--- title: "jonhill90-skills" description: "Jon Hill's public collection of portable Agent Skills: self-contained, model- and harness-agnostic instructions an AI coding agent loads on demand." canonical: https://agentpluginsdirectory.com/plugins/jonhill90-skills last-updated: 2026-09-26 --- # jonhill90-skills Jon Hill's public collection of portable Agent Skills: self-contained, model- and harness-agnostic instructions an AI coding agent loads on demand. - Slug: jonhill90-skills - Publisher: Jon Hill - Repository: https://github.com/jonhill90/skills - Manifest: plugin.json - Category (editorial): agent-tooling - Skills: 41 (adopt-or-build, ask-a-council, close-the-loop, create-skill, decide-by-variant, derive-independently-then-compare, determine-intent, determine-signals, devils-advocate, dispatch-brief, dispatching-subagents, distill, durable-fact-before-label, failing-test-first, github-cli, keep-me-honest, linear, loop-contract, loop-memory, mechanize, memory-conventions, mine-transcripts, notify, obsidian, plan-parallel-execution, prd, primer, progressive-disclosure, prompt-corpus, refuse-invented-identity, research-the-limit, safe-deletion, sanity-check, spec-driven-development, spec, supervised-lane-loop, tdd, test-in-the-consumer-context, tmux, verify-the-instrument, wire-it-when-you-write-it) - MCP servers: 0 - Stars: 9 - Repository created: 2025-06-01 - Repository last pushed: 2026-09-11 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/jonhill90-skills - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What jonhill90-skills does, in the publisher's words Jon Hill's public collection of portable Agent Skills, self-contained, model- and harness-agnostic instructions an AI coding agent loads on demand. Every skill here is individually installable; nothing in this repository is specific to any one harness, and nothing here depends on private tooling or evidence. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/jonhill90/skills/HEAD/README.md ## Skills - adopt-or-build: Decide, per component, whether to adopt an existing name, dependency, library, or tool or build it in-house, weighing blast radius over convenience. Use at the point a name or dependency is about to be chosen or recommended, before it is proposed, not after. Not for finding a technology's capabili… - ask-a-council: Convene several harnesses or models against one question, each doing a distinct job it can fail at, different evidence, a different objective, or a withheld conclusion, before an artifact becomes load-bearing and being wrong is expensive. Diversity comes from what each reviewer is given, never fr… - close-the-loop: Confirm you have everything needed to finish a change before starting it, what to implement, how it will be tested, and which rules govern it. Use before non-trivial work, when reviewing a plan for completeness, or when preparing a PR that needs planning evidence. - create-skill: Design, create, and validate portable Agent Skills with effective triggers, concise instructions, and reusable scripts, references, or assets. Use when adding a new skill, substantially restructuring an existing skill, or validating a skill's structure, frontmatter, links, and bundled scripts. - decide-by-variant: Build several genuinely different real artifacts in the real medium with fake data, and let the human pick by looking, instead of asking a taste decision in prose. Use whenever a decision has no objectively right answer, a glyph, a layout, a default, a name, a wording, a sort order, and describin… - derive-independently-then-compare: Derive an answer from the source corpus a second time, without reading the first derivation, then compare, before trusting a conclusion drawn from a large body of transcripts, notes, or documents about what someone wants, prefers, or constrains. Use when a claim about a person's stated intent or a… - determine-intent: Work out what the user actually wants, from the literal words of the request and from what they have already told you, before starting the work, and state that reading so it can be corrected. Use before acting on a non-trivial request, especially one that echoes something asked before, one that c… - determine-signals: Find out what has already been said, in transcripts, issues and PRs, the ledger, the notebook, and vault facts, before asking a question or stating a fact as current, and prefer live system state over any stored record when they disagree. Use before acting on a non-trivial request, right where yo… - devils-advocate: Argue the strongest honest case against a plan or decision before it is committed, not after. Use before a hard-to-reverse choice is finalized, a build-vs-adopt call, an architecture pick, a plan about to be executed, while the decision can still change. Distinct from sanity-check, which tests wh… - dispatch-brief: Write the brief that hands a bounded piece of implementation or verification work to a lane or subagent, name the failure with evidence, require a two-directional mutation test, state which failure direction is worse, forbid weakening a guard to reach green, allow "could not measure" as a real ver… - dispatching-subagents: Decide whether to delegate work to subagents, set each one's isolation boundary, and verify their output with external evidence. Use when considering fanning work out to parallel agents, orchestrating multiple agents, or reviewing whether a multi-agent result can be trusted. - distill: Reduce a large body of source material to the smallest thing a reader can act on, at the cost of proportion, not a shorter version of everything, a decision about what matters. Use when asked to distill, or when the request is "what do I do about this" rather than "what does this say"; not for a s… - durable-fact-before-label - failing-test-first - github-cli - keep-me-honest - linear - loop-contract - loop-memory - mechanize - memory-conventions - mine-transcripts - notify - obsidian - plan-parallel-execution - prd - primer - progressive-disclosure - prompt-corpus - refuse-invented-identity - research-the-limit - safe-deletion - sanity-check - spec-driven-development - spec - supervised-lane-loop - tdd - test-in-the-consumer-context - tmux - verify-the-instrument - wire-it-when-you-write-it Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.