Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Rpi Validate

ASecurity

Verify each implementation phase against its approved plan, deviation notes, actual changes and valid automated acceptance evidence.

5 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentstesting

Security Analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add juan294/cc-rpi --skill rpi-validate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rpi Validate?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Rpi Validate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/juan294-rpi-validate-e78713b9/badge)](https://www.skillsdirectory.com/skills/juan294-rpi-validate-e78713b9)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: "rpi-validate"
description: "Verify each implementation phase against its approved plan, deviation notes, actual changes and valid automated acceptance evidence."
---

Validate the implementation against the plan.

When a parent uses a machine-readable assignment/acceptance record, follow the
[dispatch contract](references/dispatch.md) and validate it before claiming
complete coverage. The record is optional for a small parent-only task; required
review, TDD and phase acceptance still apply.

Process:
1. Locate the requested plan and phases (provided path or repository history).
   Read controlling instructions, the complete plan/current phase contracts and
   `docs/plans/<plan-name>-notes.md` when present. Cite recorded decisions and
   deviations rather than reconstructing intent from the diff.
2. Read the [durable handoff](references/handoff.md), then revalidate actual
   worktree/base/current state before reusing its evidence. Inspect changed code
   and tests to the required depth; unchanged complete prior reads remain usable.
   Validation stays within the requested phase scope.
3. Review independently of implementation. A narrow review may use one fresh
   reviewer; useful independent assignments state objective, permitted read-only
   actions/files, evidence/output, resource limits and completion condition. Use
   available slots and account for every required result. Missing or failed review
   is an acceptance gap, not approval.
4. For each requested phase:
   - Verify marked-complete items are actually done.
   - Confirm the plan's stuck-state recovery-or-disclosure tests and its
     consumer-sweep coverage exist and pass; a stuck state with only a safety
     test, or a swept consumer left unmarked, is an open finding.
   - Run every applicable automated verification command, or reuse valid
     evidence when candidate inputs and check selection are unchanged.
   - Review test quality, not only test results. For each changed or added
     test, name the production change that would make it fail. Flag
     tautological, disjunctive, registration-only and over-broad assertions,
     mocks of owned code, and coverage exclusions that defend a threshold.
   - Think about edge cases.
5. Save `docs/agents/validation-report.md` with:
   - Implementation status per phase
   - Automated verification results
   - Code review findings (matches, deviations, issues), every confirmed finding's
     disposition and evidence-backed false-positive rejections
   - Missing review/coverage results and any unresolved architectural decision
   - Test-quality findings: assertions that cannot fail, owned-code mocks,
     threshold-defending exclusions, and any narrowed assertion's remaining invariant
   - Manual testing required (only if automation impossible — explain WHY)
   - Recommendations
6. Return findings to the authorized implementation owner for repair, simplify
   and re-verification. A validation-only request reports rather than silently
   editing product files. If this validation belongs to an implementation loop,
   continue that already-authorized loop until every actionable finding is resolved.
7. Apply the durable handoff contract in the report, including check/candidate
   identity and remaining acceptance gaps. Present the outcome and stop at the
   requested validation/phase boundary unless continuation is already authorized.

## Execution and acceptance

Use the scope and authorization already supplied in the request. Resolve routine
implementation choices from repository evidence. Complete authorized local work,
review, repair and applicable verification before its acceptance gate. An explicit
instruction can authorize continuation across phases; otherwise stop at the stated
phase boundary. Production, publication, destructive actions and new scope retain
their actual authorization requirements. Preserve durable artifacts before cleanup.

## Bundled contract tools

For a structured handoff, resolve `scripts/rpi-dispatch.py` relative to this
installed skill; its sibling `scripts/validate-findings.py` checks report IDs
and references. Follow [dispatch](references/dispatch.md) for invocation and
[durable handoff](references/handoff.md) for actual-state revalidation.

Attribution

juan294juan294
View sourceSee grades on GitHubMore from juan294 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →