Skills directory · page 45

Dependency-loaded by other okhp3-notion-* skills. Applies Notion's rate limits, payload size limits, the Free-workspace block limit, backoff policy, chunking strategy, and idempotency discipline to any sequence of Notion API or MCP calls. Not intended to be selected directly from a user prompt; always loaded by a sibling skill that is about to make more than one call or a call at risk of hitting a limit.

Read Notion page and document content: fetch a page, traverse block children, paginate long pages, recover truncated subtrees, and extract the page body as faithful markdown. Use when the user asks to read, open, summarize, or extract the content of a Notion page, doc, wiki page, subpage, or block. Does not read database rows or filtered lists (use okhp3-notion-query) and does not produce an external file (use a wave-3 egress skill).

Create or update Notion pages and document content: page creation, content append, targeted search-and-replace, icons and covers, and async handling for large writes. Use when the user asks to create, edit, update, append to, or restructure a Notion page, doc, wiki page, or subpage. Does not write pages whose parent is a database or data source (use okhp3-notion-row-write) and does not delete or archive anything (use okhp3-notion-destructive-ops).

Query Notion database rows and filtered lists from a known data source: SQL mode, rows mode, saved-view mode, filter and sort syntax, plan metering, mention-resolution limits, and rich-text fidelity caveats. Use when the user wants rows, records, or a filtered/sorted list from a Notion database, or to run a saved view. Does not find content by keyword across the workspace (use okhp3-notion-search-strategy), does not read page body content (use okhp3-notion-page-read), and does not write anything.

Create or update Notion database rows: schema-first property mapping, select and status option handling, relation and people writes, and idempotent upsert against a stable key. Use when the user wants to add, update, or upsert a record, entry, or row in a Notion database. Does not change the schema to fit new data (use a wave-2 schema-migration skill) and is not for high-volume bulk loads of thousands of rows.

Find content across a Notion workspace and its connected apps by keyword. Chooses between workspace search and AI search, applies creator, date, teamspace, title-only, and content-status filters, respects the search-specific rate limit, and routes around plan-gated filters. Use when the user wants to find, locate, or look up a page, database, or piece of content by name or topic without already knowing where it lives. Does not query structured rows from a known database (use okhp3-notion-query) and does not enumerate everything that exists (use a wave-2/3 workspace-inventory skill).

Append a quick capture note to a dated local inbox file, for later triage into Notion. Use when Jamie says "capture this", "note this down", or "remind me to look at this later" and it doesn't need an immediate answer.

Turn a rough brain-dump into a reviewable LinkedIn draft file in a drop folder, using the OKHP3 brand-voice rules. Use when Jamie pastes a raw idea, a finished piece of work, or a rant and says "turn this into a LinkedIn post" or "draft this up".

Check a Mermaid file against documented renderer gotchas before it goes into a repo or gets published. Use when asked to "check this diagram", "lint this mermaid file", or before committing a .mmd/.mermaid file.

Decide which OpenClaw agent persona should own a request (Larry, AskJamie, MurderBird, or Glee-fully by default), then package the work as a [HANDOFF] packet. Use when a request arrives at the default agent without a named persona, when work must move between agents, or when asked "who should handle this". Routes only; never executes the routed task.

Sweep the OKHP3 GitHub mirrors for uncommitted changes, unpushed commits, and stale .git locks; self-clean locks with the documented rename pattern. Use when asked "how are my repos doing", "any dirty repos", or "check for git locks".

Run local-first web research on an OpenClaw agent and return a sourced research packet (findings, evidence tiers, conflicts, gaps) sized for handoff to a drafting or thesis skill. Use when asked to research, look up, or gather sources before an article, email, or decision. Uses the runtime's built-in search and fetch tools; no Frontier provider call.

Run the skillz repo's own cataloger/integrity scripts on demand and summarize what changed. Use when asked to "refresh the skill catalog", "check skillz integrity", or after adding/editing a skill in the skillz repo.

One-shot health report on the local AI stack -- Ollama, LM Studio, and the Docker-hosted Open WebUI/SearXNG/Qdrant containers. Use when asked "how's my local AI stack", "is Ollama running", "check Docker containers", or before loading a big model.

Design and operationalize outcome models that compress noisy event histories into calibrated forecasts and constrained decisions. Use when a user asks about feature reduction, probability, expected value, aggregation, or moving a prediction method between sports, business, sales, advertising, finance, or prediction markets. Load a domain adapter when one fits.

Compare independent probabilities with prediction-market prices and evaluate expected value, calibration, liquidity, spread, and resolution risk. Use when analyzing event contracts, odds, edge, paper backtests, or risk-adjusted position sizing. Load `okhp3-outcome-modeling-core` first; this skill does not place or manage trades.

Forecast pipeline and compare salespeople, territories, accounts, and commercial allocations using expected contribution rather than close rate alone. Use when evaluating stage probability, quota, discount, retention, margin, customer lifetime value, or opportunity quality. Load `okhp3-outcome-modeling-core` first.

Model team, game, and player outcomes from repeated sports events, matchup history, schedules, injuries, and performance metrics. Use for sports rankings, matchup forecasts, season projections, or fantasy-oriented state models. Load `okhp3-outcome-modeling-core` first; this adapter does not provide live odds or trade execution.

OverKill Hill P³ OverKill Hill SPA styling. Use when a user wants an OverKill Hill application, documentation artifact, presentation, or image brief aligned to the approved OverKill Hill profile. Also activate when a target needs the forge-like technical visual system of the OverKill Hill family. This specialization applies the approved local profile and does not substitute Glee-fully or AskJamie styling.

Draft a Patreon comment or reply from supplied post and access context. Use when the user needs a privacy-preserving response within a named Patreon post discussion. It returns text only and does not comment, change access, inspect membership or payment data, message members, moderate, or publish.

Draft a Patreon post with a supplied access boundary and post form. Use when the user needs public, free-member, or paid-member post copy with a clear title, body, material handoff, and access-review note. It prepares text only and does not set membership access, attach media, schedule, or publish.

Draft a Pinterest comment or reply from supplied Pin and conversation context. Use when the user wants a concise, grounded response under a named Pin. It returns a draft only and does not comment, react, highlight, delete, filter, report, message, or moderate content.

Draft a Pinterest Pin title, description, destination-link handoff, and board-context checklist from supplied material. Use when the user needs a Pin-ready copy bundle for a named board and asset. It prepares text only and does not create a Pin, upload media, select a board, set disclosure, or publish.

Investigate a suspected agentic security incident and convert evidence into validated defensive learning. Use when reconstructing timeline, scope, control failure, and recovery actions. Do not serve as legal advice or law-enforcement evidence handling.

Detect early indicators of distributed or agentic abuse before a confirmed incident. Use when correlating reconnaissance-like behavior, authentication anomalies, or unusual request patterns. Do not execute countermeasures without approved policy.

Capture a recurring task as either a backlog entry or a new skill skeleton. Use when the user says "I keep doing X", "this is the third time", "make this a skill", "let's capture this", or at the natural end of a work session when a repeatable pattern just occurred. Extracts the pattern from conversation context (tools used, sequence of steps, input/output formats, corrections made) and produces either a BACKLOG.md line or a SKILL.md skeleton following this repo's conventions — not full skill authoring (that's skill-creator's job once a skeleton exists).

Identify deviations, gaps, and exception paths between an as-is process capture and its intended design. Use this skill when the user wants to find where a process breaks down, where steps are missing or inconsistent, where exception handling is undefined, or where current execution differs from documented procedure. Use when they say "what's wrong with the current process", "find the gaps", "where does this break", or "analyze exceptions". Produces a gap analysis report and exception catalog.

Identify deviations, gaps, and exception paths between an as-is process capture and its intended design. Use this skill when the user wants to find where a process breaks down, where steps are missing or inconsistent, where exception handling is undefined, or where current execution differs from documented procedure. Use when they say \"what's wrong with the current process\", \"find the gaps\", \"where does this break\", or \"analyze exceptions\". Records gaps only — it does not propose solutions or redesign; for that, hand off to okhp3-future-state-change-strategy. Produces a gap analysis report and exception catalog.

Conduct structured process intake and scope definition using BABOK v3 elicitation techniques. Use this skill when the user wants to document a business process from scratch; when they describe a workflow, procedure, or set of steps and need it structured; when they ask to scope a process, define process boundaries, or capture business rules; when they say "help me document this process", "let's scope out this workflow", or "what are the inputs and outputs"; when you need a Process Intake Record (PIR) as input for downstream narrative, modeling, or SOP skills.

Conduct structured process intake and scope definition using BABOK v3 elicitation techniques. Use this skill when the user wants to document a business process from scratch; when they describe a workflow, procedure, or set of steps and need it structured; when they ask to scope a process, define process boundaries, or capture business rules; when they say \"help me document this process\", \"let's scope out this workflow\", or \"what are the inputs and outputs\"; when you need a Process Intake Record (PIR) as input for downstream narrative, modeling, or SOP skills. This is the first-pass discovery skill; once a PIR exists, use okhp3-elicitation-interviews to fill remaining gaps rather than restarting intake.

Define process performance measures, KPIs, and compliance controls for a validated PNS. Use this skill when the user needs to add measurability and governance to a documented process; when they ask to define KPIs, set performance targets, add compliance controls, or map the process to a control framework. This is a recommended extension skill — use after okhp3-process-narrative-authoring when governance and measurement rigour beyond the PNS's own kpis section is required. Produces a measures register and a controls register.

Author and validate a Process Narrative Specification (PNS) from a PIR and stakeholder register. Use this skill when you have a completed Process Intake Record from okhp3-process-intake-and-scope and need to produce a structured narrative document that anchors ISO 9001 §4.4.1 process-box semantics, BABOK Core Concept Model, RACI matrix, SIPOC table, business rules, decision points, KPIs, and controls. Do not use it when only a quick diagram is needed without governance structure — go directly to okhp3-visual-process-modeling for that. The PNS is the authoritative handoff input for okhp3-visual-process-modeling, okhp3-sop-work-instructions, okhp3-raci-governance-matrix, and okhp3-sipoc-generation.

Orchestrate the full V1–V9 validation suite across all BP-SKILL process artifacts and produce a 0-100 quality score with band classification. Use this skill when the user wants to validate a complete process documentation set before publication; when they ask \"is this ready to publish\", \"validate the process docs\", \"run the quality check\", or \"what is the quality score\". Do not use it to validate a single artifact in isolation — run that artifact's own validate script directly instead. Produces a validation report with per-artifact scores, rule-level findings, band classification (A–D), and a publication gate verdict.

Create or refine a realistic professional headshot from supplied or explicitly authorized recent photos. Use for LinkedIn portraits, authentic clothing and background choices, likeness-preserving revisions, or expression references. Produces a reviewable image and source/delivery record. Profile uploads, account changes, broad photo searches, and live camera capture require separately scoped instructions.

Point at a project folder, git clone, or repository and establish or refresh its purpose, vision, mission, goals, and task tracking from evidence. Starts with a detection phase choosing Mode A, a GitHub-backed repo tracked through milestones, issues, sub-issues, labels, and releases via the gh CLI, or Mode B, a plain folder tracked entirely in files. First run infers intent from README, docs, ADRs, commits, TODO markers, and structure, then scaffolds a charter, an objectives-to-tasks decomposition, and machine-readable tracking with stable IDs. Later runs reassess progress, mark work done, blocked, or abandoned with evidence, surface new or changed goals as scope drift, flag orphaned and stale work, and emit a delta report. Also activate for "what is this repo even for", "is this project still on track", "did anything change since last time", scheduled or unattended check-ins, and projects with no tracking artifacts. Handles monorepos, content-first repos, and folders with no git histo

Prepare an exploratory effort that cleared the graduation gate for owner-approved formalization. Use to assemble the destination brief, provenance, decisions, risks, artifact inventory, and first formal-project action. Do not create repositories, publish, push, or move work externally without separate authorization.

Select or execute preapproved, reversible, cost-proportional defensive responses to validated signals. Use when an alert needs action matched to confidence, impact, and authorization. Do not take high-consequence action autonomously.

Assemble all validated BP-SKILL process artifacts into a publication-ready bundle with a manifest, approvals record, and completeness check. Use this skill when the user is ready to publish or hand off a complete process documentation set; when they ask to package the process docs, create a handoff bundle, publish the process artifacts, or generate a release package. Requires a passing validation report (Band A or B) before bundling — this is the terminal, all-artifacts step; for a single-artifact quality check use okhp3-process-validation-scoring instead. Produces a MANIFEST.yaml, APPROVALS.yaml, and a ZIP-ready directory structure.

Generate and validate a RACI matrix and governance responsibility document from a validated PNS. Use this skill when the user needs a standalone RACI chart, a governance matrix, or a responsibility assignment document for a process; when they ask to produce a RACI table, document who is responsible for what, or generate a governance framework for a process. Do not use it when the RACI table embedded in the SOP's Responsibilities section is sufficient — use okhp3-sop-work-instructions directly for that. Derives directly from PNS roles_and_raci and activity_sequence sections. Produces raci.md and governance-matrix.md.

Generate safe characterization tests for an undocumented web application, preserving observed behavior, permissions, documents, and regression baselines. Do not call captured legacy behavior correct.

Reconstruct an undocumented web application's code structure, dependency maps, control flow, and boundaries from evidence. Also activate when deciding whether to extend, refactor, or replace the system.

Preserve and inventory source, deployment, runtime, configuration, and business artifacts before analysis of an undocumented application. Also activate when hashes, provenance, redaction, or source-versus-deployed identity matters.

Plan a reversible migration and cutover for a reclaimed application, including data, integrations, rollback, ownership, and evidence gates, when a migration needs reversible stages and explicit ownership. Do not execute the migration.

Fingerprint the technology, runtime, dependency, hosting, database, and deployment platform of an undocumented web application so downstream teams can select the correct archaeology, security, testing, or modernization method.

Trace authentication, authorization, roles, permissions, tenant boundaries, and protected actions in an undocumented web application to activate when identity risk must be reviewed without becoming an unapproved penetration test.

Guide implementation of an approved replacement web application in small, testable increments with secure defaults. Do not improvise changes to the legacy system.

Turn reclaimed application evidence into a replacement specification. Make requirements, acceptance criteria, traceability, and unresolved decisions explicit.

Reconcile source, configuration, deployment, observability, and runtime evidence to determine what is actually running and where the baseline is stale. Also activate when creating a support baseline without changing the running system.

Establish authority, target identity, data boundaries, technique modes, approvals, and stop conditions before reclaiming an undocumented application. Activate when a request could become a security test, production change, or access to sensitive data.

Conduct an authorized, evidence-led security review of an undocumented web application for an assessor or remediation baseline. Keep security review distinct from penetration testing.