synaptiaisynaptiai/bdsk/skills/gate/SKILL.md

gate

Skill0 starsChanged 7 months agoMITView on GitHub

Create a BDSK review_gate artifact. Defines a checkpoint that controls whether generated output may proceed toward acceptance. Use when defining quality, security, or scope gates for execution plans.

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

0
Common
Most of the 25 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Create a review gate artifact.
line 18
Distinctive:
If linking to behavior specs or policies, add them as upstream trace refs
line 76
Very specific:
Trace refs: MUST be {target_id: <id>, edge: <edge>} objects, not bare string IDs.
line 82
Very specific:
Approvals: MUST use {authority_role: <role>, approver: <user>, approved_at: <ISO-8601>}.
line 83
Very specific:
Do NOT use constrains upstream to behavior_spec — use depends_on
line 89

“Common” is measured: kept by at least 6 in 10 of the 25 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

/gate

Create a review gate artifact.

Input

The user provides a description of what the gate checks: $ARGUMENTS

Process

Understand the gate purpose. Determine the gate_class and subject from the user's description. Ask clarifying questions if ambiguous.
Determine gate parameters:
- gate_class: blocking (prevents acceptance), warning (allows conditional), manual-review (requires human sign-off), escalation (requires authority decision)
- subject: scope, dependencies, contracts, tests, security, architecture, other
- evaluation_method: static_check, human_review, diff_analysis, contract_check, spec_coverage, other
- fail_action: block, warn, require_manual_review, escalate
Write the artifact:

kind: review_gate
schema_version: "0.3"
id: RG-<short-slug>-<YYYYMMDD-HHMMSS>
title: <human readable gate title>
status: draft
owners:
  - <current user>
created_at: <current ISO-8601 timestamp>
updated_at: <current ISO-8601 timestamp>
trace:
  upstream: []
  downstream: []
approvals: []
metadata:
  gate_class: <blocking|warning|manual-review|escalation>
  subject: <scope|dependencies|contracts|tests|security|architecture|other>
spec:
  description: <what this gate checks>
  applies_when:
    - <condition when this gate applies>
  evaluation_method: <static_check|human_review|diff_analysis|contract_check|spec_coverage|other>
  pass_condition:
    - <condition that must be true to pass>
  fail_action: <block|warn|require_manual_review|escalate>
  evidence_required:
    - <what evidence must be provided>

Write to disk. Save to artifacts/gates/<id>.yaml
Present for review. Show the artifact to the user. Explain that running /approve <id> is how they approve it.

Rules

gate_class determines severity: blocking prevents acceptance, warning allows conditional acceptance
subject determines authority requirements: security gates require security_authority for approval
pass_condition MUST be an array of strings (not a single string)
applies_when MUST be an array of strings
evidence_required MUST be an array of strings
If linking to behavior specs or policies, add them as upstream trace refs

Schema Compliance

metadata requires exactly 2 fields: gate_class and subject. No additional fields. Schema uses additionalProperties: false.
spec requires exactly 6 fields: description, applies_when, evaluation_method, pass_condition, fail_action, evidence_required. No additional fields. Schema uses additionalProperties: false.
Trace refs MUST be {target_id: <id>, edge: <edge>} objects, not bare string IDs.
Approvals MUST use {authority_role: <role>, approver: <user>, approved_at: <ISO-8601>}. Not {date, decision}.
Valid trace edges (10 total): depends_on, derived_from, constrains, implements, proves, evaluates, produced_by, supersedes, escalates_to, waives.
Valid authority roles (5 total): product_authority, technical_authority, security_authority, release_authority, qa_authority.

Edge-kind rules for review_gate

Upstream depends_on → codegen_policy, behavior_spec
Do NOT use constrains upstream to behavior_spec — use depends_on
Downstream evaluates → execution_eval

Download now (ZIP)

Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
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
17 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.
- genomewalkerSkill
  checkpoint
  Save a checkpoint of task status, decisions, active files, and next steps
  Also in 3 projects that use this
- Microsoft AzureSkill
  build
  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
- AWSSkill
  ship
  Finalize dev work on an issue branch — update docs, push, and open a PR.
  Also in 6 projects that use this
- VercelSkill
  investigate
  Investigate a specific issue report with strict, evidence-driven diagnosis.
  Also in 3 projects that use this
- BlockSkill
  plan
  Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
  Also in 4 projects that use this
- GitHubSkill
  refactor
  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 repository11 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- acceptSkill
- approveSkill
- assumeSkill
- evaluateSkill
- plan-executionSkill
- rescopeSkill
- runSkill
- specifySkill
- validateSkill
- verifySkill

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.

Check your setup, free

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

/gate

Input

Process

Rules

Schema Compliance

Edge-kind rules for review_gate

Word for word · 0

Edited · 0

Wrote their own version · 27

checkpoint

build

ship

investigate

plan

refactor

Does it work?

Your trail

Now do this for your own.