--- title: "baseline" description: "The portable minimum for disciplined, proportional software engineering" canonical: https://agentpluginsdirectory.com/plugins/baseline last-updated: 2026-09-25 --- # baseline The portable minimum for disciplined, proportional software engineering - Slug: baseline - Publisher: William Oliveira - Repository: https://github.com/woliveiras/baseline - Manifest: plugins/baseline/plugin.json - Version: 0.5.0 - License: MIT - Category (editorial): code-review - Skills: 18 (brainstorming, bugfix, ci-workflow, decision-framework, design-deep-modules, docs, git-commit, improve-architecture, measurer, premortem, refine, security-review, session-bridge, setup-baseline, shape-domain, tdd, technical-research, verify) - MCP servers: 0 - Stars: 6 - Repository created: 2026-08-04 - Repository last pushed: 2026-08-19 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/baseline - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What baseline does, in the publisher's words Baseline is the portable minimum for disciplined software engineering. It is a set of Agent Skills that helps coding agents measure work by risk, clarify real ambiguity, test behavior first, review changes proportionally, and keep Git authority explicit. Baseline is loaded by your agent on demand. It does not add a CLI, runtime, or project dependency. Baseline follows the open Agent Skills and Agent Plugins specifications. Agent Skills defines the canonical content, Agent Plugins defines the open package, and thin native adapters add lifecycle integration only where a client requires it. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/woliveiras/baseline/HEAD/README.md ## Skills - brainstorming: Explore a software problem space deeply before choosing a direction. Use when the user explicitly asks to explore materially different alternatives, hidden assumptions, or opportunity discovery before selecting a design, even without naming this skill. This owns the divergent phase over refine; sec… - bugfix: Diagnose and repair an existing software defect through bug report, reproduction, fail-first regression test, causal fix, and focused review. Use for reported incorrect, regressed, or intermittent existing behavior; this workflow owns its regression check, so do not also invoke tdd unless separatel… - ci-workflow: Create, review, or repair CI pipelines and workflows, including GitHub Actions, that produce traceable quality evidence with least privilege. Use for test, lint, build, cache, artifact, release, deploy, fork, secret, or workflow-permission automation; compose with security-review for untrusted inpu… - decision-framework: Make a material software decision with explicit options, evidence types, uncertainty, dependencies, reversibility, and validation. Use when several viable paths remain after refinement; do not use to add ceremony to routine reversible choices. - design-deep-modules: Design or compare concrete high-leverage module boundaries with small stable interfaces, hidden complexity, explicit seams, adapters, locality, and reversible migration. Use when the request asks for boundary or interface design; not for whole-architecture audits or requests that explicitly defer n… - docs: Maintain the smallest durable software documentation surface for shipped behavior, architecture, decisions, operations, incidents, and non-obvious code reasons. Use when knowledge must outlive the current task; do not create documentation for routine reversible work or narrate self-explanatory code. - git-commit: Create a safe atomic local Git commit from a verified task-owned slice using Conventional Commits. Use only when the user explicitly requests a local commit or explicitly asks to follow a repository contract that requires one; do not use when the request says not to commit, or for push, amend, reba… - improve-architecture: Audit a codebase for evidence-backed architecture improvements, leverage, seams, locality, and reversibility. Use when the user explicitly requests an assessment of the existing architecture, including when the request defers new module-boundary design; do not implement changes, create a refactor s… - measurer: Classify software work by risk, boundaries, reversibility, ambiguity, validation difficulty, and rollout exposure, then route only the proportional refinement, documentation, and review depth. Use implicitly at the start of software implementation, repair, review, or delivery work; do not use line… - premortem: Anticipate plausible failure modes for a proposed software change and convert them into proportional mitigations, expected checks, detection, and rollback. Use before committing to medium or high-risk work; do not use to generate generic risk lists for trivial changes. - refine: Resolve material ambiguity in a software request with a proportional decision tree. Invoke from incompatible interpretations even without naming this skill; do not use because a task is large or when repository evidence already makes the path clear. - security-review: Review a software change or CI workflow for technology-neutral security, privacy, data-loss, and authority risks using verifiable evidence. Use for trust boundaries, untrusted or fork-controlled input, secrets, sensitive data, permissions, privileges, or destructive and external actions. This owns… - session-bridge - setup-baseline - shape-domain - tdd - technical-research - verify Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.