Skip to main content
Run any Skill in Manus
with one click
Anselmoo
GitHub creator profile

Anselmoo

Repository-level view of 95 collected skills across 6 GitHub repositories.

skills collected
95
repositories
6
updated
2026-07-26
repository explorer

Repositories and representative skills

andon-loop
software-developers

Auto-enforcing loop that walks a project's value stream — its stages and the wires between them — closing one gap per stage and refusing to advance past a broken or unproven wire (the andon rule). Composes andon-propose (pick and design the fix) and andon-verify (prove the wire) over a native OKF ledger. Use this when the user wants to "harden this repo", "run the andon loop", "scan for gaps and fix them in order", "prove this wire is proven", "resume the andon ledger", or any request to iterate a multi-stage codebase closing gaps while keeping each handoff evidence-grounded rather than assumed.

2026-07-26
andon-preflight
software-developers

Checks whether the current repository has a legible multi-stage value stream and where the andon ledger should live. Detects stage/wire legibility (directly or via self-assess:stage-mapper if installed), checks for a house-rules.md andon-propose can draw defaults from, and confirms an output/ledger location is writable. Use this when the user asks "is my repo ready for andon", "can andon-loop run here", "check if andon can find my stages", or before running andon-propose, andon-verify, or andon-loop for the first time in a repo.

2026-07-26
compass-solve
software-developers

Runs a complex, ambiguous, or multi-faceted task through compass's full Clarify -> Explore -> Decompose -> Execute -> Revise pipeline, composing the plugin's other 12 skills as pipeline stages instead of requiring the user to invoke them individually. Use when a task is genuinely large enough to need staged decomposition AND carries real ambiguity or multiple viable approaches worth weighing before committing — "solve this end-to-end, I'm not sure of the best approach", "plan this out and carry it out, here are the constraints", or a request that would otherwise mean chaining several compass-* skills by hand. Do not use for a single well-scoped question, a task with one obvious approach and nothing to decompose, or anything answerable directly — most requests do not need this skill; each of compass's other 12 skills stays independently invocable for a narrower job that doesn't warrant the full pipeline.

2026-07-26
confab-contract-drift
software-developers

This skill should be used when the user asks to "check for type signature drift", "verify our API schema matches the handler", "audit our function signatures for drift", "find mismatched function contracts", "check if type hints match how functions are actually called", or "audit our OpenAPI/GraphQL schema against the code". Extracts machine-checkable contracts (type hints, function signatures, docstring parameter/return descriptions, API/OpenAPI/GraphQL schemas) from source files and checks each against actual call-site and handler usage, reporting contradictions with file:line evidence on both sides.

2026-07-26
confab-cycle
software-developers

This skill should be used when the user asks to "run a quality self-optimization cycle", "harden the quality findings", "fix what quality found and re-check", "converge the quality audit", or wants the confab plugin's four domain audits run repeatedly with cross-run memory until they stop finding new things — optionally applying and re-verifying fixes for dependency-hallucination, contract-drift, and mechanical agentic-reliability findings, and drafting (never applying) assertion-strength suggestions.

2026-07-26
confab-dependency-audit
software-developers

This skill should be used when the user asks to "check for hallucinated dependencies", "verify our packages actually exist", "audit dependencies for AI-generated code", "does this package actually exist on npm/PyPI", or wants declared dependencies in manifest files (package.json, requirements.txt, pyproject.toml, Cargo.toml, go.mod, Gemfile) cross-checked against their real public registries for non-existent or typosquat-adjacent packages.

2026-07-26
confab-preflight
software-developers

Checks whether the current repository is ready for the confab plugin's audit skills to run well. Detects declared-dependency manifests, probes reachability of each detected language's public package registry, and checks for a real mutation-testing tool on PATH. Use this when the user asks to "run quality preflight", "check if the confab plugin can run here", "is my repo ready for a dependency audit", or before running confab-dependency-audit, confab-assertion-audit, confab-contract-drift, or confab-agentic-reliability for the first time in a repo.

2026-07-26
self-assess-ci-topology
software-developers

Audits this repository's git remotes, CI configuration, any publish/mirror scripts, and commit-signing consistency for redundant remotes, doc-vs-reality drift about CI, one-directional force-push mirrors with no reverse-sync path, and inconsistent commit signing (the green "Verified" vs grey "Unverified" badge — some commits signed, some not, or `commit.gpgsign` unset). Use this when the user asks to check our git remotes, audit CI setup, find redundant mirrors, verify the docs about CI/CD are accurate, or check commit signing / why some commits show grey/unverified / provenance (CI/git-topology claims only — for broader doc-vs-code drift on other topics, use self-assess-docs-drift).

2026-07-26
Showing top 8 of 63 collected skills in this repository.
rrt-user-mcp-server
computer-occupations-all-other

Teaches AI assistants (Claude Code, Claude Desktop, Cursor) how to install and connect the repo-release-tools MCP server so rrt tools (config, version, health, drift, tree, artifacts, changelog, validation) are available via MCP. Use when wiring up rrt[mcp] to an AI assistant for the first time. DO NOT USE for debugging rrt CLI commands or for users who only need the CLI.

2026-07-12
rrt-user-bootstrap
software-developers

Helps rrt users bootstrap install targets, local workflow checks, and day-one automation safely. Use when setting up rrt in a new repository or workstation. DO NOT USE for repo-maintainer-only automation changes or for cloning `.claude/*` runtime assets into source control.

2026-05-13
rrt-user-branch-strategy
software-developers

Helps rrt users create, validate, and repair semantic branch names that match their workflow. Use when starting or renaming work with `rrt branch`. DO NOT USE for arbitrary git branching conventions unrelated to rrt.

2026-05-13
rrt-user-changelog-automation
software-developers

Helps rrt users keep `[Unreleased]` current with less manual changelog work. Use when deciding between automated and manual changelog flows with rrt hooks. DO NOT USE for maintainers redesigning changelog internals or section mapping.

2026-05-13
rrt-user-ci-readiness
software-developers

Helps rrt users run local preflight checks that mirror common CI gates for branch, changelog, docs, and release readiness. Use when you want fewer CI surprises before opening a PR. DO NOT USE for editing CI pipeline internals.

2026-05-13
rrt-user-commit-quality
software-developers

Helps rrt users write conventional commits with clear intent and fewer rejected commits. Use when shaping commit messages or triaging commit lint failures. DO NOT USE for changelog authoring without a commit-quality decision.

2026-05-13
rrt-user-config-safety
computer-systems-analysts

Helps rrt users validate config files, version targets, and install paths before policy failures happen. Use when setting up or repairing rrt config. DO NOT USE for changing internal config loader implementation.

2026-05-13
rrt-user-docs-consistency
software-developers

Helps rrt users keep generated docs, command references, and source-owned docs aligned. Use when docs drift from command behavior or source assets change. DO NOT USE for long-form product writing unrelated to rrt automation.

2026-05-13
Showing top 8 of 11 collected skills in this repository.
andon-loop
software-developers

Auto-enforcing, self-optimizing hardening loop that walks a project's value stream — its ordered chain of services/packages and the wires (data contracts) between them — fixing one gap per stage and refusing to advance past a broken wire (the andon rule). A pass is one traversal; a cycle is the converged run of several passes; a hard fix triggers a sub-cycle that backtracks upstream to re-verify; in fix mode it auto-assigns subagents and MCPs to go faster. Language- and platform-agnostic. Always use when the user wants to: "harden my pipeline", "self-optimization loop", "scan for gaps and fix them in order", "wired test", "can service A deliver to service B", "value stream", "attack the bottleneck", "split fast vs slow (Playwright) checks", or any request to autonomously iterate over a multi-service codebase closing gaps while keeping each handoff proven. Also trigger on: contract test, Jidoka, Theory of Constraints, error budget, PDCA, harden faster.

2026-07-25
big-picture-driven-development
software-developers

Fix the class, not the instance. A TDD-sibling discipline for working at the right altitude: before patching any reported defect or gap, reconstruct the system model, name the invariant it violates, enforce that invariant as a check, and sweep every sibling — so the next instance never needs a human to point at it. Use whenever a bug/gap is REPORTED (especially when a human noticed it), when reviewing "is this complete?", when the same kind of bug keeps recurring, or when you catch yourself about to make a one-line fix to a reported symptom. Trigger language: "fix the class not the instance", "are we fingerpointing", "see the big picture", "what invariant does this violate", "is this a one-off?", "did we miss the system view", "stop patching symptoms", "this keeps happening". DO NOT use to write the test itself (that is superpowers:test-driven-development — this skill decides WHAT invariant the test should pin) or to explore an unbuilt design (that is superpowers:brainstorming).

2026-07-25
crates-stream
software-developers

Conductor for the Rust crates/ stream. Diagnoses + fixes kernels, solvers, workspace layout, PyO3 binding surface, and any other code under crates/. Absorbs spectrafit-solver, spectrafit-bindings, spectrafit-scaffold, and rust-model-scaffolder — their specialist content lives in references/. Use when a task touches Rust kernels, the LM/TRF/dogleg/Newton-CG solver family, the ModelTypeStr enum, the pyo3 ABI, or the crate workspace. Also when the user pastes Rust or PyO3/maturin code and asks "is this idiomatic?", "review this Rust", or "check my PyO3 code". Composes with superpowers:test-driven-development and superpowers:verification-before-completion. Serena-first.

2026-07-25
meta-builder
computer-occupations-all-other

Generator of skills, agents, hooks, prompts, and instructions for the universal-creator framework. Used when the catalog needs to grow. Absorbs skill-generator, agent-generator, hook-generator, prompt-generator, and instruction-generator — their specialist content lives in references/. Use when the user asks to scaffold a new skill, write a sub-agent definition, design a hook configuration, draft a one-shot prompt, or create workspace instruction files. Composes with superpowers:writing-skills and superpowers:writing-plans.

2026-07-25
python-stream
software-developers

Conductor for the Python python/ stream. Owns Pydantic schemas, the oracles benchmark engine, the BenchReport contract, test coverage, and Python architecture decisions. Absorbs spectrafit-schemas, spectrafit-tests, spectrafit-tdd, python-arch-proposer, and python-pattern-advisor — their specialist content lives in references/. Use when a task touches python/oracles/, python/spectrafit_core/, the Pydantic models, the benchmark engine, the contract, or pytest. Also when the user pastes Python and asks "is this Pythonic?", "review this Python", or "how can I improve this code?". Composes with superpowers:test-driven-development and superpowers:verification-before-completion. Serena-first.

2026-07-25
quality-council
software-developers

Five-voice quality council — Jobs (reduction), Ive (craft), Dye (system hierarchy), Tog (usability), Kare (metaphor). Convened on stuck wires, design questions, and presentation polish. Absorbs one-more-thing, boring-to-brilliant, cupertino-council, and evolutionary-platform-thinking — their specialist content lives in references/. Use when the user says "it feels off", "design from first principles", "what's missing", "make it memorable", "elevate this", "Time Machine treatment", "Apple-style", "future-proof this", "Vista trap", or when a tri-stream cycle's stuck-mode escape hits rung 3. Composes with superpowers:brainstorming.

2026-07-25
semantic-debugging
software-developers

Use FIRST when starting any goal or hitting any bug/failure — holds the trunk (the goal), classifies every find, dispatches instance bugs to systematic-debugging and class bugs to big-picture-driven-development, and forces convergence via a committed trunk ledger. Use before systematic-debugging or BPDD.

2026-07-25
verification
software-developers

Crosscut verification conductor — closes the oracle gap for scientific / numerical software. Owns ground-truth V&V, NIST StRD fixtures, benchmark scenarios, and DAG validation across the three streams. Absorbs ground-truth, nist-strd-runner, benchmark-scenario-generator, and dag-validator. Use when validating against a gold standard, closing the oracle gap, auditing benchmark trustworthiness, running NIST StRD harnesses, generating realistic benchmark scenarios, or checking the Rust crate DAG for cycles. Composes with superpowers:verification-before-completion. Serena-first for code.

2026-07-25
Showing top 8 of 9 collected skills in this repository.
shared
software-developers

Shared resources for universal-creator generator skills: prompting technique registry (techniques.json), the technique-selector subagent, the 18 worked prompt-technique examples (examples/), and the reusable agent trio (agents/) — validation-reviewer, artifact-router, prompt-strategist — plus the shared memory-guardrails snippet. Installed automatically when any dependent generator skill is installed. DO NOT USE directly — consumed by agent-generator, skill-generator, hook-generator, and prompt-generator.

2026-06-01
agent-generator
software-developers

Designs and generates Claude agent definitions: custom sub-agents (.agent.md), bounded-role system prompts, tool-use policies, handoff criteria, and delegation boundaries. Use when the user wants to create a specialized Claude agent, define a multi-stage agentic workflow, set tool restrictions per agent role, design a sub-agent that returns a single result and terminates, scope an agent to a specific domain or task type, or prevent an agent from overstepping its role. Generates .agent.md files, system prompt stubs, tool-allow/deny matrices, and role boundaries. DO NOT USE for Claude Code lifecycle hooks (use hook-generator); for writing prompts for one-shot tasks (use prompt-generator); for writing always-on workspace instructions (use instruction-generator).

2026-05-30
hook-generator
software-developers

Designs and generates Claude Code hook configurations for all 30+ lifecycle events including PreToolUse, PostToolUse, PermissionRequest, UserPromptSubmit, Stop, SessionStart, SubagentStop, PreCompact, PostCompact, FileChanged, ConfigChange, TeammateIdle, TaskCreated, TaskCompleted, and more. Use when the user asks to automate Claude Code behavior, enforce rules deterministically, block or approve tool calls, inject context after compaction, format code after edits, notify on idle, audit configuration changes, gate sub-agent execution, or add any lifecycle automation. Generates ready-to-paste JSON hook blocks, shell command scripts, prompt-based hook stubs, and agent-based hook stubs. DO NOT USE for general Claude API prompt engineering (use prompt-generator skill); for creating Claude agents or sub-agents (use agent-generator skill); for writing VS Code instructions (use instruction-generator skill).

2026-05-30
instruction-generator
software-developers

Creates and refines workspace and file-level instruction files: copilot-instructions.md, AGENTS.md, and *.instructions.md. Use when the user wants to save coding preferences, enforce team conventions, apply rules to specific file patterns, configure always-on agent behavior, document style guides for Claude to follow automatically, or scope instructions to a particular language, framework, or workflow area. Generates ready-to-use instruction markdown with correct applyTo patterns, concise rule sets, and optional extended variants for fragile workflows. DO NOT USE for one-shot prompts (use prompt-generator); for custom agent role definitions (use agent-generator); for Claude Code lifecycle hooks (use hook-generator).

2026-05-30
prompt-generator
software-developers

Designs and generates effective prompts for Claude and other LLMs using all 18 prompting techniques: zero-shot, few-shot, chain-of-thought, prompt chaining, ReAct, meta-prompting, self-consistency, generate-knowledge, tree-of-thoughts, RAG, ART, APE, active-prompt, DSP, PAL, reflexion, multimodal-CoT, and graph-prompting (full catalog: docs/techniques.md; worked examples live in the shared dependency at skills/shared/examples/). Use when the user wants to write a Claude system prompt, create a .prompt.md file, improve an existing prompt, choose between prompting techniques, structure multi-step reasoning, or apply context-budget-aware prompt engineering. Generates ready-to-use prompt files with technique justification and eval scenarios. DO NOT USE for Claude Code lifecycle hooks (use hook-generator); for creating agent role definitions (use agent-generator); for workspace instructions (use instruction-generator).

2026-05-30
skill-generator
software-developers

Designs and generates new skill directories for the universal-creator framework: SKILL.md definitions, workflow steps, domain conventions, generate_X_stub.py scaffold scripts, validate_X_output.py validators, agent definitions, templates, and evals. Use when the user wants to add a new skill to universal-creator, package a new artifact type as a reusable generator, create a skill from scratch following framework conventions, define a new skill for prompts/configs/documents or any domain-specific output, or extend the skill library with a new generator. Also use when someone says "make me a skill that generates X" or "I want a skill-creator style skill for Y" or "scaffold a new skill". DO NOT USE for creating Claude Code lifecycle hooks (use hook-generator); for writing workspace instruction files (use instruction-generator); for writing one-shot task prompts (use prompt-generator); for designing sub-agents with tool policies (use agent-generator).

2026-05-30
Showing 6 of 6 repositories
All repositories loaded