Menu
SkillsMP has collected 24 skills from gootf/software-agent-sop. Open a skill to review its source and details.
Showing 24 of 24 collected skills.
Methodology for designing, building, and validating an AI-agent skill workflow — the design principles behind production workflow graphs (routing/evidence/synthesis/gates/recovery/knowledge loops), a 7-phase build loop with a pass/fail gate on every phase,…
This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent…
Deeply analyze codebase architecture and dependencies. Use when understanding system design, finding patterns, or mapping how components interact.
Comprehensive project consistency review across code, documentation, diagrams, and configuration
Ask which skill or flow fits your situation. A router over the skills in this repo.
Maintain durable repository memory for architecture and technical decisions using ADRs, decision candidates, and update/supersede checks. Use when reviewing architecture changes, service boundaries, API contracts, runtime choices, security/deploy decisions,…
Structured 6-section delegation template and session-continuity rules for orchestrating sub-agents. Load before spawning any agent.
Analyze project dependencies for health, security, and bloat — audit outdated, deprecated, vulnerable, duplicate, heavy, and unused packages across npm, pip, cargo, go mod, and more. Produce a dependency health score, CVE inventory, license compatibility…
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Workflow skill for proactively updating stale docs and fixing docs path/layout drift. Use when: docs in README.md or docs/** are outdated, command usage has changed, or documentation file/folder placement changed.
Produce the engineering closeout report for a completed work unit — final status, changed files, tests, release state, docs state, remaining issues, next steps — with a completion gate. Use when implementation and verification are done and the work must be…
GitHub PR lifecycle: branch, commit, open, CI, merge.
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or…
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents…
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Manage the project rolling context file for team-shared codebase knowledge
Use when a project needs multi-session retrospective analysis — after milestones, before starting a new phase, when vision drift is suspected, or every 3-5 sessions. Triggers: user says "retro", "run a retro", "since-last-retro"; asks to analyze patterns,…
Pre-commit review: security scan, quality gates, auto-fix.
[discovery-phase pack · scoping] High-level solution design as a discovery deliverable — system context, logical components, data flow, integrations, NFRs (perf/scale/security/SLA), and tech-stack rationale. Not detailed design; feeds estimation and surfaces…
Use when executing implementation plans with independent tasks in the current session
Synthesize upstream artifacts (requirements, source evidence, architecture/dependency/design findings, readiness) into candidate entries for PROJECT-CONTEXT.md — the S10 synthesis step that the project-context carrier format lacks. Use when multiple upstream…
Use at the beginning of a new task. Ensures you fully understand the requirements, boundaries, and acceptance criteria before writing code.
Define an agent workflow graph as a first-class engineering artifact — workflow.yaml schema (mermaid-flowchart-flavored: node blocks + explicit edge list), validation rules (pass/fail gates), and a zero-dependency validator script for CI. Use when creating or…
Execute a workflow.yaml graph — the scheduler protocol: validate the graph, topologically order nodes, execute each node via its skill, carry artifacts, apply gates/branches/loops/skips, persist state to .workflow/state.json, resume from checkpoints, and…