boshu2__agentops/docs/SKILLS.md

Skills Reference

Complete reference for all 173 AgentOps skills (164 user-facing + 9 internal).

Skills are the primitive layer of AgentOps. Higher-level entry points like /implement, /validation, /rpi, and /evolve compose those primitives into repeatable flows.

Behavioral Contracts: Most skills include scripts/validate.sh behavioral checks to verify key features remain documented. Run skills/<name>/scripts/validate.sh when present, or the GOALS.yaml behavioral-skill-contracts goal to validate the full covered set.

Skill Router (Start Here)

Use this when you're not sure which skill to run. For a full flow overview, run /using-agentops.

What are you trying to do?
│
├─ "Not sure what to do yet"
│   └─ Generate options first ─────► /brainstorm
│
├─ "I have an idea"
│   └─ Understand code + context ──► /research
│
├─ "I know what I want to build"
│   └─ Break it into issues ───────► /plan
│
├─ "Now build it"
│   ├─ Small/single issue ─────────► /implement
│   ├─ Multi-issue epic ───────────► /crank <epic-id>
│   └─ Full flow in one command ───► /rpi "goal"
│
├─ "Fix a bug"
│   ├─ Already scoped? ────────────► /implement <issue-id>
│   └─ Need to investigate? ───────► /bug-hunt
│
├─ "Build a feature"
│   ├─ Small (1-2 files) ─────────► /implement
│   ├─ Medium (3-6 issues) ───────► /plan → /crank
│   └─ Large (7+ issues) ─────────► /rpi (full pipeline)
│
├─ "Validate something"
│   ├─ Work ready to close? ──────► /validation
│   ├─ Code quality only? ───────► /vibe
│   ├─ Plan ready to build? ──────► /pre-mortem
│   └─ Quick sanity check? ───────► /council --quick validate
│
├─ "Explore or research"
│   ├─ Understand this codebase ──► /research
│   ├─ Compare approaches ────────► /council research <topic>
│   └─ Generate ideas ────────────► /brainstorm
│
├─ "Learn from past work"
│   ├─ Turn the corpus into operator surfaces ─► /knowledge-activation
│   ├─ What do we know about X? ──► ao lookup "<query>" / ao search
│   ├─ Save this insight ─────────► /retro --quick "insight"
│   └─ Full retrospective ────────► /post-mortem
│
├─ "Parallelize work"
│   ├─ Multiple independent tasks ► /swarm
│   └─ Full epic with waves ──────► /crank <epic-id>
│
├─ "Ship a release"
│   └─ Changelog + tag ──────────► /release <version>
│
├─ "Session management"
│   ├─ Prep or review Dream runs ─► /dream
│   ├─ Where was I? ──────────────► /status
│   ├─ Save for next session ─────► /handoff
│   └─ Recover after compaction ──► /recover
│
└─ "First time here" ────────────► ao quick-start → /quickstart

Core Flow Skills

/research

Deep codebase exploration using Explore agents.

/research authentication flows in services/auth

Output: .agents/research/<topic>.md

/plan

Decompose goals into trackable beads issues with dependencies.

/plan "Add user authentication with OAuth2"

Output: Beads issues with parent/child relationships

/implement

Execute a single beads issue with full lifecycle.

/implement ap-1234

Phases: Context → Tests → Code → Validation → Commit

/brainstorm

Structured idea exploration. Four phases: assess clarity, understand idea, explore approaches, capture design.

/brainstorm "add user authentication"

Output: .agents/brainstorm/YYYY-MM-DD-<slug>.md

/rpi

Full RPI lifecycle orchestrator. Discovery → Implementation → Validation in one command.

/rpi "Add user authentication"
/rpi --fast-path "fix typo in README"
/rpi --from=implementation ag-1234

Phases: Discovery (/discovery) → Implementation (/crank) → Validation (/validation)

/crank

Autonomous multi-issue execution. Runs until epic is CLOSED.

/crank <epic-id>

Execution model: Wave-based orchestration via /swarm with runtime-native workers.

/validation

Full validation close-out. Wraps /vibe + /post-mortem + /retro + /forge.

/validation
/validation ag-1234

Use when: The work is ready for final review, closeout, and learning capture.

/vibe

Comprehensive code validation across 8 aspects with finding classification (CRITICAL vs INFORMATIONAL), suppression framework for known false positives, and domain-specific checklists (SQL safety, LLM trust boundary, race conditions) auto-loaded from /standards. Correlates findings against pre-mortem predictions.

/vibe services/auth/

Checks: Security, Quality, Architecture, Complexity, Testing, Accessibility, Performance, Documentation

/retro

Quick-capture a learning. For full retrospectives, use /post-mortem.

/retro --quick "debugging memory leak"

Output: .agents/learnings/

/post-mortem

Full validation + knowledge lifecycle. Council validates, extracts learnings, activates/retires knowledge, then synthesizes process improvement proposals and suggests the next /rpi command. The flywheel exit point. Now includes RPI session streak tracking, prediction accuracy scoring (HIT/MISS/SURPRISE against pre-mortem predictions), and persistent retro history to .agents/retro/ for cross-epic trend analysis. Supports --quick, --process-only, and --skip-activate flags.

/post-mortem <epic-id>
/post-mortem --quick            # Lightweight post-mortem
/post-mortem --process-only     # Process improvements only
/post-mortem --skip-activate    # Skip knowledge activation

Output: Council report, learnings, knowledge activation/retirement, process improvement proposals, next-work queue (.agents/rpi/next-work.jsonl)

---

Utility Skills

/beads

Git-native issue tracking operations.

bd ready              # Unblocked issues
bd show <id>          # Issue details
bd close <id>         # Close issue

/bug-hunt

Root cause analysis with git archaeology.

/bug-hunt "login fails after password reset"

Knowledge queries (no slash command)

Query knowledge artifacts across locations via the CLI. There is no standalone /knowledge skill — use /knowledge-activation to build operator surfaces, or run the CLI below for ad-hoc lookup.

ao lookup "patterns for rate limiting"
ao search --all "patterns for rate limiting"

Searches: .agents/learnings/, .agents/patterns/, .agents/research/, .agents/compiled/

/llm-wiki

Maintain a compounding wiki for external reading material.

/llm-wiki ingest raw/articles/example.md
/llm-wiki query "what do we know about this topic?"
/llm-wiki lint

Status: Proposal skill for external raw/ to wiki/ knowledge, separate from the internal .agents/ compiler.

/complexity

Code complexity analysis using radon (Python) or gocyclo (Go).

/complexity services/

Threshold: CC > 10 triggers refactoring issue

/doc

Generate and validate repo documentation. --mode selects the artifact family: default (code/API docs, code-maps), --mode=readme (gold-standard README via interview + council validation, absorbed /readme), --mode=oss (open-source doc pack — CONTRIBUTING/CHANGELOG/AGENTS, absorbed /oss-docs).

/doc services/auth/          # code/API docs (default)
/doc --mode=readme           # gold-standard README
/doc --mode=oss              # scaffold/audit OSS doc pack

/pre-mortem

Simulate failures before implementing. Includes error/rescue mapping (tabular risk/mitigation), scope mode selection (Expand/Hold/Reduce with auto-detection), temporal interrogation (hour 1/2/4/6+ timeline), and prediction tracking with unique IDs (pm-YYYYMMDD-NNN) correlated through vibe and post-mortem.

/pre-mortem "add caching layer"

Output: Failure modes, error/rescue maps, predictions with IDs, mitigation strategies, spec improvements

---

Orchestration Skills

/council

Multi-model validation — the core primitive used by vibe, pre-mortem, and post-mortem. Auto-extracts significant findings from WARN/FAIL verdicts into the knowledge flywheel.

/council validate recent
/council --deep recent

/swarm

Parallel agent spawning for concurrent task execution.

/swarm <epic-id>

/codex-team

Spawn parallel Codex execution agents.

/codex-team <epic-id>

---

Additional Utility Skills

/handoff

Session handoff — preserve context for continuation.

/handoff

/release

Pre-flight checks, changelog generation, version bumps, and tagging.

/release

/status

Single-screen dashboard of project state.

/status

/quickstart

Interactive onboarding — mini RPI cycle for new users.

/quickstart

/dream

Retirement pointer. The in-tree out-of-session compounding engine was removed (soc-2rtm0); scheduled, between-session knowledge compounding now runs via Gas City (the reference substrate), and AgentOps ships no out-of-session runner of its own. In-session knowledge primitives stay on-demand: /harvest, /forge, /compile, /inject. Daytime code compounding is /evolve via /rpi.

Output: none — this skill no longer drives an in-repo command.

/trace

Trace design decisions through knowledge artifacts.

/trace "why did we choose Redis?"

/knowledge-activation

Operationalize a mature .agents corpus into reusable belief, playbook, briefing, and gap surfaces.

/knowledge-activation
ao knowledge activate --goal "productize knowledge activation"
ao knowledge gaps

/recover

Post-compaction context recovery. Detects in-progress RPI and evolve sessions, loads knowledge, shows recent work and pending tasks.

/recover                     # Recover context after compaction

/evolve

Autonomous fitness-scored improvement loop. Measures GOALS.yaml, fixes the worst gap, compounds via knowledge flywheel.

/evolve                      # Run until stopped or the full producer ladder is exhausted
/evolve --max-cycles=5       # Cap at 5 cycles
/evolve --dry-run            # Measure only, don't execute

/product

Interactive PRODUCT.md generation. Interviews about mission, personas, value props, and competitive landscape.

/product

Output: PRODUCT.md in repo root

/heal-skill

Detect and auto-fix skill hygiene issues (missing frontmatter, unlinked references, dead references).

/heal-skill --check                     # Report issues
/heal-skill --fix                       # Auto-fix what's safe
/heal-skill --check skills/council      # Check specific skill

Checks: MISSING_NAME, MISSING_DESC, NAME_MISMATCH, UNLINKED_REF, EMPTY_DIR, DEAD_REF

/converter

Convert skills to other platforms (Codex, Cursor).

/converter skills/council codex          # Single skill to Codex format
/converter --all cursor                  # All skills to Cursor .mdc format

Targets: codex (SKILL.md + prompt.md), cursor (.mdc + optional mcp.json), test (raw bundle)

/openai-docs

Use official OpenAI docs MCP access for current API/platform guidance with citations.

/openai-docs "responses api tools"

/pr-research

Research upstream contribution conventions before implementing an external PR.

/pr-research https://github.com/org/repo

/pr-implement

Execute fork-based contribution work with isolation checks.

/pr-implement

/pr-validate

Run PR-specific validation (scope creep, isolation, upstream alignment).

/pr-validate

/pr-prep

Prepare structured PR bodies with validation evidence. Includes commit split advisor (Phase 4.5) suggesting bisectable commit ordering.

/pr-prep

---

Additional Skills

Single-purpose skills not listed above. See each skill's SKILL.md for triggers, phases, and flags.

Skill	Purpose
/autodev	Manage the PROGRAM.md operational contract for autonomous development loops
/bootstrap	One-command product-layer setup (GOALS.md, PRODUCT.md, README.md, .agents/, optional hooks)
/compile	Compile raw .agents/ artifacts into an interlinked wiki at .agents/compiled/ (Mine → Grow → Defrag → Lint)
/deps	Dependency audit, updates, vulnerability scanning, license compliance
/design	Product validation gate — aligns goal with PRODUCT.md before discovery
/discovery	Full discovery-phase orchestrator (brainstorm + search + research + plan + pre-mortem)
/goals	Maintain GOALS.yaml/GOALS.md fitness specs; measure drift; add/prune directives
/grafana-platform-dashboard	Design/refactor/validate Grafana dashboards for OpenShift/Kubernetes platform ops
/harvest	Cross-rig knowledge consolidation and tiered promotion to the global hub
/hooks-authoring	Author and validate AgentOps runtime hooks
/perf	Performance profiling, benchmarking, regression detection, optimization
/push	Atomic test-commit-push with conventional-commit message
/red-team	Persona-based adversarial validation — probes whether docs/skills actually work
/refactor	Safe, verified refactoring with regression tests at each step
/reverse-engineer-rpi	Reverse-engineer a product into feature catalog, code map, and specs
/review	Structured review of incoming PRs, agent-generated changes, or diffs
/scaffold	Project scaffolding, component generation, boilerplate
/scenario	Author/manage holdout scenarios in .agents/holdout/ for behavioral validation
/security	Continuous repository security scanning and release gating
/security-suite	Composable security suite — static, dynamic, redteam, baseline drift, policy gating
/test	Test generation, coverage analysis, TDD workflow

---

Internal Skills

These fire automatically and are not directly invoked:

Skill	Purpose
inject	Load knowledge at session start (ao inject)
forge	Mine transcripts for knowledge artifacts (decisions, learnings, failures, patterns)
ratchet	Progress gates for RPI workflow
flywheel	Knowledge health monitoring
provenance	Trace knowledge artifact lineage
standards	Language-specific coding standards (auto-loaded by /vibe, /implement)
shared	Shared reference documents for multi-agent backends
beads	Issue tracking reference
using-agentops	Workflow guide (hook-capable silent state prep, explicit Codex startup fallback)

---

Subagents

Subagent behaviors are defined inline within SKILL.md files (not as separate agent files). Skills that use subagents spawn them as Task agents during execution. 20 specialized roles are used across /vibe, /pre-mortem, /post-mortem, and /research.

Agent Role	Used By	Focus
Code reviewer	/vibe, /council	Quality, patterns, maintainability
Security reviewer	/vibe, /council	Vulnerabilities, OWASP
Security expert	/vibe, /council	Deep security analysis
Architecture expert	/vibe, /council	System design review
Code quality expert	/vibe, /council	Complexity and maintainability
UX expert	/vibe, /council	Accessibility and UX validation
Plan compliance expert	/post-mortem	Compare implementation to plan
Goal achievement expert	/post-mortem	Did we solve the problem?
Ratchet validator	/post-mortem	Verify gates are locked
Flywheel feeder	/post-mortem	Extract learnings with provenance
Technical learnings expert	/post-mortem	Technical patterns
Process learnings expert	/post-mortem	Process improvements
Integration failure expert	/pre-mortem	Integration risks
Ops failure expert	/pre-mortem	Operational risks
Data failure expert	/pre-mortem	Data integrity risks
Edge case hunter	/pre-mortem	Edge cases and exceptions
Coverage expert	/research	Research completeness
Depth expert	/research	Depth of analysis
Gap identifier	/research	Missing areas
Assumption challenger	/research	Challenge assumptions

---

ao CLI Integration

Skills integrate with the ao CLI for orchestration:

Skill	ao CLI Command
/research	ao lookup, ao search, ao rpi phased
/retro	ao forge markdown, ao session close
/post-mortem	ao forge, ao flywheel close-loop, ao constraint activate
/implement	ao context assemble, ao lookup, ao ratchet record
/crank	ao rpi phased, ao ratchet, ao flywheel status