validate · rsmdt — Claude Code skill: what it does, how to install
validate orchestrates spec reviews, file audits, spec-to-code drift detection, and constitution rule checks across specialist subagents.
MIT ★ 587 updated 2026-10-26
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startupWhat validate does
This skill acts as a validation orchestrator without inspecting source code directly. Instead, it delegates the analysis to specialized subagents launched in parallel. Based on the target argument, it activates one of six modes: three-digit spec ID checks, single-file reviews by path, spec-to-code drift analysis, governance rule verification against CONSTITUTION.md, two-artifact comparisons, or general sanity checks.
Execution runs in one of three environments: fire-and-forget parallel agents, a persistent Agent Team with a shared task backlog, or an inline Dynamic Workflow. Every issue returned contains a severity rating, the exact file path and line number, a one-sentence summary, and an actionable fix.
Results are advisory by default, but L1 and L2 constitution violations block the workflow completely. For drift detection, the skill tracks issues as tasks via the bundled task.js script.
What it helps with
- detect divergence between specification documents and code
- audit a single file with line-level references and explicit fixes
- enforce repository governance rules from CONSTITUTION.md
- compare two project artifacts directly against each other
Example prompts for the agent
- /validate 005
- /validate src/auth/service.ts
- /validate drift
How to install validate
1Plugin marketplace
/plugin marketplace add rsmdt/the-startup/plugin install start@the-startupThis installs the whole start plugin with all its skills
2Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill validate -a claude-code3Manually: put the files in place
~/.claude/skills/validate/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/validate/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill validate -a codex2Manually: put the files in place
.agents/skills/validate/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill validate -a cursor2Manually: put the files in place
.cursor/skills/validate/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rsmdt/the-startup plugins/start/skills/validate2Manually: put the files in place
.github/skills/validate/SKILL.md1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill validate -a gemini-cli2Platform CLI
gemini skills install https://github.com/rsmdt/the-startup --path plugins/start/skills/validateManually: put the files in place
.devin/skills/validate/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about validate
How to install validate in Claude Code?
Run /plugin marketplace add rsmdt/the-startup followed by /plugin install start@the-startup to install the plugin.
What does the validate skill do?
It parses your input target, launches dedicated validation perspectives across subagents, and builds a consolidated report with file:line pointers and fixes.
Can validate run without blocking the build?
Most findings remain purely advisory, but governance violations classified as L1 or L2 in CONSTITUTION.md are strictly blocking.
Source text
SKILL.md · MIT
---
name: validate
description: Validate in any of six modes — spec quality, single-file review, spec-to-implementation drift, constitution rule enforcement, comparison between two artifacts, or sanity-checking your understanding. Use when checking a spec by ID, validating a file by path, detecting drift, enforcing constitution rules, comparing two sources ("$X against $Y"), or asking a freeform validation question.
user-invocable: true
argument-hint: "spec ID (e.g., 005), file path, 'constitution', 'drift', or description of what to validate"
---
## Persona
Act as a validation orchestrator that ensures quality and correctness across specifications, implementations, and governance.
**Validation Request**: $ARGUMENTS
## Interface
Finding {
status: PASS | WARN | FAIL
severity: HIGH | MEDIUM | LOW
title: string // max 40 chars
location: string // file:line
issue: string // one sentence
recommendation: string // how to fix
}
State {
target = $ARGUMENTS
validationMode: Spec | File | Drift | Constitution | Comparison | Understanding
perspectives = [] // from reference/perspectives.md
mode: Standard | Agent Team | Dynamic Workflow
findings: Finding[]
}
## Constraints
**Always:**
- Launch ALL applicable validation perspectives simultaneously.
- Include file paths and line numbers for all findings.
- Every finding must have a clear, actionable fix recommendation.
- Advisory by default — provide recommendations without blocking.
**Never:**
- Validate code yourself — always delegate to specialist agents.
- Skip constitution L1/L2 violations — these are blocking.
- Present findings without specific file:line references.
- Summarize agent findings — present complete results.
## Reference Materials
- reference/perspectives.md — perspective definitions, activation rules, mode-to-perspective mapping
- reference/3cs-framework.md — completeness, consistency, correctness validation
- reference/ambiguity-detection.md — vague language patterns and scoring
- reference/drift-detection.md — spec-implementation alignment checking
- reference/constitution-validation.md — governance rule enforcement
- reference/output-format.md — assessment level definitions, next-step options
- examples/output-example.md — concrete example of expected output format
## Workflow
### 1. Parse Mode
Determine validation mode from $ARGUMENTS:
match (target) {
/^\d{3}/ => Spec Validation
file path => File Validation
"drift" | "check drift" => Drift Detection
"constitution" => Constitution Validation
"$X against $Y" => Comparison Validation
freeform text => Understanding Validation
}
### 2. Gather Context
match (mode) {
Spec Validation => load spec documents (PRD, SDD, PLAN), identify cross-references
Drift Detection => load spec + identify implementation files + extract requirements
Constitution => check for CONSTITUTION.md, parse rules by category
File Validation => read target file + surrounding context
Comparison => load both sources for comparison
}
### 3. Select Mode
Ask the user to choose:
Standard (default) — parallel fire-and-forget subagents
Agent Team — persistent teammates with shared task list and coordination
Dynamic Workflow — one inline workflow script fans out the validators and collects their findings
Recommend Agent Team when: full spec validation | drift + constitution together | 4+ perspectives | multi-document scope.
Recommend Dynamic Workflow instead when those thresholds apply but the perspectives are independent and need no coordination between validators.
### 4. Launch Validation
Read reference/perspectives.md for the mode-to-perspective mapping.
match (mode) {
Standard => launch parallel subagents per applicable perspectives
Agent Team => create team, spawn one validator per perspective, assign tasks
Dynamic Workflow => run one dynamic workflow: one validator agent per perspective in parallel, returning every finding
}
For Dynamic Workflow, these instructions are the opt-in: call the Workflow tool directly with an inline script. Do not load the workflow-authoring reference or assemble the script through shell commands first — runs that detour through either stall before launching. Choose `model` and `effort` per stage from what the stage does. Mechanical stages — running a command, gathering or quoting sources, mapping text into a fixed schema — can run on a smaller, faster model at lower effort. Analysis, writing, and judging another agent's work need the strongest model. A judging stage never runs on a weaker model than the stage it judges. When unsure, omit `model` so the stage inherits the session model.
### 5. Synthesize Findings
Process findings:
1. Deduplicate by location (within 5 lines), keeping highest severity and merging complementary details.
2. Sort by severity (descending).
3. Group by category.
Mode-specific synthesis:
- Drift: Read reference/drift-detection.md and categorize by type (Scope Creep, Missing, Contradicts, Extra).
- Constitution: Read reference/constitution-validation.md and separate by level (L1 autofix, L2 manual, L3 advisory).
- Spec: Read reference/ambiguity-detection.md and include ambiguity score.
assessment = match (failCount, warnCount) {
(0, 0) => Excellent
(0, 1..3) => Good
(0, > 3) => Needs Attention
(> 0, _) => Critical
}
Read reference/output-format.md and format the report accordingly.
### 6. Next Steps
match (validationMode) {
Constitution => ask the user to choose: Apply autofixes (L1) | Show violations | Skip
Drift => ask the user to choose: Acknowledge | Update implementation | Update spec | Defer
Spec | File => ask the user to choose: Address failures | Show details | Continue anyway
}
For a drift check on a spec, file each finding as a tracker task (`node ${CLAUDE_PLUGIN_ROOT}/scripts/task.js create --spec {specId} --type drift --name "<finding>"`) unless an open one already describes it, set a finding to `passed` once the implementation or the spec is updated to resolve it, and record the check: `node ${CLAUDE_PLUGIN_ROOT}/scripts/spec.js {specId} --event '{"kind":"verify","constitution":"pass|fail|none"}'` (`none` when no constitution was checked).
## Integration with Other Skills
Called by other workflow skills:
- `/start:implement` — drift check at phase boundaries, constitution check at checkpoints
- `/start:specify` — architecture alignment during SDD phase
© Rudolf S. · MIT · rsmdt/the-startup
Similar skills
All skills for Agent setup: memory, context, orchestration →validate by other authors comes first.