agentic-gate-verification
Decide whether agentic work may proceed, be marked done, merge, or spawn more work.
Skill by smlfg
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/smlfg-agentic-gate-verification
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agentic-gate-verification
What's inside
- Skill name
agentic-gate-verification- Description
- Decide whether agentic work may proceed, be marked done, merge, or spawn more work. Use when verifying a gate (PR merge, kanban verifier, mission/owner decision, Git-hygiene checkpoint, completion proof) instead of trusting a worker's summary.
- License
- MIT
- Instructions
- 73 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Agentic Gate Verification
A gate is a yes/no decision about whether work may move on. This skill makes that decision against primary evidence, never against the previous worker's report.
## Procedure
1. **Name the gate before judging it.** Classify it as one of: owner decision, schema/metadata truth, PR merge readiness, Git-hygiene checkpoint, mission/session authorization, or completion proof.
2. **Find the source of authority.** Use primary repo docs, code, config and tests, not the previous worker summary. For docs/schema work, identify the file that defines the truth before reading generated output.
3. **Check presence and correctness separately.** First prove the artifact exists; then prove its values are true against the source of authority. Tests that prove keys exist or booleans are typed do not prove the booleans are correct.
4. **Block on owner-marked questions.** If a value, trade-off, scope, merge or override must be decided by the owner, do not choose for them. Add concise context and block.
5. **Separate concept value from merge readiness.** Output can be valuable raw material and still be "do not merge" because it is draft, stale, conflicting, generated from an old baseline, or rewrites canonical docs from obsolete facts.
6. **Use Git dirtiness as a checkpoint gate, not a takeover.** Broad uncommitted state may pause new missions or agents, but the gate must never auto-commit, auto-stash, push or reset.
7. **Lead with the verdict.** `merge`, `do not merge`, `block`, `continue`, or `checkpoint first`, then one or two decisive reasons and a salvage path if there is one.
## Concrete checks
### PR merge triage
Metadata before taste:
```bash
gh pr view <N> --json number,title,state,isDraft,mergeable,mergeStateStatus,headRefName,baseRefName,statusCheckRollup,updatedAt,body,files
gh pr diff <N> --name-only
gh pr diff <N>
```
Default to **not merge yet** when the PR is draft, conflicting, stale against current main, has a body that does not match its files, contains unreproducible generated artifacts, or preserves outdated claims.
### Kanban / verifier gate
A verifier must say what it verified against. Good verifier output lists: source files read, exact declared values checked, presence checks, semantic findings, and whether owner decisions remain open. "Tests pass", "keys exist" or "schema has all fields" alone is an incomplete gate for declarative or policy work.
### Git-hygiene gate
The client gathers and filters `git status` and reports file paths; the policy kernel only classifies `continue`, `warn`, `pause` or `override`. It should not shell out to Git itself.
```yaml
git_hygiene:
mode: advisory # off | advisory | required
warn_uncommitted_files: 8
pause_uncommitted_files: 15
allowed_during_pause:
- summarize_diff
- propose_commit
- checkpoint
- owner_override
```
Fail-closed rules for `required` mode:
- Missing telemetry is blocked, not clean. An empty object, a missing/null file list, or an override-only payload counts as missing. Only an explicitly supplied empty list is a clean tree; otherwise the gate is bypassable by sending nothing.
- Validate `override_reason` as a non-empty string. Truthy coercion lets booleans, ints or arrays override a pause.
- Return policy constants as tuples or fresh copies so callers cannot mutate global policy.
## Pitfalls
- Verifying only artifact presence. Presence catches missing work, not wrong claims.
- Letting green tests certify assertions no test encodes. Report the gap instead.
- Answering owner questions inside a headless worker. Output a block plus a decision table.
- Merging valuable-but-stale PRs. Salvage the idea onto current main.
- Making Git discipline destructive.
## Example
> **User:** Worker says PR #42 is done, all tests green. Merge?
>
> **Agent:** `do not merge`. The PR is 31 commits behind `main` and rewrites `docs/gates.md` with the old 3-gate model, while `src/policy.py` on main defines 4 gates. Tests only check that the doc's YAML parses. Salvage: cherry-pick the new validator in `src/validate.py` onto a fresh branch.
## Use case
You run several coding agents in parallel and a supervisor agent marks tickets "done". Before anything merges, run this skill as the final gate: it re-derives truth from the repo, separates "useful" from "mergeable", and kicks owner-only decisions back to a human instead of silently picking a default.From smlfg/HAI-skills-registry, MIT.
More from smlfg/HAI-skills-registry
- 0.570score
pdf-to-md
smlfg
Convert PDFs (lecture slides, scripts, books) into clean Markdown/text an agent can read and search, with automatic fallback to Tesseract OCR for scanned PDFs.
SkillAFreshness: AClaude Code +9 - 0.570score
archify-swarm
smlfg
Map a repository's architecture with several cheap/free models in parallel, verify every claimed file:line deterministically against the committed code, and…
SkillAFreshness: AClaude Code +9 - 0.565score
commit
smlfg
Create atomic git commits with a secrets/artifact safety check, green tests, and explicit human approval per commit.
SkillAFreshness: AClaude Code +9 - 0.565score
cross-model-review
smlfg
Get independent second, third and fourth opinions from different model families on a problem or solution, then synthesise convergence (validated) versus…
SkillAFreshness: AClaude Code +9 - 0.565score
experiment-to-project
smlfg
Turn an AI/agent experiment with several failed or half-working attempts into an evaluated, measurable project.
SkillAFreshness: AClaude Code +9 - 0.565score
github-community-checklist
smlfg
Audit a GitHub repo's community health files (description, README, license, code of conduct, contributing, security policy, issue/PR templates).
SkillAFreshness: AClaude Code +9 - 0.565score
skilleval
smlfg
Run the same task through several models or agents and score the artifacts against a pre-agreed, machine-checkable quality axis.
SkillAFreshness: AClaude Code +9 - 0.565score
subprocess-cli-pitfalls
smlfg
Diagnose Linux CLI commands that run in milliseconds in a terminal but hang or crawl when called via Python subprocess (or any non-TTY caller like cron or an…
SkillAFreshness: AClaude Code +9 - 0.565score
coursepack
smlfg
Push an entire course folder into Google NotebookLM and generate prioritised study media (audio, video, study guide) per topic and per exercise sheet, driven…
SkillAFreshness: AClaude Code +9 - 0.565score
podcast
smlfg
Produce an audio podcast from source material (doc, text, link, topic) via Google NotebookLM's MCP server.
SkillAFreshness: AClaude Code +9 - 0.565score
spoiler-free-shorts
smlfg
Add a short (60–90 s) NotebookLM video to each task of an existing interactive learning page, using a parallel example so the short never solves the task…
SkillAFreshness: AClaude Code +9 - 0.565score
visual-explainer
smlfg
Generate self-contained HTML explainers with SVG diagrams and interactive step-by-step animations for algorithms, data structures, systems or concepts.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 15, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/smlfg/HAI-skills-registry
- Website
- human-agent-interface.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from smlfg
- 0.606score
HAI-MCP
smlfg
Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.
ConnectorAFreshness: ALocal★ 1↓ 47/wkClaude Code +5 - 0.570score
archify-swarm
smlfg
Map a repository's architecture with several cheap/free models in parallel, verify every claimed file:line deterministically against the committed code, and…
SkillAFreshness: AClaude Code +9 - 0.570score
pdf-to-md
smlfg
Convert PDFs (lecture slides, scripts, books) into clean Markdown/text an agent can read and search, with automatic fallback to Tesseract OCR for scanned PDFs.
SkillAFreshness: AClaude Code +9 - 0.565score
automation-handover
smlfg
Hand a verified automation over to its users with a short explanation, a visible demo through the real UI, a demonstrated stop path, and one small user action…
SkillAFreshness: AClaude Code +9 - 0.565score
cross-model-review
smlfg
Get independent second, third and fourth opinions from different model families on a problem or solution, then synthesise convergence (validated) versus…
SkillAFreshness: AClaude Code +9 - 0.565score
commit
smlfg
Create atomic git commits with a secrets/artifact safety check, green tests, and explicit human approval per commit.
SkillAFreshness: AClaude Code +9
Cite this page
agentic-gate-verification skill. Agent Mart. https://agentmart.dev/skills/smlfg-agentic-gate-verification (last updated 2026-10-24)