gate
Skill1 starsChanged 11 days agoMITView on GitHub
Instrument a repo with mechanical gates so an agent cannot commit untested code. Installs local hooks, a TDD gate, and a required CI check, then proves the gate fires. Do NOT use if already gated.
- Pipes a download into a shell
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 95
Do not claim enforcement — demonstrate it:
“Common” is measured: kept by at least 6 in 10 of the 26 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Gate
Turn "please follow the rules" into "you cannot commit until you do."
A gate is a mechanical check at a lifecycle point. It does not depend on the agent remembering anything. This skill installs the enforcement layer — local hooks, a TDD gate, and a required CI check — and then proves it fires.
When to Activate
- A user says their AI agent ships untested, unreviewed, or broken code.
- They want a TDD gate, a pre-commit gate, or a required CI status check.
- They ask to "add enforcement", "block bad commits", or "make the agent prove it works".
- A repo has prompts (
CLAUDE.md,.cursorrules,AGENTS.md) but no mechanical enforcement.
When NOT to Use
- The repo already has active gates — verify first (see Verification).
- Non-git projects: no VCS means no hooks; enforcement is convention-only.
- One-off scripts where a gate is pure noise.
Output Contract
| Artifact | Format | Location | Quality Criteria |
| Enforcement wired | hooks + CI workflow | .git/hooks/ or .husky/, .github/workflows/ | A commit without a matching test is blocked; a PR without green gates cannot merge |
| Verification evidence | terminal transcript | chat | The first gate actually fires (blocked commit shown) |
The Principle
Agent = Model + Harness. Most agent failures blamed on "the model" are configuration failures: a missing gate, not a missing brain. This skill installs the harness — the layer that survives when the agent's context fills up.
Rules that depend on memory fail. Rules that live in a hook succeed.
Workflow
1. Detect the VCS and the stack
git rev-parse --is-inside-work-tree # git?
git config core.hooksPath # hooks shadowed by husky/lefthook?
ls package.json pyproject.toml Cargo.toml go.mod Gemfile pubspec.yaml Makefile 2>/dev/nullThe hook directory is not always .git/hooks/. If core.hooksPath is set
(husky, lefthook), that is where hooks must live. → See guides/WIRE-THE-GATES.md.
2. Install the harness
The canonical installer is Another Agent Skills (MIT, self-hosted, stack-agnostic):
# pinned, checksum-verified release
curl -fsSL https://github.com/juandelossantos/another-agent-skills/releases/latest/download/bootstrap.sh | bash
aas install --agents autoOr, with the ecosystem CLI (installs the skills into your agent):
npx skills add juandelossantos/another-agent-skillsThen, inside the target repo:
init-agents # detects the agent + stack, writes STACK_CONFIG.md, wires the hooks3. Wire the three layers
- L1 — local hooks (
.git/hooks/or.husky/): fast, advisory feedback. - L2 — required remote
gatescheck (.github/workflows/gates.yml+ branch protection): the authority. - L3 —
CODEOWNERS: protects the gate configuration from the agent.
→ Full setup: guides/WIRE-THE-GATES.md.
4. Prove it (the whole point)
Do not claim enforcement — demonstrate it:
- Make a code change with no matching test.
git commit→ the hook must BLOCK.- Paste the blocked output as evidence.
→ guides/VERIFY-ENFORCEMENT.md.
Decision Tree
- No git? → stop. Install is convention-only; say so.
- git, no remote? → L1 only. Explain that L2 needs a GitHub remote.
- git + GitHub? → full L1 + L2 + L3.
core.hooksPathpoints elsewhere? → write hooks there, not.git/hooks/.
Anti-Patterns
- Installing gates and claiming "done" without the blocked-commit proof.
- A gate that a silent bypass file (
SKIP_*) can skip without a log. - Enforcement that depends on the agent remembering the rule.
Quick Reference
| Need | Command |
| Detect | git config core.hooksPath; ls .husky 2>/dev/null |
| Install harness | curl …/bootstrap.sh | bash && aas install --agents auto |
| Wire project | init-agents |
| Verify | git commit on an untested change → must block |
Integration
test-driven-development— the discipline this gate enforces.git-init-and-versioning— repo setup before enforcement.shipping-and-launch— the TOOL_GAP rule: never fake a green.
Verification
core.hooksPathresolved; hooks present in the directory git actually reads.- A commit without a matching test is blocked (transcript captured).
- The remote
gatescheck exists and is required by branch protection. - README install path and the gate story are documented.
Other versions28 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 28
- plugin87/ux-ui-agent-skills★ 3.1ksame name
- guardana/guardana★ 289same name
- skillberry-ai/cap-evolve★ 67same name
- assaio/assaio★ 63same name
- Cleveland-RD/hivehouse★ 46same name
- ProjectAJ14/eklavya★ 29same name
- Railly/skills★ 11same name
- BenjaminG/ai-skills★ 4same name
- dadwadw233/team-collab-skills★ 4same name
- usmanmanii/realitygate★ 4same name
18 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use checkpoint, build and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
genomewalkerSkillcheckpoint
Save a checkpoint of task status, decisions, active files, and next steps
Also in 3 projects that use this
Microsoft AzureSkillbuild
Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.
Also in 4 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 6 projects that use this
VercelSkillinvestigate
Investigate a specific issue report with strict, evidence-driven diagnosis.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 4 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 3 projects that use this
In this repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- adapt-skillSkill
- api-and-interface-designSkill
- architecture-analysisSkill
- audit-skillSkill
- backend-api-masterySkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- clarify-skillSkill
- cli-toolsSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- critique-skillSkill
- customize-opencodeSkill
- debugging-and-error-recoverySkill
- debugging-three-strikesSkill
- delight-skillSkill
- deprecation-and-migrationSkill
- dev-environment-auditSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- engineering-fundamentalsSkill
- frontend-desktopSkill
- frontend-mobileSkill
- frontend-pwaSkill
- frontend-ui-engineeringSkill
- frontend-webSkill
- fullstack-shippingSkill
- git-init-and-versioningSkill
- git-workflow-and-versioningSkill
- hard-skillSkill
- idea-refineSkill
- incremental-implementationSkill
- industrial-brutalist-uiSkill
- interview-meSkill
- minimalist-uiSkill
- multi-agent-orchestrationSkill
- observability-and-instrumentationSkill
- optimize-skillSkill
- output-skillSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- polish-skillSkill
- project-health-checkSkill
- project-metricsSkill
- redesign-skillSkill
- security-and-hardeningSkill
- self-improvementSkill
- shipping-and-launchSkill
- skill-creatorSkill
- skill-improverSkill
- soft-premium-uiSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- typeset-skillSkill
- user-onboardingSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

