Claude Skills by zby

Use when asked to analyse, review, or refresh an external agent runtime, orchestration system, agent operating layer, agent memory/knowledge/context-engineering system, or narrower model-dependent operational mechanism from inspectable sources.

Discover connections for a single artifact. Writes a connect-report under kb/reports/cache/connect/<collection>/ without mutating library artifacts or indexes. Use with an artifact path or artifact name.

Convert notes between types. Currently supports text to note by adding unverified structured frontmatter, renaming the file to match the title, and fixing backlinks. Use with a note path or note name.

Ground one source-side claim by retaining minimum verbatim quotes or requiring the pinned snapshot. Use when a note needs source support or retained quotes; choose this skill, not cp-skill-ingest, for quote retention.

Diagnose Commonplace project layout, promoted-skill discovery, user-level uv tool installation, command PATH ownership, and launch-environment failures.

Use when asked to ingest one URL or local snapshot into a tracked .ingest.md source analysis, or to execute a bounded re-ingest request. Retaining quotes in an existing ingest is cp-skill-ground's job, not this skill's.

Experimentally revise a note with fresh critic, author, synthesizer, and blind-judge agents while retaining the incumbent as fallback.

Snapshot a URL into the local kb/sources/.snapshots/ cache, routing GitHub, X/Twitter, PDF, and ordinary web sources to the appropriate capture path.

Run deterministic validation on KB artifacts, collections, collection landings, and the published redirect map, including schemas, links, required sections, and batch signals.

Write or rebuild one unsettled KB artifact through source-first reconstruction, consolidated authorship, independent review, and guarded promotion. Use when claims need grounding or synthesis; avoid it for settled local edits.

Write one KB note whose intended contribution is already determined, under its collection and type contracts; validate it and hand broader graph discovery to cp-skill-connect.

Measure framework overhead by decomposing scenarios into clean-context forks and reporting per-fork load plus aggregate cost.

Explain an existing complex technical finding to an operator when its practical meaning is obscured by implementation detail, task-local terminology, or a long causal chain. Do not use for routine updates or simple answers.

Open a Markdown file in Roughdraft, wait for the user's CriticMarkup review, then apply or respond to the feedback.

Use when asked what an existing external-system analysis currently suggests for Commonplace under a named design question or priority. Produces selective living state, never system characterization or matrix data.

Use when asked to write or refresh public cross-system analysis from the agent-memory review corpus and its generated matrix. Produces a snapshot-bound landscape synthesis; do not use Commonplace transfer scans as evidence.

Run only when analyse-agentic-system invokes the legacy review-publication workflow for a detected external memory, knowledge, or context-engineering system; do not select or invoke directly.

Accepted decision that source-claim grounding is the promoted skill cp-skill-ground, the single advertised entry for choosing which quotes an ingest retains and the only writer of its Quotes section, with cp-skill-ingest confined to (re-)ingest

Write or update a local code-grounded agent memory system review from a GitHub repository reference, including checkout refresh, optional sub-agent drafting, semantic QA, and validation.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

Architectural code analysis for Python design quality. Evaluates simplicity (Rich Hickey), functional core/imperative shell (Gary Bernhardt), and coupling (Constantine & Yourdon). Use for design review or architectural assessment of Python code.

Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after /extract creates notes, when exploring connections, or when a topic needs synthesis. Triggers on "/connect", "/connect [note]", "find connections", "update MOCs", "connect these notes".

Extract structured knowledge from source material. Two modes — `extract` (default) for comprehensive atomic claim extraction, and `analyze` for design proposals where one impact-analysis note replaces claim decomposition. A relevance filter ("does this change how we build our project?") applies to all modes. For `extract` mode on domain-relevant sources, skip rate must be below 10%. Triggers on "/extract", "/extract [file]", "extract insights", "mine this", "process this".

Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".

Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

End-to-end source processing -- seed, reduce, process all claims through reflect/revisit/review, archive. The full pipeline in one command. Triggers on "/pipeline", "/pipeline [file]", "process this end to end", "full pipeline".

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval. Triggers on "/refactor", "restructure vault".

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".

Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/review", "/review [note]", "verify note quality", "check note health".

Update old notes with new connections. The backward pass that /connect doesn't do. Revisit existing notes that predate newer related content, add connections, sharpen claims, consider splits. Triggers on "/revisit", "/revisit [note]", "update old notes", "backward connections", "revisit notes".

Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".

Show vault statistics and knowledge graph metrics. Provides a shareable snapshot of vault health, growth, and progress. Triggers on "/stats", "vault stats", "show metrics", "how big is my vault".

View and manage the task stack and processing queue. Shows pending work, active tasks, completed items, and queue state. Triggers on "/tasks", "show tasks", "what's pending", "task list", "queue status".

Schema validation for notes. Checks against domain-specific templates. Validates required fields, enum values, description quality, and link health. Non-blocking — warns but doesn't prevent capture. Triggers on "/validate", "/validate [note]", "check schema", "validate note", "validate all".