Industry

Software engineering

How professionals in Software engineering instruct their AI tools — browse what works in the field, scanned and sealed.

155 published items · Filter in browse

Prompt✓ sealedCC0-1.0

Security auditor

Claude Code subagent (.claude/agents/security-auditor.md). Read-only subagent that traces untrusted input to dangerous sinks across a diff or module and reports severity-rated vulnerabilities with fixes.

Prompt✓ sealedMIT

Security auditor subagent (wshobson)

Claude Code subagent (.claude/agents/security-auditor.md). Claude Code subagent for security audits: threat modelling, OWASP, OAuth2/OIDC, secrets, dependency and container scanning, compliance reporting.

Prompt✓ sealedCC0-1.0

Release manager

Claude Code subagent (.claude/agents/release-manager.md). Subagent that prepares a release - verifies tree and CI, computes the semver bump from merged changes, updates version and changelog files, and tags locally without pushing.

Prompt✓ sealedMIT

Python pro subagent (wshobson)

Claude Code subagent (.claude/agents/python-pro.md). Claude Code subagent for modern Python 3.12+: uv, ruff, pydantic, FastAPI, asyncio, typing and production practices.

Prompt✓ sealedCC0-1.0

Performance profiler

Claude Code subagent (.claude/agents/performance-profiler.md). Subagent that measures before guessing - establishes a baseline, profiles with the stack's native tools, identifies the top hotspots, and proposes fixes with expected and measured gains.

Prompt✓ sealedCC0-1.0

Migration planner

Claude Code subagent (.claude/agents/migration-planner.md). Read-only subagent that inventories everything a migration touches (framework, library, schema, or API version) and produces a phased, reversible plan with risks and verification steps.

Prompt✓ sealedCC0-1.0

Docs writer

Claude Code subagent (.claude/agents/docs-writer.md). Subagent that writes or updates README sections, API references, and how-to guides from the code itself, verifying every command and example against the repository.

Prompt✓ sealedCC0-1.0

Dependency auditor

Claude Code subagent (.claude/agents/dependency-auditor.md). Read-only subagent that audits a project's dependency tree for known vulnerabilities, abandoned or risky packages, license conflicts, and lockfile drift, and returns a prioritized remediation list.

Prompt✓ sealedCC0-1.0

Debugger

Claude Code subagent (.claude/agents/debugger.md). Subagent that reproduces a failure, isolates the root cause with evidence, applies a minimal fix, verifies it, and reports cause, fix, and prevention.

Prompt✓ sealedMIT

Debugger subagent (VoltAgent)

Claude Code subagent (.claude/agents/debugger.md). Claude Code subagent for systematic debugging: symptom gathering, hypotheses, isolation, root-cause analysis and verified fixes, on sonnet.

Prompt✓ sealedMIT

Debug mode (Copilot agent)

Claude Code subagent (.github/agents/debug.agent.md). Copilot custom agent that debugs in phases: assess, reproduce, isolate, fix, verify and document, running tests and reading terminal output along the way.

Prompt✓ sealedMIT

Critical thinking mode (Copilot agent)

Claude Code subagent (.github/agents/critical-thinking.agent.md). Copilot custom agent that challenges assumptions and keeps asking why instead of writing code; use before design decisions and big refactors.

Prompt✓ sealedCC0-1.0

Code reviewer

Claude Code subagent (.claude/agents/code-reviewer.md). Read-only subagent that reviews a diff for correctness, edge cases, and maintainability and returns prioritized findings with file:line and fixes.

Prompt✓ sealedMIT

Code reviewer subagent (wshobson)

Claude Code subagent (.claude/agents/code-reviewer.md). Claude Code subagent for comprehensive code review: security, performance, reliability, maintainability and test coverage with a structured report.

Prompt✓ sealedMIT

Architect review subagent (wshobson)

Claude Code subagent (.claude/agents/architect-review.md). Claude Code subagent that reviews designs and changes for architectural integrity: clean/hexagonal architecture, service boundaries, DDD, SOLID, cloud-native and security, with High/Medium/Low impact.

Skill✓ sealedMIT

Verification Before Completion (superpowers skill)

Jesse Vincent's skill that forbids claiming success without running the verification command and reading its output first; evidence before assertions.

Skill✓ sealedMIT

Test-Driven Development (superpowers skill)

Jesse Vincent's TDD skill: the iron law (watch the test fail first), red-green-refactor steps, rationalization red flags and a guide to writing good tests.

Skill✓ sealedCC0-1.0

TDD red/green/refactor loop

Strict red/green/refactor loop with a behavior list, one failing test at a time, and explicit stop points for user confirmation.

Skill✓ sealedMIT

Systematic Debugging (superpowers skill)

Jesse Vincent's debugging skill: four-phase root-cause process, root-cause tracing, defense in depth, condition-based waiting, and a test-polluter finder script.

Skill✓ sealedCC0-1.0

Suggesting Skills

When the user struggles with a task that a known skill could handle, suggest installing or using a skill from the project's `.agents/skills/` directory.

Skill✓ sealedCC0-1.0

SQL query explainer and optimizer

Explains a SQL query clause by clause, reads EXPLAIN output for scans, misestimates, loops and spills, and proposes verified index and rewrite fixes per engine.

Skill✓ sealedCC0-1.0

OWASP-oriented security review of a diff

Boundary-tagged diff review that traces inputs to sinks, applies a 13-section OWASP checklist from references/, and reports severity-rated findings with fixes.

Skill✓ sealedCC0-1.0

Saving Workspace Context

Persist project knowledge that should outlast this conversation: decisions, gotchas, research, and commands. Writes to AGENTS.md or a docs folder the project already uses. Use when the user asks to...

Skill✓ sealedCC0-1.0

Release notes from merged PRs since last tag

Collects merged PRs and commits since the last tag, classifies by user impact, rewrites in user vocabulary, and adds upgrade steps.

Software engineering — Industry directory · Waxmark