metacircu1ar/skill_vault

2

stars

0

commits

Python

primary language

Aug 27, 2026

updated

README

hive_skills logo

hive_skills

A personal collection of agent skills, workflow references, multi-agent coordination protocols, delivery playbooks, and focused audit checklists for AI coding agents.

Contents

Top-level workflow skills and references

The standalone Markdown files directly under skills/ capture reusable agent workflows and extracted runtime behavior:

Skill or referencePurpose
advisorConfigure a smaller Claude model to consult a stronger advisor model at difficult decision points.
batchPlan and execute wide, independently mergeable changes through parallel worktree agents and separate pull requests.
code-reviewRun a multi-angle diff review with independent finding verification and optional fixes or pull-request comments.
deep-researchProduce a cited report through parallel searches, source extraction, and adversarial claim verification.
goalKeep an agent working until an evidence-backed completion condition is judged to be satisfied.
init-verifiersGenerate project-specific functional verifier skills for browser, CLI, and HTTP behavior.
professional-localizationDesign localization as an end-to-end product boundary spanning UI, server, storage, contracts, and CI.
simplifyReview a diff for reuse, simplicity, efficiency, and abstraction-level improvements, then apply the cleanup.
testable-frontendStructure frontend code and test tiers so deterministic automated testing is practical by construction.

Agent coordination skills

The repository contains both lightweight file-protocol coordination skills and Hive-backed skills that use named registry implementors, parallel reviewer panels, durable workflow artifacts, and bounded multi-repository execution.

SkillPurpose
code-review-loopCoordinate an implementor and persistent reviewer through session-isolated frozen-diff cycles, NO_FINDINGS work-item boundaries, and caller- or implementor-controlled session completion; the protocol includes TLA+ state-machine verification.
parallel-code-review-loopSchedule multiple independent code-review-loop pairs across distinct repository working paths, pass shared and assignment-specific context to implementors, enforce per-pair startup order, and wait for all pairs to terminate. See the one-workspace, N-repository example.
hive-review-loopRun one repository through a named hive_registry implementor and a configurable parallel reviewer panel using hive_workflow; it launches no Codex subagents.
hive-parallel-review-loopRun multiple disjoint repository review loops as bounded concurrent hive_workflow processes, with shared defaults and per-assignment registry-agent overrides in YAML.

For one pair, invoke code-review-loop on both agents with the appropriate role:

/code-review-loop implementor
/code-review-loop reviewer

Omitting completion authority on the implementor defaults it to completion-authority=implementor. The reviewer has no completion-authority input. Use completion-authority=caller only on the implementor when an enclosing workflow, such as an epic implementor, must keep the reviewer alive across multiple work items and close the session itself. Continue such a session by resuming the same initialized implementor role; a fresh implementor invocation would perform startup cleanup and must begin a new session instead.

For multiple independent repositories, invoke parallel-code-review-loop on one orchestrator with its input manifest. The orchestrator validates disjoint repository roots and complete-pair capacity, then launches one code-review-loop implementor/reviewer pair per repository. Install the complete directories for both coordination skills because the parallel wrapper depends on the base protocol and its scripts.

For provider-neutral agent panels, use the Hive-backed variants. They call hive_registry and hive_workflow directly and never create Codex subagents. hive-review-loop runs one registry implementor with one or more parallel registry reviewers; hive-parallel-review-loop runs that topology across multiple repositories from one YAML manifest.

Git history skills

SkillPurpose
verified-commit-splitSplit uncommitted work, one commit, or a contiguous commit range into logical commits while proving final tree identity against a protected backup.

Product delivery skills

skills/product-delivery-skills/ contains four self-contained, installable skills:

SkillPurpose
product-implementation-plannerTurn a product description and repository evidence into a phased implementation plan.
product-plan-compilerCompile a detailed product plan into formal models, run relevant provers and model checkers, and refine inconsistencies before implementation.
parallel-plan-implementationImplement an approved plan through controlled, dependency-aware parallel phases.
phase-commit-reviewerPerform a read-only, phase-aware review of one implementation commit.

The default delivery sequence is product-implementation-plannerproduct-plan-compilerparallel-plan-implementationphase-commit-reviewer.

Across that sequence, the main stage orchestrator maintains docs/implementation-plan/delivery-status.md as a concise, derived human view of scope, stage outcomes, decisions, blockers, and evidence links. It remains non-authoritative, and the operator is explicitly told its path and any required action after planning, formal verification, implementation, and optional review.

Each product-delivery skill includes its supporting references, templates, schemas, scripts, and a dedicated README.

Audit skills

skills/audit/ contains focused audit playbooks. Each one is intended to produce concrete findings with file paths, line numbers, impact, and suggested fixes.

SkillPurpose
audit-input-validationAudit client and server validation for user-controlled input.
audit-auth-and-access-controlAudit auth flows, sessions, roles, admin routes, and cross-user data isolation.
audit-secrets-and-configAudit hardcoded secrets, environment validation, and webhook signatures.
audit-rate-limitingAudit API-route rate-limit coverage and policy fit.
audit-corsAudit CORS configuration and origin allowlists.
audit-database-performanceAudit indexes, pagination, unbounded queries, and connection-pool risks.
audit-resilience-and-observabilityAudit error boundaries, external I/O, health checks, logs, and backups.
audit-asset-pipelineAudit uploads, storage, CDN/object storage, and asset delivery.
audit-type-safetyAudit TypeScript safety bypasses and unchecked external data.
security-reviewRun an umbrella security review composed from focused web skills.
ios-prelaunch-checklistAudit iOS App Store assets, technical setup, legal readiness, and signing.

Use

Clone the repository and copy the skill or reference you need into the directory expected by your agent runtime:

skills/<standalone-workflow>-skill.md
skills/code-review-loop/
skills/parallel-code-review-loop/
skills/hive-review-loop/
skills/hive-parallel-review-loop/
skills/verified-commit-split/
skills/product-delivery-skills/<skill-name>/
skills/audit/<skill-name>/

Repository layout

skills/*-skill.md               Standalone workflow skills and references
skills/code-review-loop/         Two-agent implementation/review coordination skill
skills/code-review-loop/verification/  TLA+ model, checks, and reproducibility notes
skills/parallel-code-review-loop/  Multi-repository orchestration over isolated review pairs
skills/hive-review-loop/       Hive-backed implementation and reviewer-panel loop
skills/hive-parallel-review-loop/  Bounded multi-repository Hive workflow launcher
skills/verified-commit-split/    Content-preserving Git commit-splitting skill
skills/audit/                    Focused audit skills
skills/product-delivery-skills/  Self-contained product-delivery skills
LICENSE                          MIT license

metacircu1ar/skill_vault

2

stars

0

commits

Python

primary language

Aug 27, 2026

updated

README

hive_skills logo

hive_skills

A personal collection of agent skills, workflow references, multi-agent coordination protocols, delivery playbooks, and focused audit checklists for AI coding agents.

Contents

Top-level workflow skills and references

The standalone Markdown files directly under skills/ capture reusable agent workflows and extracted runtime behavior:

Skill or referencePurpose
advisorConfigure a smaller Claude model to consult a stronger advisor model at difficult decision points.
batchPlan and execute wide, independently mergeable changes through parallel worktree agents and separate pull requests.
code-reviewRun a multi-angle diff review with independent finding verification and optional fixes or pull-request comments.
deep-researchProduce a cited report through parallel searches, source extraction, and adversarial claim verification.
goalKeep an agent working until an evidence-backed completion condition is judged to be satisfied.
init-verifiersGenerate project-specific functional verifier skills for browser, CLI, and HTTP behavior.
professional-localizationDesign localization as an end-to-end product boundary spanning UI, server, storage, contracts, and CI.
simplifyReview a diff for reuse, simplicity, efficiency, and abstraction-level improvements, then apply the cleanup.
testable-frontendStructure frontend code and test tiers so deterministic automated testing is practical by construction.

Agent coordination skills

The repository contains both lightweight file-protocol coordination skills and Hive-backed skills that use named registry implementors, parallel reviewer panels, durable workflow artifacts, and bounded multi-repository execution.

SkillPurpose
code-review-loopCoordinate an implementor and persistent reviewer through session-isolated frozen-diff cycles, NO_FINDINGS work-item boundaries, and caller- or implementor-controlled session completion; the protocol includes TLA+ state-machine verification.
parallel-code-review-loopSchedule multiple independent code-review-loop pairs across distinct repository working paths, pass shared and assignment-specific context to implementors, enforce per-pair startup order, and wait for all pairs to terminate. See the one-workspace, N-repository example.
hive-review-loopRun one repository through a named hive_registry implementor and a configurable parallel reviewer panel using hive_workflow; it launches no Codex subagents.
hive-parallel-review-loopRun multiple disjoint repository review loops as bounded concurrent hive_workflow processes, with shared defaults and per-assignment registry-agent overrides in YAML.

For one pair, invoke code-review-loop on both agents with the appropriate role:

/code-review-loop implementor
/code-review-loop reviewer

Omitting completion authority on the implementor defaults it to completion-authority=implementor. The reviewer has no completion-authority input. Use completion-authority=caller only on the implementor when an enclosing workflow, such as an epic implementor, must keep the reviewer alive across multiple work items and close the session itself. Continue such a session by resuming the same initialized implementor role; a fresh implementor invocation would perform startup cleanup and must begin a new session instead.

For multiple independent repositories, invoke parallel-code-review-loop on one orchestrator with its input manifest. The orchestrator validates disjoint repository roots and complete-pair capacity, then launches one code-review-loop implementor/reviewer pair per repository. Install the complete directories for both coordination skills because the parallel wrapper depends on the base protocol and its scripts.

For provider-neutral agent panels, use the Hive-backed variants. They call hive_registry and hive_workflow directly and never create Codex subagents. hive-review-loop runs one registry implementor with one or more parallel registry reviewers; hive-parallel-review-loop runs that topology across multiple repositories from one YAML manifest.

Git history skills

SkillPurpose
verified-commit-splitSplit uncommitted work, one commit, or a contiguous commit range into logical commits while proving final tree identity against a protected backup.

Product delivery skills

skills/product-delivery-skills/ contains four self-contained, installable skills:

SkillPurpose
product-implementation-plannerTurn a product description and repository evidence into a phased implementation plan.
product-plan-compilerCompile a detailed product plan into formal models, run relevant provers and model checkers, and refine inconsistencies before implementation.
parallel-plan-implementationImplement an approved plan through controlled, dependency-aware parallel phases.
phase-commit-reviewerPerform a read-only, phase-aware review of one implementation commit.

The default delivery sequence is product-implementation-plannerproduct-plan-compilerparallel-plan-implementationphase-commit-reviewer.

Across that sequence, the main stage orchestrator maintains docs/implementation-plan/delivery-status.md as a concise, derived human view of scope, stage outcomes, decisions, blockers, and evidence links. It remains non-authoritative, and the operator is explicitly told its path and any required action after planning, formal verification, implementation, and optional review.

Each product-delivery skill includes its supporting references, templates, schemas, scripts, and a dedicated README.

Audit skills

skills/audit/ contains focused audit playbooks. Each one is intended to produce concrete findings with file paths, line numbers, impact, and suggested fixes.

SkillPurpose
audit-input-validationAudit client and server validation for user-controlled input.
audit-auth-and-access-controlAudit auth flows, sessions, roles, admin routes, and cross-user data isolation.
audit-secrets-and-configAudit hardcoded secrets, environment validation, and webhook signatures.
audit-rate-limitingAudit API-route rate-limit coverage and policy fit.
audit-corsAudit CORS configuration and origin allowlists.
audit-database-performanceAudit indexes, pagination, unbounded queries, and connection-pool risks.
audit-resilience-and-observabilityAudit error boundaries, external I/O, health checks, logs, and backups.
audit-asset-pipelineAudit uploads, storage, CDN/object storage, and asset delivery.
audit-type-safetyAudit TypeScript safety bypasses and unchecked external data.
security-reviewRun an umbrella security review composed from focused web skills.
ios-prelaunch-checklistAudit iOS App Store assets, technical setup, legal readiness, and signing.

Use

Clone the repository and copy the skill or reference you need into the directory expected by your agent runtime:

skills/<standalone-workflow>-skill.md
skills/code-review-loop/
skills/parallel-code-review-loop/
skills/hive-review-loop/
skills/hive-parallel-review-loop/
skills/verified-commit-split/
skills/product-delivery-skills/<skill-name>/
skills/audit/<skill-name>/

Repository layout

skills/*-skill.md               Standalone workflow skills and references
skills/code-review-loop/         Two-agent implementation/review coordination skill
skills/code-review-loop/verification/  TLA+ model, checks, and reproducibility notes
skills/parallel-code-review-loop/  Multi-repository orchestration over isolated review pairs
skills/hive-review-loop/       Hive-backed implementation and reviewer-panel loop
skills/hive-parallel-review-loop/  Bounded multi-repository Hive workflow launcher
skills/verified-commit-split/    Content-preserving Git commit-splitting skill
skills/audit/                    Focused audit skills
skills/product-delivery-skills/  Self-contained product-delivery skills
LICENSE                          MIT license

Languages

Python

89.7%

TLA

8.4%

Shell

1.9%