p10ns11y

Engineering-judgment overlay for control-graph + eva-emptiness: diagnose Odysseus mistakes (Cyclops leak, Sirens rewrite, Helios prod, Circe overbuild, Winds unbounded, Scylla big-bang, ignored prophecy), prescribe professional antidotes, and gate Odysseus…

Pre-control-graph feeder: rewrite a dumped prompt, pick tools/plugins/skills, then route light vs control-graph Outer vs EVA Inner. Use when starting from a paste, --prompt-file, --prompt-json, -p/--single, or a messy dump before opening a Control Card.…

Agent control-plane as a graph: outer state machine (or cyclic loop) over named phases, nested inner DAGs or bounded sub-loops, hard budgets, HITL pause gates, and multi-model routing (fast/explore/coding/deep/review). Use for multi-step agent cycles,…

Applies first-principles, multi-order consequence analysis, inversion, systems thinking, probability, antifragility, and high-energy thrive ascent (2036 lens) before material coding decisions (architecture, dependencies, public API, security, data contracts,…

Builds a project master plan as an interconnected web of friction-removing automations aimed at impossible missions. Resolves the skills library from SKILLS_ROOT, ~/Work/personal/skills, or clones https://github.com/p10ns11y/skills when local is missing;…

One-time (re-runnable) host prep for Grok Build: check binaries, lsp.json, [features] lsp_tools, MCP command existence, and efficiency knobs. Use when setting up a machine, enabling LSP, or a Feed harness_gap is mcp / permissions / 8192. Triggers:…

Adversarial verification of claimed work: read shipped modules (not memory), grep wiring and approvals, run tests, demand evidence before pass verdict. Use when reviewing agent output, PRs, or security-sensitive changes before merge. Triggers: adversarial…

Triage every non-trivial task first: single-shot when safe, full orchestration when multi-step, multi-agent, or high-risk. Covers briefs, verification before "done", iterative waves, and resume. Use when coordinating workers, delegating, or reviewing agent…

Author a SKILL.md that works as a Cursor skill and a Grok slash command (/skill-name). Use when creating or porting a frequent workflow skill across agents, or when the user runs /portable-skill-author or /create-skill for multi-agent install.

Generate PDF, rename with name-role-job-id, copy to devprofile/out/apply and pack submit folder

Apply /impeccable to convert vertical chip wall into two-pane interview desk while keeping answer in primary viewport

compare featured projects against target apply pack (xAI) and update overlay to include only relevant ones like collab-finder, elomaxz, adaptate

Create gitignored application_packs symlink from collab-finder into devprofile for clean CV input

replace generic opp_N names with company-title-date slugs for both pack folders and output CV filenames

Use grep + web_fetch + read_file to map endpoint ACLs and key scopes when 403 appears on /documents/search

Rewrite first-person coder tone to general-audience visitor tone and correct golden short-circuit vs curated paths

Adversarial verification of claimed work: read shipped modules (not memory), grep wiring and approvals, run tests, demand evidence before pass verdict. Use when reviewing agent output, PRs, or security-sensitive changes before merge. Triggers: adversarial…

Triage every non-trivial task first: single-shot when safe, full orchestration when multi-step, multi-agent, or high-risk. Covers briefs, verification before "done", iterative waves, and resume. Use when coordinating workers, delegating, or reviewing agent…

Fission engine for token-efficient coding (JS, TS, Node, Rust, Python, ML/AI): relevance scoring, hierarchical compression, strict token budgets, progressive disclosure, accuracy guardrails. Pair with fusion-sage for synthesis/surplus. Triggers: tokens,…

Architecture synthesis after ai-optimization (fission): cross-file abstractions, ⚡ surplus (Q>1), optional session knowledge graph, binding energy toward iron-peak design. Use for architecture, domain models, compounding maintainability — not pure one-file…

Agent control-plane as a graph: outer state machine (or cyclic loop) over named phases, nested inner DAGs or bounded sub-loops, hard budgets, HITL pause gates, and multi-model routing (fast/explore/coding/deep/review). Use for multi-step agent cycles,…

Map the relevant code with Glob/Grep/Read before writing. Use when the user asks to change, fix, or add behavior and the touch points are unclear, or when top tool sequences show Read→Grep→edit. Also for /explore-then-edit.

Fusion on fission: after ai-optimization pruning, synthesize cross-file abstractions, emit ⚡ surplus (Q>1), maintain a session knowledge graph, and score binding energy toward iron-peak design. Use for architecture, domain models, compounding maintainability…

Applies first-principles, multi-order consequence analysis, inversion, systems thinking, probability, antifragility, and high-energy thrive ascent (2036 lens) before material coding decisions (architecture, dependencies, public API, security, data contracts,…

Triage every non-trivial task first: single-shot when safe, full orchestration when multi-step, multi-agent, or high-risk. Covers briefs, verification before "done", iterative waves, and resume. Use when coordinating workers, delegating, or reviewing agent…

Fission engine for token-efficient coding (JS, TS, Node.js, Rust, Python, ML/AI). Pruning, compression, strict token budgeting. Pair with fusion-sage for synthesis and surplus. Trigger on implementation, debugging, refactoring; hand off architecture to…

Fusion-oriented evolution of Context Sage. Uses the original fission engine as containment field, then adds synthesis, surplus generation, and self-amplifying knowledge loops. For AI coding tasks where you want not just efficiency, but compounding…

Effective git worktree workflows for agents and humans: branches vs worktrees, safe commit-then-merge integration (never cp into main checkout), conflict handling, when to use or skip worktrees, macOS concurrency, and **disk hygiene for the global…

Applies first-principles, multi-order consequence analysis, inversion, systems thinking, probability, antifragility, and high-energy thrive ascent (2036 lens) before material coding decisions (architecture, dependencies, public API, security, data contracts,…

Structured agent loop manager: outer state machine (phases, transitions, checkpoints, HITL pause gates), bounded inner steps (DAG-style done/retry/cancel/max-iter), and multi-model routing (fast vs deep vs review vs explore). Use for multi-step agent cycles,…

Builds a project master plan as an interconnected web of friction-removing automations aimed at impossible missions. Installs portable skills via npx skills from https://skills.sh/p10ns11y/skills (skills-lock.json), tweaks via project overlays, and adds…

Authors evidence-driven architecture backlog docs (coming-next style): scorecards, mermaid diagrams, blueprint cards SN-*, thrive vision, gantt order. Use when creating or updating roadmaps, arch-design/coming-next.md, backlog after PRs, or when the user…

Audit web layout-content-view stability: landmark/sitemap graph, named viewports, overflow/clip/ellipsis on must-show data, z-index and scroll quirks. Survives redesigns because it measures boxes and roles, not pixels. Use when /layout-content-view, visual…

Companion to layout-content-view for code implementers. Propose then write data-lcv marks on routes and components so the probe can classify must-show, preview, beats, and interact edges. Use when /lcv-implement, adding a page, wiring a deck/dialog/nav, or…

Playbook map from Cursor pstack (Lauren Tan / poteto, MIT): match a playbook, load installed pstack when present, else house skills. House HITL wins on secrets, prod, irreversible git, unknown auth. Use for /pstack-map, pstack, poteto-mode, rigor playbooks,…

Resolve conflicts and contradictions in notes, memory, and harness state using admissions rules (archive vs memory). Always stamp context-hint tags (source, time, status, kind). Pulse sparse snippets instead of dumping transcripts. Use when claims disagree, a…

Build a Mission-Impossible-style ops map: steps, calculated risks, what/how/when, and how to adjust when outside shocks hit. Not a future oracle. Uses critical path, PERT bands, and sensitivity (∇T) to rank effort. Use when the user runs /mission-map, says…

Engineering-judgment overlay for control-graph + eva-emptiness: diagnose Odysseus mistakes (Cyclops leak, Sirens rewrite, Helios prod, Circe overbuild, Winds unbounded, Scylla big-bang, ignored prophecy), prescribe professional antidotes, and gate Odysseus…

Reasoning under epistemic emptiness: Prior → Probe → Simulate → Score → ActOrAsk (EVA tether). Use when the map/data is missing, unknowns dominate, requirements are rumor-thin, or authorization is the real unknown — not when the fix path is already clear.…

Operator surface for arch-machine: thin-first sentinel status, consent-gated thin install, threat-focused audit, expand/pull modules or profiles, archy control plane. Prefer archy + slash commands over gum tinfoil TUI. Use when user mentions arch-machine,…

Run prompt-tuning-lab insights and extraction workflow. Use in agent-prompt-tuning-lab when analyzing splits, mining tool patterns, or updating artifacts from gold sessions.

Add or extend turbo test scripts and coverage across a pnpm monorepo. Use when user asks for test scripts, turbo.json test pipeline, 100% coverage, or check-types fixes after package changes.

Organize markdown, images, and non-source clutter without breaking links. Use when user asks to organize md files, move images to images/, add logo to README, or clean repo root.

Plan lightweight Chrome extension monorepo delivery. Use when user asks monorepo split, delivery plan, or attached plan for extension refactor.

Broad codebase exploration with fixed deliverable. Use when user asks to explore thoroughly, map modules, trace data flow, or says Return with file tree / mermaid / pain points.

Generates project-specific tmux cockpits for shellyxz ab/av/at workflows. Reads AGENTS.md and stack scripts; writes .agents/verification/ (tmux-layout, cockpit.yaml, legacy manifests). Use when setting up or regenerating av/at project config, mission-control…

Load and maintain the shellyxz shell kernel ontology graph — PATH contract, kernel/plugin boundary, load order, and verification bridge (ab/av/at). Use when editing core/, plugins/verification/, bin shims, moving files across the kernel boundary, or answering…

Authors evidence-driven architecture backlog docs (coming-next style): scorecards, mermaid diagrams, blueprint cards SN-*, thrive vision, gantt order. Use when creating or updating roadmaps, arch-design/coming-next.md, backlog after PRs, or when the user…

Edit github.com/p10ns11y/p10ns11y README.md (the public profile). Use when the user edits the profile, GitHub README hero, featured products, hire-loop visibility, or runs /p10ns11y-profile.

Sorkalam MV3 Chrome extension (Tamil ↔ English). Use when editing popup.js, event.js, content.js, manifest.json, or dictionary lookup behavior in this repo.