AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Ss Ci Review

skill-jonisavo-supersigil-ss-ci-review · by jonisavo

Use when setting up CI gates, reviewing pull requests, interpreting verification failures, or adding Supersigil checks to automated pipelines. Activates on CI configuration, PR review workflows, and verification output triage.

— No reviews yet
0 installs
40 views
0.0% view→install

Install

$ agentstack add skill-jonisavo-supersigil-ss-ci-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jonisavo-supersigil-ss-ci-review)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ss Ci Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

CI and Review

Use this skill when the goal is to integrate Supersigil verification into CI pipelines, review pull requests against spec coverage, or interpret verification output in automated contexts.

Current Contract

supersigil verify [--format terminal|json|markdown]
supersigil affected --since  [--format json]
supersigil status [] [--format json]
supersigil plan [] [--format json]
supersigil verify

CI Pipeline Integration

Basic Verification Gate

Add supersigil verify as a CI step. It exits non-zero when error-level findings exist, making it a natural gate:

# GitHub Actions example
- name: Verify specs
  run: supersigil verify --format terminal

PR-Scoped Verification

Use supersigil affected --since to scope verification to documents affected by the PR's changes:

# Find docs affected by changes in this PR
supersigil affected --since origin/main --format json

This returns documents whose TrackedFiles globs match changed files. Use it to:

  • Run targeted supersigil status on each affected doc.
  • Flag PRs that change tracked source files without updating specs.
  • Detect stale specs before they reach the main branch.

Structured Output for Annotations

Use --format json for machine-readable output that can drive GitHub annotations, GitLab code quality reports, or custom dashboards:

supersigil verify --format json

The JSON output includes finding severity, affected document IDs, and human-readable messages suitable for inline PR comments.

PR Review Workflow

When reviewing a PR against Supersigil specs:

  1. Run supersigil affected --since origin/main to identify which

spec documents are touched by the change.

  1. For each affected document, run supersigil status to check

current health: coverage, staleness, and status consistency.

  1. Run supersigil verify to get the full finding set. Focus on:
  • New error-level findings introduced by the PR.
  • Coverage gaps: criteria without VerifiedBy evidence.
  • Stale tracked files: source changes not reflected in specs.
  • Status inconsistencies: tasks marked done but sibling docs

not promoted.

  1. Check that new code includes appropriate supersigil: {tag}

comments or that VerifiedBy file-glob paths cover new test files.

  1. If the PR introduces new behavior without spec coverage, flag it.

New criteria should exist before or alongside the implementation, not after.

Interpreting Findings

Supersigil has two layers of errors:

Graph-build errors (broken refs, cycles, duplicate IDs) are always fatal. They prevent the graph from loading and cause verify to exit non-zero regardless of document status. These are not affected by draft gating or severity configuration.

Verification findings have configurable severity and are affected by document status:

| Finding type | Default severity (non-draft) | CI action | |--------------|------------------------------|-----------| | Missing verification evidence | error | Block merge | | Missing test files | error | Block merge | | Status inconsistency | warning | Review required | | Stale tracked files | warning | Review required | | Orphan test tag | warning | Review required | | Orphan decision | warning | Review required |

Draft gating: When a document is status: draft, all its verification findings are unconditionally downgraded to info. This means draft documents will not block CI even if they have coverage gaps or status inconsistencies. Only graph-build errors (broken refs, cycles, duplicates) remain fatal on draft documents.

Coverage Reporting

Use supersigil plan to generate a coverage report showing outstanding criteria and pending tasks:

supersigil plan --format json

This can feed into a coverage dashboard or be included as a PR comment summarizing what work remains for a feature.

Failure Modes

  • Do not treat supersigil verify passing as proof that the code is

correct. It proves the spec graph is internally consistent and that declared evidence exists. It does not run tests.

  • Do not ignore affected output. Changed tracked files that do not

trigger spec updates are a drift signal.

  • Do not block PRs on info-level findings. They exist for iterative

authoring awareness, not enforcement.

Handoff

If CI reveals broken or missing specs, suggest ss-feature-specification or ss-retroactive-specification to repair them. If CI reveals implementation gaps (criteria without evidence), suggest ss-feature-development to close the coverage.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.