PARA hygiene review, suggest archiving, audit vault structure, or process new knowledge inputs into an existing PARA-based vault. Also trigger when the user mentions inbox processing, vault cleanup, note classification, PARA review, or asks "where does this note belong?". Works with existing Obsidian skills (obsidian-markdown, obsidian-cli) — never replaces them.
Keeps implementation and specs in sync. Use when working on a feature that has a spec in .agents/specs/, when the user says /spec, or when starting implementation of a documented feature. Also use when the user asks to verify implementation against a spec or update a spec after changes.
Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.
How to use it
Take microsoft/validate-skills from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.