mcpbeat

boshu2 Skills

104 skills published by boshu2 across 1 repository. Together they weigh 445 913 tokens — that is what loading all of them at once would cost you in context.

104 skills 445 913 tokens total

Account Rotation
agentops

Switch a caller-selected coding-agent account and report the observed identity. Triggers: "switch account", "rotate coding-agent account".

678 tokens
Agent Mail
agentops

Use Agent Mail as an optional messaging and file-reservation adapter for explicitly coordinated writers. Triggers: "coordinate writers", "reserve files".

1k tokens
Agent Native
agentops

Operate explicit orchestrator, implementer, validator, and scribe roles through a caller-selected agent runtime. Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".

927 tokens
Agy Native
agentops

Use an explicitly selected AGY runtime for one provided packet or fresh validator context. Triggers: "agy", "antigravity", "AGY evidence".

787 tokens
Automation Shape Routing
agentops

Front door for agent automation: choose inline, bounded fanout, reusable skill/workflow/gate, persistent agent-native workers, or explicit Gas City. Triggers: "build automation", "which orchestration shape", "should this use NTM".

1k tokens
Bootstrap
agentops

Initialize minimal AgentOps documentation and verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".

798 tokens
Cass
agentops

Mine past agent sessions for working prompts, decisions, and patterns (session archaeology). Triggers: "cass", "mine past agent sessions for", "cass skill".

4k tokens
Cc Hooks
agentops

Configure default Claude Code enforcement hooks and opt-in guard recipes. Triggers: "cc-hooks", "configure Claude Code hooks", "install hooks".

4k tokens
Codebase Recon
agentops

Reconstruct a repository as cited entry-to-test flows and bounded claims. Triggers: "codebase recon", "trace this codebase", "repository audit", "refresh the prior recon".

2k tokens
Codex Exec
agentops

Run one caller-supplied Codex command non-interactively and capture evidence. Triggers: "run Codex headless", "capture Codex evidence".

1k tokens
Converter
agentops

Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".

3k tokens
Council
agentops

Collect independent perspectives for an explicitly high-stakes or contested judgment. Triggers: "council", "multi-judge review", "independent perspectives".

1k tokens
Craft Goal
agentops

Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment''s intent routes to plan.)

3k tokens
Dcg
agentops

Handle blocked destructive commands and configure agent safety guardrails. Triggers: "dcg", "handle a DCG block", "configure agent safety guardrails".

3k tokens
Doc
agentops

Generate and validate repo docs, READMEs, and OSS doc packs. Triggers: "doc", "generate and validate repo docs", "doc skill".

2k tokens
Domain
agentops

Load the AgentOps language and bounded-context contracts when a term needs precise meaning. Triggers: "define this domain term", "check the bounded context".

494 tokens
Fitness
agentops

Measure declared project fitness goals without recommending or applying work. Triggers: "fitness", "check project fitness", "measure goals".

733 tokens
Goals
agentops

Compatibility alias — renamed to fitness. Use fitness to measure declared project fitness goals. Triggers: "goals" (deprecated).

277 tokens
Handoff
agentops

Write compact caller-authored session evidence without choosing continuation. Triggers: "handoff", "write compact session handoff".

490 tokens
Idea Genie
agentops

Generate evidenced opportunities or challenge an idea with sealed perspectives. Triggers: "idea genie", "what should we build", "challenge this idea", "compare proposals".

1k tokens
Implement
agentops

Execute one bounded RED to GREEN experiment

1k tokens scripts
Implement
agentops

Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts. Triggers: "implement", "implement this bead", "run the experiment". Full plan-to-validation requests route to rpi.

935 tokens
Learn
agentops

Optionally analyze collections of durable verdicts for recurring evidence after the critical path. Triggers: "learn from verdicts", "mine validation history".

564 tokens
Ms
agentops

meta_skill (ms) — the skill-search/load engine over both corpora (agentops + jsm). Find a skill for a task, search skills, or load runnable skill guidance. Triggers: "ms", "meta_skill", "skill search", "find a skill for", "load skill guidance".

3k tokens
Ntm
agentops

Use NTM as an optional pane adapter for caller-supplied roles and commands. Triggers: "ntm", "tmux panes", "ntm robot state".

1k tokens
Operationalize
agentops

Distill repeated, evidence-backed expertise into a proposed skill, check, reference, or workflow artifact. Triggers: "operationalize this", "turn this expertise into a reusable capability".

918 tokens
Pattern Mining
agentops

Test repeated implementation shapes against independent exemplars and a holdout before routing an earned abstraction. Triggers: "mine a recurring code pattern", "is this abstraction earned", "extract invariants from implementations".

2k tokens
Plan
agentops

Shape or refine the existing bead or caller intent without a second planning artifact. Triggers: "plan", "discover and plan", "shape this goal", "plan manifest".

2k tokens
Postmortem
agentops

Optionally test a retrospective causal question against durable verdict evidence. Triggers: "postmortem", "causal retrospective", "test a retrospective hypothesis".

1k tokens
Premortem
agentops

Optionally challenge a frozen plan with one fresh independent judge before implementation. Triggers: "premortem", "challenge this plan", "what could make this plan fail".

1k tokens
Product
agentops

Create or refine PRODUCT.md while separating evidence, aspiration, users, value, and non-goals. Triggers: "product", "create PRODUCT.md", "product boundary".

561 tokens
Rch
agentops

Use RCH once to offload a build or collect remote-compilation diagnostics. Triggers: "use RCH", "offload this build".

952 tokens
Reality Check
agentops

Compare a claimed state with observable repository evidence and report concrete gaps. Requires a claim or expected state to test. Triggers: "reality check", "is this claim actually done", "compare claim to repo".

862 tokens
Refactor
agentops

Execute one behavior-preserving structural transformation and report evidence. Triggers: "refactor this", "simplify without changing behavior".

895 tokens
Research
agentops

Answer a bounded question with current cited evidence. Triggers: "research", "investigate this question", "find evidence". (Investigating a repository routes to codebase-recon.)

1k tokens
Reverse Engineer
agentops

Reverse-engineer an authorized repo, binary, or product into a verifiable feature inventory and adoption map. Triggers: "reverse-engineer X", "tear down Y", "what should we steal from Z", "evaluate competitor/upstream", "should we fork/adopt/build-native".

3k tokens
Rpi
agentops

Run one bounded Plan, Implement, and fresh Validate experiment, then report and stop. Triggers: "run rpi", "feed this through the loop", "execute this plan", orchestration or worker delegation that implements changes.

2k tokens
Sbh
agentops

Inspect disk pressure with SBH and run one explicitly authorized recovery action. Triggers: "check disk pressure", "run SBH".

745 tokens
Scaffold
agentops

Stamp a bounded project, component, or CI scaffold and verify the generated result once. Triggers: "scaffold", "create project component or boilerplate".

921 tokens
Scope
agentops

Review the bead or caller intent write scope for completeness and ambiguity. Triggers: "review write scope", "check scope boundaries", "scope this change".

993 tokens
Security
agentops

Run authorized repository security scans for vulnerabilities, dependency risk, secrets, and binary policy. Triggers: "security", "run repository security scans for", "security skill".

2k tokens
Shared
agentops

Retired — its runtime-neutrality contract moved to docs/contracts/runtime-neutrality.md. Triggers: none — not routable.

262 tokens
Skill Builder
agentops

Create a metadata-complete AgentOps skill source package, regenerate its derived projections, and check or repair structural hygiene in skill packages. Triggers: "create a skill", "scaffold skill", "absorb external skill", "new skill", "heal skill", "repair skill hygiene", "audit skill structure", "check skill package".

2k tokens
Standards
agentops

Load only the standards relevant to a caller-supplied change, then report concrete findings. Triggers: "check standards", "which standards apply".

810 tokens
Status
agentops

Report observable AgentOps evidence without selecting work. Triggers: "status", "show AgentOps status".

719 tokens
Swarm
agentops

Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".

729 tokens
Toil Mining
agentops

Mine caller-supplied usage history for repeated toil and emit ranked evidence. Triggers: "mine toil", "find repeated operational work".

2k tokens
Using Flywheel
agentops

Operate the Agentic Coding Flywheel as a caller-selected software factory; keep its runtime state out of AgentOps verdicts. Triggers: "using flywheel", "agent flywheel".

1k tokens
Using Gc
agentops

Operate a caller-selected Gas City 1.4 with

5k tokens
Using Gc
agentops

Operate a caller-selected Gas City 1.4 with upstream registry packs and native run-centered surfaces while keeping GC runtime state out of AgentOps verdicts. Triggers: "using gc", "gas city", "drive the mayor", "dispatch through gc".

5k tokens
Validate
agentops

Freshly judge exact subject content against bead or caller acceptance, optionally persist verdict.v2 for a declared consumer, and stop. Triggers: "validate", "independently validate", "vibe".

3k tokens
Validate
agentops

Freshly judge exact subject content against

16k tokens scripts
Workflow Builder
agentops

Scaffold an explicit one-shot workflow adapter without lifecycle authority. Triggers: "build a workflow adapter", "scaffold a one-shot workflow".

575 tokens
Account Rotation
agentops

Switch a caller-selected coding-agent account and report the observed identity. Triggers: "switch account", "rotate coding-agent account".

678 tokens
Agent Native
agentops

Operate explicit orchestrator, implementer, validator, and scribe roles through a caller-selected agent runtime. Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".

4k tokens scripts
Cc Hooks
agentops

Configure default Claude Code enforcement hooks and opt-in guard recipes. Triggers: "cc-hooks", "configure Claude Code hooks", "install hooks".

24k tokens scripts
Agy Native
agentops

Use an explicitly selected AGY runtime for one provided packet or fresh validator context. Triggers: "agy", "antigravity", "AGY evidence".

787 tokens
Automation Shape Routing
agentops

Front door for agent automation: choose inline, bounded fanout, reusable skill/workflow/gate, persistent agent-native workers, or explicit Gas City. Triggers: "build automation", "which orchestration shape", "should this use NTM".

1k tokens
Cass
agentops

Mine past agent sessions for working prompts, decisions, and patterns (session archaeology). Triggers: "cass", "mine past agent sessions for", "cass skill".

39k tokens scripts
Bootstrap
agentops

Initialize minimal AgentOps documentation and verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".

1k tokens
Agent Mail
agentops

Use Agent Mail as an optional messaging and file-reservation adapter for explicitly coordinated writers. Triggers: "coordinate writers", "reserve files".

5k tokens
Converter
agentops

Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".

11k tokens scripts
Dcg
agentops

Handle blocked destructive commands and configure agent safety guardrails. Triggers: "dcg", "handle a DCG block", "configure agent safety guardrails".

12k tokens scripts
Council
agentops

Collect independent perspectives for an explicitly high-stakes or contested judgment. Triggers: "council", "multi-judge review", "independent perspectives".

3k tokens scripts
Codex Exec
agentops

Run one caller-supplied Codex command non-interactively and capture evidence. Triggers: "run Codex headless", "capture Codex evidence".

1k tokens
Domain
agentops

Load the AgentOps language and bounded-context contracts when a term needs precise meaning. Triggers: "define this domain term", "check the bounded context".

1k tokens scripts
Doc
agentops

Generate and validate repo docs, READMEs, and OSS doc packs. Triggers: "doc", "generate and validate repo docs", "doc skill".

24k tokens scripts
Codebase Recon
agentops

Reconstruct a repository as cited entry-to-test flows and bounded claims. Triggers: "codebase recon", "trace this codebase", "repository audit", "refresh the prior recon".

3k tokens scripts
Craft Goal
agentops

Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment''s intent routes to plan.)

3k tokens scripts
Idea Genie
agentops

Generate evidenced opportunities or challenge an idea with sealed perspectives. Triggers: "idea genie", "what should we build", "challenge this idea", "compare proposals".

3k tokens scripts
Goals
agentops

Compatibility alias — renamed to fitness. Use fitness to measure declared project fitness goals. Triggers: "goals" (deprecated).

277 tokens
Fitness
agentops

Measure declared project fitness goals without recommending or applying work. Triggers: "fitness", "check project fitness", "measure goals".

733 tokens
Handoff
agentops

Write compact caller-authored session evidence without choosing continuation. Triggers: "handoff", "write compact session handoff".

490 tokens
Implement
agentops

Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts. Triggers: "implement", "implement this bead", "run the experiment". Full plan-to-validation requests route to rpi.

1k tokens scripts
Implement
agentops

Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts. Triggers: "implement", "implement this bead", "run the experiment". Full plan-to-validation requests route to rpi.

1k tokens scripts
Ms
agentops

meta_skill (ms) — the skill-search/load engine over both corpora (agentops + jsm). Find a skill for a task, search skills, or load runnable skill guidance. Triggers: "ms", "meta_skill", "skill search", "find a skill for", "load skill guidance".

6k tokens scripts
Ntm
agentops

Use NTM as an optional pane adapter for caller-supplied roles and commands. Triggers: "ntm", "tmux panes", "ntm robot state".

1k tokens
Learn
agentops

Optionally analyze collections of durable verdicts for recurring evidence after the critical path. Triggers: "learn from verdicts", "mine validation history".

767 tokens scripts
Premortem
agentops

Optionally challenge a frozen plan with one fresh independent judge before implementation. Triggers: "premortem", "challenge this plan", "what could make this plan fail".

2k tokens scripts
Plan
agentops

Shape or refine the existing bead or caller intent without a second planning artifact. Triggers: "plan", "discover and plan", "shape this goal", "plan manifest".

2k tokens scripts
Operationalize
agentops

Distill repeated, evidence-backed expertise into a proposed skill, check, reference, or workflow artifact. Triggers: "operationalize this", "turn this expertise into a reusable capability".

918 tokens
Pattern Mining
agentops

Test repeated implementation shapes against independent exemplars and a holdout before routing an earned abstraction. Triggers: "mine a recurring code pattern", "is this abstraction earned", "extract invariants from implementations".

2k tokens scripts
Postmortem
agentops

Optionally test a retrospective causal question against durable verdict evidence. Triggers: "postmortem", "causal retrospective", "test a retrospective hypothesis".

2k tokens scripts
Reality Check
agentops

Compare a claimed state with observable repository evidence and report concrete gaps. Requires a claim or expected state to test. Triggers: "reality check", "is this claim actually done", "compare claim to repo".

2k tokens scripts
Product
agentops

Create or refine PRODUCT.md while separating evidence, aspiration, users, value, and non-goals. Triggers: "product", "create PRODUCT.md", "product boundary".

561 tokens
Rch
agentops

Use RCH once to offload a build or collect remote-compilation diagnostics. Triggers: "use RCH", "offload this build".

17k tokens
Refactor
agentops

Execute one behavior-preserving structural transformation and report evidence. Triggers: "refactor this", "simplify without changing behavior".

3k tokens
Research
agentops

Answer a bounded question with current cited evidence. Triggers: "research", "investigate this question", "find evidence". (Investigating a repository routes to codebase-recon.)

3k tokens scripts
Reverse Engineer
agentops

Reverse-engineer an authorized repo, binary, or product into a verifiable feature inventory and adoption map. Triggers: "reverse-engineer X", "tear down Y", "what should we steal from Z", "evaluate competitor/upstream", "should we fork/adopt/build-native".

40k tokens scripts
Rpi
agentops

Run one bounded Plan, Implement, and fresh Validate experiment, then report and stop. Triggers: "run rpi", "feed this through the loop", "execute this plan", orchestration or worker delegation that implements changes.

7k tokens scripts
Sbh
agentops

Inspect disk pressure with SBH and run one explicitly authorized recovery action. Triggers: "check disk pressure", "run SBH".

745 tokens
Scaffold
agentops

Stamp a bounded project, component, or CI scaffold and verify the generated result once. Triggers: "scaffold", "create project component or boilerplate".

4k tokens scripts
Scope
agentops

Review the bead or caller intent write scope for completeness and ambiguity. Triggers: "review write scope", "check scope boundaries", "scope this change".

1k tokens scripts
Security
agentops

Run authorized repository security scans for vulnerabilities, dependency risk, secrets, and binary policy. Triggers: "security", "run repository security scans for", "security skill".

19k tokens scripts
Shared
agentops

Retired — its runtime-neutrality contract moved to docs/contracts/runtime-neutrality.md. Triggers: none — not routable.

262 tokens
Skill Builder
agentops

Create a metadata-complete AgentOps skill source package, regenerate its derived projections, and check or repair structural hygiene in skill packages. Triggers: "create a skill", "scaffold skill", "absorb external skill", "new skill", "heal skill", "repair skill hygiene", "audit skill structure", "check skill package".

42k tokens scripts
Swarm
agentops

Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".

3k tokens scripts
Standards
agentops

Load only the standards relevant to a caller-supplied change, then report concrete findings. Triggers: "check standards", "which standards apply".

20k tokens scripts
Status
agentops

Report observable AgentOps evidence without selecting work. Triggers: "status", "show AgentOps status".

719 tokens
Toil Mining
agentops

Mine caller-supplied usage history for repeated toil and emit ranked evidence. Triggers: "mine toil", "find repeated operational work".

6k tokens scripts
Using Flywheel
agentops

Operate the Agentic Coding Flywheel as a caller-selected software factory; keep its runtime state out of AgentOps verdicts. Triggers: "using flywheel", "agent flywheel".

1k tokens scripts
Using Gc
agentops

Operate a caller-selected Gas City 1.4 with upstream registry packs and native run-centered surfaces while keeping GC runtime state out of AgentOps verdicts. Triggers: "using gc", "gas city", "drive the mayor", "dispatch through gc".

5k tokens
Validate
agentops

Freshly judge exact subject content against bead or caller acceptance, optionally persist verdict.v2 for a declared consumer, and stop. Triggers: "validate", "independently validate", "vibe".

16k tokens scripts
Workflow Builder
agentops

Scaffold an explicit one-shot workflow adapter without lifecycle authority. Triggers: "build a workflow adapter", "scaffold a one-shot workflow".

575 tokens