I reviewed OpenCode's docs, the OpenCode GitHub repo, recent writeups, and a large set of public skills and commands people share for OpenCode, Claude Code, Codex, and related tools. A clear pattern showed up quickly. The useful ideas are small, concrete workflows that improve routine engineering work: planning, debugging, review, verification, context loading, and memory capture. So this is not a big theory piece. It is a compact collection of skills and commands worth reusing. Start with this rule The best skill is the one you make yourself to automate your own routine. Public skills are useful because they give you working patterns. The real payoff comes when you turn your repeated work into a reusable skill or command: the way your team reviews migrations the checks you run before a release the steps you use during incident response the handoff format you expect before a PR the way your team reviews migrations the checks you run before a release the steps you use during incident response the handoff format you expect before a PR That is where skills stop being a demo and start becoming infrastructure. Skills worth reusing These are listed in rough priority order. Name Why it made the list Source systematic-debugging Strong rule set for real debugging. It forces root-cause investigation before fixes. obra/superpowers verification-before-completion High-value finishing skill. No success claim without fresh evidence. obra/superpowers test-driven-development Useful because agents often skip the failing-test step and then rationalize it later. obra/superpowers implementation-strategy Good before runtime, API, or migration work. It forces design decisions before edits. OpenAI blog ask-questions-if-underspecified Good behavior-shaping skill. It keeps the agent from charging ahead on vague requirements. trailofbits/skills code-change-verification Practical repo skill. Run the exact verification stack when code or build behavior changed. OpenAI blog writing-plans Turns a fuzzy task into a concrete execution plan with files, tests, and checkpoints. obra/superpowers using-git-worktrees Good isolation skill for parallel work, experiments, and larger agent-driven changes. obra/superpowers dispatching-parallel-agents One of the better public playbooks for splitting independent tasks across agents. obra/superpowers receiving-code-review Teaches the agent to verify review feedback instead of blindly applying it. obra/superpowers Name Why it made the list Source systematic-debugging Strong rule set for real debugging. It forces root-cause investigation before fixes. obra/superpowers verification-before-completion High-value finishing skill. No success claim without fresh evidence. obra/superpowers test-driven-development Useful because agents often skip the failing-test step and then rationalize it later. obra/superpowers implementation-strategy Good before runtime, API, or migration work. It forces design decisions before edits. OpenAI blog ask-questions-if-underspecified Good behavior-shaping skill. It keeps the agent from charging ahead on vague requirements. trailofbits/skills code-change-verification Practical repo skill. Run the exact verification stack when code or build behavior changed. OpenAI blog writing-plans Turns a fuzzy task into a concrete execution plan with files, tests, and checkpoints. obra/superpowers using-git-worktrees Good isolation skill for parallel work, experiments, and larger agent-driven changes. obra/superpowers dispatching-parallel-agents One of the better public playbooks for splitting independent tasks across agents. obra/superpowers receiving-code-review Teaches the agent to verify review feedback instead of blindly applying it. obra/superpowers Name Why it made the list Source Name Name Why it made the list Why it made the list Source Source systematic-debugging Strong rule set for real debugging. It forces root-cause investigation before fixes. obra/superpowers systematic-debugging systematic-debugging systematic-debugging Strong rule set for real debugging. It forces root-cause investigation before fixes. Strong rule set for real debugging. It forces root-cause investigation before fixes. obra/superpowers obra/superpowers obra/superpowers verification-before-completion High-value finishing skill. No success claim without fresh evidence. obra/superpowers verification-before-completion verification-before-completion verification-before-completion High-value finishing skill. No success claim without fresh evidence. High-value finishing skill. No success claim without fresh evidence. obra/superpowers obra/superpowers obra/superpowers test-driven-development Useful because agents often skip the failing-test step and then rationalize it later. obra/superpowers test-driven-development test-driven-development test-driven-development Useful because agents often skip the failing-test step and then rationalize it later. Useful because agents often skip the failing-test step and then rationalize it later. obra/superpowers obra/superpowers obra/superpowers implementation-strategy Good before runtime, API, or migration work. It forces design decisions before edits. OpenAI blog implementation-strategy implementation-strategy implementation-strategy Good before runtime, API, or migration work. It forces design decisions before edits. Good before runtime, API, or migration work. It forces design decisions before edits. OpenAI blog OpenAI blog OpenAI blog ask-questions-if-underspecified Good behavior-shaping skill. It keeps the agent from charging ahead on vague requirements. trailofbits/skills ask-questions-if-underspecified ask-questions-if-underspecified ask-questions-if-underspecified Good behavior-shaping skill. It keeps the agent from charging ahead on vague requirements. Good behavior-shaping skill. It keeps the agent from charging ahead on vague requirements. trailofbits/skills trailofbits/skills trailofbits/skills code-change-verification Practical repo skill. Run the exact verification stack when code or build behavior changed. OpenAI blog code-change-verification code-change-verification code-change-verification Practical repo skill. Run the exact verification stack when code or build behavior changed. Practical repo skill. Run the exact verification stack when code or build behavior changed. OpenAI blog OpenAI blog OpenAI blog writing-plans Turns a fuzzy task into a concrete execution plan with files, tests, and checkpoints. obra/superpowers writing-plans writing-plans writing-plans Turns a fuzzy task into a concrete execution plan with files, tests, and checkpoints. Turns a fuzzy task into a concrete execution plan with files, tests, and checkpoints. obra/superpowers obra/superpowers obra/superpowers using-git-worktrees Good isolation skill for parallel work, experiments, and larger agent-driven changes. obra/superpowers using-git-worktrees using-git-worktrees using-git-worktrees Good isolation skill for parallel work, experiments, and larger agent-driven changes. Good isolation skill for parallel work, experiments, and larger agent-driven changes. obra/superpowers obra/superpowers obra/superpowers dispatching-parallel-agents One of the better public playbooks for splitting independent tasks across agents. obra/superpowers dispatching-parallel-agents dispatching-parallel-agents dispatching-parallel-agents One of the better public playbooks for splitting independent tasks across agents. One of the better public playbooks for splitting independent tasks across agents. obra/superpowers obra/superpowers obra/superpowers receiving-code-review Teaches the agent to verify review feedback instead of blindly applying it. obra/superpowers receiving-code-review receiving-code-review receiving-code-review Teaches the agent to verify review feedback instead of blindly applying it. Teaches the agent to verify review feedback instead of blindly applying it. obra/superpowers obra/superpowers obra/superpowers Good runners-up: docs-sync for keeping docs aligned with code changeset-validation for JS monorepos and release hygiene openai-knowledge as a pattern for "use current docs, not memory" variant-analysis for security and bug sibling hunting docs-sync for keeping docs aligned with code docs-sync changeset-validation for JS monorepos and release hygiene changeset-validation openai-knowledge as a pattern for "use current docs, not memory" openai-knowledge variant-analysis for security and bug sibling hunting variant-analysis Commands worth reusing These are the commands I would look at first when setting up an OpenCode repo. Name Why it made the list Source /learn Best memory pattern I found. It writes non-obvious lessons into the right AGENTS.md. OpenCode repo /finish-work Strong pre-commit gate covering code quality, docs, API, DB, cross-layer impact, and manual checks. Trellis /check-cross-layer Catches a common failure: one layer changed, another one was missed. Trellis /context-prime Small but effective bootstrap command. Load enough repo context before real work starts. just-prompt /careful-review Forces a fresh-eyes pass before the work gets called done. harperreed/dotfiles /update-spec Good companion to /learn. Captures design decisions and hard-won lessons in living specs. Trellis /find-missing-tests Useful when the code works but the safety net is thin. harperreed/dotfiles /race and pick Run isolated implementations in parallel, then choose a winner or merge ideas. cook /session-summary Good handoff command. Capture actions, cost, inefficiency, and next improvements. harperreed/dotfiles /harness-audit Useful meta-command for checking the agent stack itself: tools, quality gates, memory, security, and cost. everything-claude-code Name Why it made the list Source /learn Best memory pattern I found. It writes non-obvious lessons into the right AGENTS.md. OpenCode repo /finish-work Strong pre-commit gate covering code quality, docs, API, DB, cross-layer impact, and manual checks. Trellis /check-cross-layer Catches a common failure: one layer changed, another one was missed. Trellis /context-prime Small but effective bootstrap command. Load enough repo context before real work starts. just-prompt /careful-review Forces a fresh-eyes pass before the work gets called done. harperreed/dotfiles /update-spec Good companion to /learn. Captures design decisions and hard-won lessons in living specs. Trellis /find-missing-tests Useful when the code works but the safety net is thin. harperreed/dotfiles /race and pick Run isolated implementations in parallel, then choose a winner or merge ideas. cook /session-summary Good handoff command. Capture actions, cost, inefficiency, and next improvements. harperreed/dotfiles /harness-audit Useful meta-command for checking the agent stack itself: tools, quality gates, memory, security, and cost. everything-claude-code Name Why it made the list Source Name Name Why it made the list Why it made the list Source Source /learn Best memory pattern I found. It writes non-obvious lessons into the right AGENTS.md. OpenCode repo /learn /learn /learn Best memory pattern I found. It writes non-obvious lessons into the right AGENTS.md. Best memory pattern I found. It writes non-obvious lessons into the right AGENTS.md. AGENTS.md OpenCode repo OpenCode repo OpenCode repo /finish-work Strong pre-commit gate covering code quality, docs, API, DB, cross-layer impact, and manual checks. Trellis /finish-work /finish-work /finish-work Strong pre-commit gate covering code quality, docs, API, DB, cross-layer impact, and manual checks. Strong pre-commit gate covering code quality, docs, API, DB, cross-layer impact, and manual checks. Trellis Trellis Trellis /check-cross-layer Catches a common failure: one layer changed, another one was missed. Trellis /check-cross-layer /check-cross-layer /check-cross-layer Catches a common failure: one layer changed, another one was missed. Catches a common failure: one layer changed, another one was missed. Trellis Trellis Trellis /context-prime Small but effective bootstrap command. Load enough repo context before real work starts. just-prompt /context-prime /context-prime /context-prime Small but effective bootstrap command. Load enough repo context before real work starts. Small but effective bootstrap command. Load enough repo context before real work starts. just-prompt just-prompt just-prompt /careful-review Forces a fresh-eyes pass before the work gets called done. harperreed/dotfiles /careful-review /careful-review /careful-review Forces a fresh-eyes pass before the work gets called done. Forces a fresh-eyes pass before the work gets called done. harperreed/dotfiles harperreed/dotfiles harperreed/dotfiles /update-spec Good companion to /learn. Captures design decisions and hard-won lessons in living specs. Trellis /update-spec /update-spec /update-spec Good companion to /learn. Captures design decisions and hard-won lessons in living specs. Good companion to /learn. Captures design decisions and hard-won lessons in living specs. /learn Trellis Trellis Trellis /find-missing-tests Useful when the code works but the safety net is thin. harperreed/dotfiles /find-missing-tests /find-missing-tests /find-missing-tests Useful when the code works but the safety net is thin. Useful when the code works but the safety net is thin. harperreed/dotfiles harperreed/dotfiles harperreed/dotfiles /race and pick Run isolated implementations in parallel, then choose a winner or merge ideas. cook /race and pick /race and pick /race pick Run isolated implementations in parallel, then choose a winner or merge ideas. Run isolated implementations in parallel, then choose a winner or merge ideas. cook cook cook /session-summary Good handoff command. Capture actions, cost, inefficiency, and next improvements. harperreed/dotfiles /session-summary /session-summary /session-summary Good handoff command. Capture actions, cost, inefficiency, and next improvements. Good handoff command. Capture actions, cost, inefficiency, and next improvements. harperreed/dotfiles harperreed/dotfiles harperreed/dotfiles /harness-audit Useful meta-command for checking the agent stack itself: tools, quality gates, memory, security, and cost. everything-claude-code /harness-audit /harness-audit /harness-audit Useful meta-command for checking the agent stack itself: tools, quality gates, memory, security, and cost. Useful meta-command for checking the agent stack itself: tools, quality gates, memory, security, and cost. everything-claude-code everything-claude-code everything-claude-code Good runners-up: /generate-command-diff for porting command improvements across repos /catchup for rebuilding branch context after clearing a session /orchestrate for multi-agent coordination when the task is large enough to justify it /generate-command-diff for porting command improvements across repos /generate-command-diff /catchup for rebuilding branch context after clearing a session /catchup /orchestrate for multi-agent coordination when the task is large enough to justify it /orchestrate A small starter pack Most teams do not need a huge command catalog. This is a good first pack: AGENTS.md .opencode/ commands/ learn.md finish-work.md careful-review.md session-summary.md skills/ systematic-debugging/SKILL.md verification-before-completion/SKILL.md ask-questions-if-underspecified/SKILL.md writing-plans/SKILL.md AGENTS.md .opencode/ commands/ learn.md finish-work.md careful-review.md session-summary.md skills/ systematic-debugging/SKILL.md verification-before-completion/SKILL.md ask-questions-if-underspecified/SKILL.md writing-plans/SKILL.md Then add a few rules to AGENTS.md: AGENTS.md use systematic-debugging for bugs and failed tests use ask-questions-if-underspecified before ambiguous implementation work use verification-before-completion before saying work is done run /finish-work and /careful-review before commit or PR handoff use systematic-debugging for bugs and failed tests systematic-debugging use ask-questions-if-underspecified before ambiguous implementation work ask-questions-if-underspecified use verification-before-completion before saying work is done verification-before-completion run /finish-work and /careful-review before commit or PR handoff /finish-work /careful-review That is already enough to improve how an agent behaves inside a real repo. Final note The good part of this ecosystem is that you do not need to invent everything from scratch. There are already plenty of strong public patterns. Reuse them. Trim them down. Adapt them to your own repo. And remember the main rule: the best skills are the ones that describe your team's repetitive tasks. Sources OpenCode docs: opencode.ai/docs OpenCode repo: anomalyco/opencode OpenCode /learn: raw file obra/superpowers skills: repo OpenAI's skills writeup for the Agents SDK repos: blog post Claude Code skills docs: docs cook, for race and pick: project page OpenCode docs: opencode.ai/docs OpenCode docs: opencode.ai/docs opencode.ai/docs OpenCode repo: anomalyco/opencode OpenCode repo: anomalyco/opencode anomalyco/opencode OpenCode /learn: raw file OpenCode /learn: raw file /learn raw file obra/superpowers skills: repo obra/superpowers skills: repo repo OpenAI's skills writeup for the Agents SDK repos: blog post OpenAI's skills writeup for the Agents SDK repos: blog post blog post Claude Code skills docs: docs Claude Code skills docs: docs docs cook, for race and pick: project page cook, for race and pick: project page race pick project page
