Best for
- Surface potential issues in protocol definitions without blocking commits. Follow Anthropic philosophy: transparency over enforcement, user agency over automation.
jongwony/epistemic-protocols/.claude/skills/verify/SKILL.md
This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality. Invoke explicitly with /verify for pre-commit validation.
Decision brief
Verify epistemic protocol consistency before commit through static checks and expert review.
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/jongwony/epistemic-protocols --skill ".claude/skills/verify"Inspect the Agent Skill "verify" from https://github.com/jongwony/epistemic-protocols/blob/45c5f84ce13471b8c0447242290a7faa3bfa5ce6/.claude/skills/verify/SKILL.md at commit 45c5f84ce13471b8c0447242290a7faa3bfa5ce6. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
Run scripts/static-checks.js against project root. This script executes without loading into context.
Run scripts/static-checks.js against project root. This script executes without loading into context.
Spawn parallel Task subagents for LLM-based review — one per perspective (Type Theory / Category Theory, Instruction Design, Claude Code Ecosystem). Load each subagent's prompt template from references/review-checklists.md (single source of truth; do not duplicate the templates…
Combine static check results with expert review findings. Categorize by severity:
Present findings via gate interaction. Format:
Permission review
The documentation asks the agent to run terminal commands or scripts.
node ${SKILL_DIR}/scripts/static-checks.js ${PROJECT_ROOT}The documentation asks the agent to run terminal commands or scripts.
Most common pattern: invoke `/verify` before `/commit` command.Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 91/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 160 | Source | Repository attention, not individual Skill quality |
| Compatibility | 1 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Verify epistemic protocol consistency before commit through static checks and expert review.
Surface potential issues in protocol definitions without blocking commits. Follow Anthropic philosophy: transparency over enforcement, user agency over automation.
| Principle | Implementation |
|---|---|
| Surface, don't enforce | Present findings; user decides action |
| Zero-context scripts | Static checks run without consuming context |
| Explicit control | User invokes /verify intentionally |
| Graduated severity | Critical / Concern / Note categorization |
Run scripts/static-checks.js against project root. This script executes without loading into context.
node ${SKILL_DIR}/scripts/static-checks.js ${PROJECT_ROOT}
Output format:
{
"pass": [{ "check": "...", "file": "...", "message": "..." }],
"fail": [{ "check": "...", "file": "...", "message": "..." }],
"warn": [{ "check": "...", "file": "...", "message": "..." }]
}
Checks performed: Structural conformance (JSON schema, Unicode notation, directive verbs, required sections, morphism anatomy, gate-type soundness), cross-reference and routing integrity (cross-reference integrity and scan, routing-index contract, onboard/catalog sync, partition invariant), drift prevention (version staleness, codex-manifest sync, spec-vs-impl drift, single-axis soundness, emit-load discipline, framing-readout enforcement, language purity), and packaging/contract sync (artifact self-containment, packaged-agent contract sync). The check inventory is the script itself (scripts/static-checks.js); references/verification.md carries why the non-obvious checks exist and what to do when one fires.
Spawn parallel Task subagents for LLM-based review — one per perspective (Type Theory / Category Theory, Instruction Design, Claude Code Ecosystem). Load each subagent's prompt template from references/review-checklists.md (single source of truth; do not duplicate the templates here — see Review Checklists below). Each template samples the protocols changed in the current diff, falling back to a representative sample when the diff is not protocol-scoped.
All three subagents run in parallel. Collect results before proceeding.
Combine static check results with expert review findings. Categorize by severity:
| Severity | Static Check Source | LLM Review Source |
|---|---|---|
| Critical | fail array | findings with severity: "critical" |
| Concern | warn array (structural) | findings with severity: "concern" |
| Note | warn array (stylistic) | findings with severity: "note" |
Identify convergence (all perspectives agree) and divergence (perspectives differ).
Apply Claude Code Ecosystem expert's filtered array to dismiss false positives from other perspectives.
Present findings via gate interaction. Format:
## Verification Results
### Critical (n issues)
- [issue 1]: [location] - [description]
- [issue 2]: [location] - [description]
### Concerns (n issues)
- [issue 1]: [location] - [description]
### Notes (n observations)
- [observation 1]
### Filtered (Claude Code context)
- [filtered issue]: [reason dismissed]
---
Select action:
Options to present:
| Decision | Action |
|---|---|
| Fix critical | Show specific fixes, await approval for each |
| Review concerns | Present concerns one by one with dismiss/address options |
| Proceed anyway | Log decision, suggest commit message annotation |
| Cancel | End verification, no changes |
Commit message annotation (if proceeding with issues):
[verify: n critical, m concerns acknowledged]
Consult references/criteria.md for detailed severity definitions and decision matrix.
Consult references/review-checklists.md for:
| Error | Response |
|---|---|
| Script execution fails | Report error, offer manual check option |
| Subagent timeout | Report partial results, continue with available data |
| No issues found | Confirm clean state, proceed to commit |
Verification may trigger perspective selection if findings require analysis approach decision.
Critical findings surface as high-stakes gaps. Syneidesis gap detection may augment verification.
Most common pattern: invoke /verify before /commit command.
## Verification Results
All checks passed.
- Static checks: all checks pass (0 fail, 0 warn)
- Type/Category review: No issues
- Instruction Design review: No issues
Ready to commit.
## Verification Results
### Critical (1 issue)
- State machine totality: prothesis/skills/frame/SKILL.md - Undefined transition when |perspectives(C)| < 2
### Concerns (2 issues)
- Categorical terminology: prothesis/skills/frame/SKILL.md - limit/colimit may not match intended semantics
- Directive verb: prothesis/skills/frame/SKILL.md - "Invoke AskUserQuestion" should be "call"
### Notes (1 observation)
- Version: prothesis plugin.json version not bumped since last change
---
How to proceed?
Frequently asked questions
Verify epistemic protocol consistency before commit through static checks and expert review.
The source record exposes this install command: npx skills add https://github.com/jongwony/epistemic-protocols --skill ".claude/skills/verify". Inspect the command and pinned source before running it.
The pinned source record declares support for: claude code.
Static rules flagged exec-script in the source; the page lists the matching lines and excerpts.
Alternatives
yonatangross/orchestkit
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use when verifying changes are ready to merge. Use /ork:cover instead when the tests still have to be written.
asgeirtj/system_prompts_leaks
Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.
oaustegard/claude-skills
Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tre
vasilyu1983/AI-Agents-public
Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit trails, worktree automation, or budget enforcement.