Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
joeldevzSkilljoeldevz/skynex-pi/skills/adversarial-review/SKILL.md
On-demand adversarial review for non-code decisions — proposals, architecture, plans, specs. Two independent judges in parallel surface blind spots the single-author missed.
joeldevzDeletes or force-pushesSkilljoeldevz/skynex-pi/skills/archive-spec/SKILL.md
Trigger: archive-spec, archive feature spec, spec archive. Archives a completed feature change folder to .skynex/archive/YYYY-MM-DD-<slug>/ after sync is confirmed. Immutable audit trail.
joeldevzSkilljoeldevz/skynex-pi/skills/branch-pr/SKILL.md
Create a pull request for the current branch following project conventions. Validates branch name, runs pre-push checks, gates before push, and produces a structured PR body.
joeldevzSkilljoeldevz/skynex-pi/skills/build/SKILL.md
Phase 3 of the Medium-path workflow. Use after plan produced PLAN.md. Iterates slices, spawning coder+verifier in chain mode (with retry-on-fail) or multiple coders in parallel for disjoint slices. Handles HITL gates for high-risk paths.
joeldevzDeletes or force-pushesSkilljoeldevz/skynex-pi/skills/chained-pr/SKILL.md
Split large changes (>400 lines OR >5 slices) into a series of reviewable PRs. Two strategies — stacked-to-main and feature-branch-chain. Prevents the 100-conflict merge disaster.
joeldevzSkilljoeldevz/skynex-pi/skills/cognitive-doc-design/SKILL.md
Design documentation that reduces cognitive load — progressive disclosure, recognition over recall, signposting. Apply to PRDs, SPECs, architecture docs, READMEs, PR descriptions.
joeldevzSkilljoeldevz/skynex-pi/skills/comment-writer/SKILL.md
Draft warm, direct collaboration comments for PR reviews, issue replies, Slack messages, and async project updates.
joeldevzSkilljoeldevz/skynex-pi/skills/discover/SKILL.md
Phase 1 of the Medium-path workflow. Use when triage classifies a task as medium or substantial. Delegates to the scout sub-agent to gather codebase context + Neurox prior decisions, then returns a structured exploration envelope to be passed to the plan skill.
Often used withdaily-arxivexp-evalexp-run
joeldevzSkilljoeldevz/skynex-pi/skills/grill-me/SKILL.md
Relentless one-question-at-a-time discovery for non-trivial features. Use BEFORE writing a PRD, proposal, or plan. Stops vibe coding. Forces shared design concept with the user.
Often used withbrief-to-taskswriting-beatsrequest-refactor-plan
joeldevzSkilljoeldevz/skynex-pi/skills/onboard/SKILL.md
First-time project onboarding. Scans codebase, identifies stack/conventions/architecture, and saves knowledge to Neurox for all future sessions. Run once per project.
Often used withsoak-testteach-impeccableproject-stage-detect
joeldevzSkilljoeldevz/skynex-pi/skills/plan/SKILL.md
Phase 2 of Medium and Substantial-path workflows. Invokes tech-planner to produce PLAN.md. On SUBSTANTIAL path, this is the SINGLE HITL gate by default — blocks for explicit user approval before /skill:build (showing proposal.md + SPEC.md + PLAN.md together). On medium path, only blocks if new_dependencies non-empty or any slice has requires_hitl=true (current Sprint 2 behavior).
Often used withheartmulawebhook-subscriptionstouchdesigner-mcp
joeldevzSkilljoeldevz/skynex-pi/skills/prd/SKILL.md
Formal Product Requirements Document for stakeholders. Use when a feature needs business sign-off before engineering. Produces user stories, acceptance criteria, NFRs, and out-of-scope sections.
joeldevzSkilljoeldevz/skynex-pi/skills/propose/SKILL.md
Substantial-path proposal skill. Invokes product-planner to write a 1-page proposal.md. By default AUTO-CONTINUES to /skill:specify (no gate). Only blocks for user approval when SKYNEX_HITL=strict.
joeldevzSkilljoeldevz/skynex-pi/skills/research/SKILL.md
Deep web research on external topics — libraries, APIs, prior art, documentation. Use when local context is insufficient and internet lookup is needed.
Often used withdaily-arxivProblem-Solving Techniquessetup-ts-deep-modules
joeldevzSkilljoeldevz/skynex-pi/skills/security/SKILL.md
On-demand security audit of code, config, or infrastructure. Use when the user wants security review outside the normal /skill:validate flow.
Often used withalbert-dmcost-reducertrigger-dev
joeldevzSkilljoeldevz/skynex-pi/skills/skynex-execute/SKILL.md
Execution mode flow. Sequential 8 steps — fetch, discover, test-audit, TDD-proposal (HITL), generate-tests, implement, validate, PR. Activated by /skynex:execute. Delegates discovery, build, validate, and PR phases to existing sub-skills.
joeldevzSkilljoeldevz/skynex-pi/skills/skynex-research/SKILL.md
Research mode synthesis protocol. Called by the main model after 3 parallel research agents (neurox, web, code) return their envelopes. Synthesizes a final verdict with source attribution.
joeldevzSkilljoeldevz/skynex-pi/skills/skynex-sdd/SKILL.md
SDD (Sustainable Design Delivery) mode lifecycle. Full 8-phase workflow — discover, propose, specify, plan (HITL gate), build, validate, sync, archive. Activated by /skynex:sdd. Delegates each phase to existing sub-skills (discover, propose, specify, plan, build, validate, sync, archive-spec).
joeldevzSkilljoeldevz/skynex-pi/skills/skynex-task/SKILL.md
Task-creation mode flow. Sequential 4 steps — grill, decompose, HITL gate, Jira creation. Activated by /skynex:task. Main model is the executor; no sub-agents.
joeldevzSkilljoeldevz/skynex-pi/skills/specify/SKILL.md
Substantial-path specification skill. Invokes product-planner + architect IN PARALLEL, merges into unified SPEC.md. By default AUTO-CONTINUES to /skill:plan (no gate). Only blocks for user approval when SKYNEX_HITL=strict.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
