Menu
SkillsMP a collecté 54 skills depuis p10ns11y/skills. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 54.
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…
Langue du texte source : anglais
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.…
Langue du texte source : anglais
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,…
Langue du texte source : anglais
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,…
Langue du texte source : anglais
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;…
Langue du texte source : anglais
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:…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Overarching patterns for self-guarded, pause-aware, agent-driven desktop/web platforms. Combines finder-reactor, Tauri shell, X resources, and CV guard into a cohesive autonomous system with intervention only on guards. Use for high-level autonomy design,…
Langue du texte source : anglais
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,…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Runs Hermes, OpenClaw, and Grok Build concurrently on isolated git worktrees or cloud sandboxes (Modal, Daytona, E2B, Fly Sprites). Use when orchestrating multiple CLI coding agents, git worktree isolation, subagents in separate branches, or offloading agent…
Langue du texte source : anglais
Core autonomous, self-guarded decision loop for opportunity-finder apps. Handles discovery (e.g. X search), analysis (LLM + CV + platform context), prep generation, tracking, and guarded promote with cost/rate/fit/CV mutation guards, human pause points,…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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 global…
Langue du texte source : anglais
DEPRECATED alias for control-graph. Outer state machine/loop + inner DAG or nested loops, budgets, HITL, multi-model routing. Prefer control-graph; this file only redirects. Triggers: looper (legacy).
Langue du texte source : anglais
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
Langue du texte source : anglais
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, spacemaps, arch-design/coming-next.md, backlog after PRs, or when…
Langue du texte source : anglais
Delegate broad exploration to a subagent with a fixed Return format. Use when the task needs readonly repo mapping, token/CSS/prosody surveys, QA module exploration, or "explore thoroughly" with numbered deliverables.
Langue du texte source : anglais
Inspect git status, remove junk/legacy/secrets from the commit set, craft a conventional commit message, and commit locally; push only with explicit user approval. Use before shipping a logical unit of work. Triggers: tidy commit, conventional commit,…
Langue du texte source : anglais
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 ~/.config/shell core/, plugins/verification/, bin shims, moving files across the kernel…
Langue du texte source : anglais
DEPRECATED alias for stellar-spacemap. Architecture backlog docs: scorecards, SN-* cards, thrive vision, gantt. Prefer stellar-spacemap; this file only redirects. Triggers: stellar-roadmap (legacy).
Langue du texte source : anglais
Publish a project-born skill into both the consuming project tree and the portable skills library with matching content, index updates, and hash/symlink verification. Use when promoting a project-only skill outward or fixing drift between two git-tracked…
Langue du texte source : anglais
Prevents user-systemd / UWSM / Hyprland first-login failures caused by pulling graphical-session (or compositor) targets from Persistent timers under Linger. On Omarchy-flavoured Arch (Hyprland + omarchy CLI + ~/.config/omarchy), ALSO load the omarchy skill…
Langue du texte source : anglais
One-pass rename of a skill: folder, frontmatter name, Cursor rules, validators, README catalog, pack scripts, workflows, and consuming-repo references. Use when renaming skills (e.g. looper → control-graph) or after folder moves. Triggers: skill rename,…
Langue du texte source : anglais
Graphite (gt) stacking decision and execution: diagnose coupling, honestly recommend when gt is overkill (plain branches / split-to-prs / sequential), and when chosen enforce commit-in-generation + two-phase handoff + backup refs so code is never lost. Use…
Langue du texte source : anglais
Systematically read modules, grep for mappings, run tests, and capture evidence of bugs or leaks before verdict
Langue du texte source : anglais
Incorporate user review comments on plan.md by editing anti-refs and adding SN cards
Langue du texte source : anglais
load multiple skills via system reminders then drive a goal using their combined rules
Langue du texte source : anglais
when performing pnpm audit fixes, deprecation removal, supply-chain hardening with sfw; agent-agnostic under .agents/skills/
Langue du texte source : anglais
Keep git-tracked project copy under .agents/skills/ while maintaining identical copy under {REPO_ROOT} and pushing both to skills remote
Langue du texte source : anglais
Read goal plan then immediately call todo_write before any code changes
Langue du texte source : anglais
when authoring a new agent skill: read plan, seed todos, write SKILL.md + rule + validation script then update indexes
Langue du texte source : anglais
when creating a new portable skill: read plan, write SKILL.md + rule + validation, update indexes and todos
Langue du texte source : anglais
rename skill folder/rule/index everywhere then update both library and consuming repo
Langue du texte source : anglais
Inspect, clean legacy files, verify privacy, then commit and push with conventional message
Langue du texte source : anglais
Create a new project SKILL.md for a repeatable workflow. Use when user asks to add a skill for vulnerabilities, package upgrades, audits, supply-chain checks, or any named agent workflow.
Langue du texte source : anglais
Harvest Cursor, Grok Build, Kilo, and Cline agent transcripts into agent-prompt-tuning-lab: pnpm harvest:all, seed-manifest, env vars, and gold tagging. Use when collecting or re-indexing local agent JSONL for this repo.
Langue du texte source : anglais
Manifest V3 Chrome extension development — service worker lifecycle, message passing (popup ↔ service worker ↔ content script), content script injection, and host_permissions fetch patterns. Use when editing manifest.json, background/service worker, popup,…
Langue du texte source : anglais
Strict self-guarded mechanism for reading an external CV source (e.g. cvdata.json in a portfolio repo) for grounding and safely promoting insights back with sidecars, diffs, previews, backups, and explicit user confirmation. Never mutates external profile…
Langue du texte source : anglais