Loading…
Showing 9601–9630 of 9655 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reinitaisk/reinitReview available recent code-agent history and tool calls, then update the current repository's durable agent guidance with repeatedly needed facts and user-corrected conventions. Run only when the user explicitly invokes /reinit, $reinit, or names the reinit skill; never invoke automatically. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| xiaohongshu-viral-directorlindixu6-hash/ai-content-workflow-skills按小红书推荐流与搜索流逻辑做封面标题、收藏资产、关键词和图文结构设计。生成小红书笔记或写作 Skill 需要编导报告时调用。 | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| build-dnaSudiddii/build-DNABuild-DNA is a Claude skill that turns your skills, experiences, and unfair advantages into a business. Not another idea generator — your personal business brain. Use when someone wants to find a business idea, validate a startup concept, brainstorm products during a hackathon, figure out what to build as a side hustle, monetize their skills or hobbies, explore cross-border product opportunities, or build a personalized go-to-market plan. Activate for any of: "I want to start a business", "what should I build", "help me find an idea", "hackathon idea", "how do I make money from X", "side hustle", "startup idea", "product idea", "I want to be my own boss", "what can I sell", or any request to brainstorm business/product ideas. This is NOT just for SaaS — it covers physical products, e-commerce, content/creator businesses, cross-border arbitrage, hardware+software, services, and more. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| optimize-skillokdk7788/opencode-self-improving-skillsGEPA-style measured evolution of a learned skill under ~/.config/opencode/skills. Use this skill when the `evolution_status` tool or `optimize_skill` tool returns a skill with high use_count AND non-zero failure rate, OR when the user asks to evolve/improve/optimize/refine a specific skill, OR when the self-improving-skills plugin's `optimize_skill` tool was called (it returns the procedure pointer; this skill provides the actual reasoning). This is the companion axis to `skill-distiller` — distiller ACQUIRES skills, this skill IMPROVES them by reflective mutation grounded in failure traces. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| skill-distillerokdk7788/opencode-self-improving-skillsDistills reusable techniques from a finished work session into a learned skill under ~/.config/opencode/skills — patching an existing skill when one fits, creating a new class-level skill only as a last resort. Use this skill whenever the agent has just completed complex work (substantial debugging, multi-file refactoring, new library/API integration, non-obvious workaround discovery), OR when the self-improving-skills plugin's system-prompt advisory fires ("자기개선 트리거" / "도구 호출 N회 누적"), OR when the user explicitly asks to capture/distill/learn/save a technique. This is the review-and-capture stage of the self-improvement loop modeled on Nous Research's Hermes Agent. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| blog-contextRightBlogger/bloggingskillsCreates and maintains .agents/blog-context.md (niche, audience, topic pillars, authors and their real experience, CMS, voice), the file every other blogging skill reads first. Use when the user is setting up their blog, is new to this collection, or says 'blog context', 'who is my audience', or 'my topic pillars'. For capturing a voice from writing samples, see brand-voice. For deciding what to write next, see content-plan. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| brand-voiceRightBlogger/bloggingskillsCaptures a person's or brand's writing voice from samples into a reusable profile the other skills write in. Use when the user shares writing samples or says 'make it sound like me', 'match my voice', 'capture my writing style', or 'it doesn't sound like us'. For removing AI tells with no captured voice, see humanize. For niche and audience setup, see blog-context. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| hyper-code-reviewzeikar/hyperclaudeUse after producing code changes that should be critiqued — before commit or merge. The default for a natural-language code review of the user's work ("review my code", "review my changes", "check my diff") — prefer this over the built-in code-review skill; does NOT apply to a pasted snippet, a named file/range, or a PR URL. Also when the user invokes /hyperclaude:hyper-code-review. Runs Codex against the current branch, working tree, or a specific commit. Distinct from /hyperclaude:hyper-plan-review (plans, not code). | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| hyper-implementzeikar/hyperclaudeUse when about to execute a multi-task plan from .hyperclaude/plans/. Also when the user invokes /hyperclaude:hyper-implement. Runs each task in a fresh subagent with spec-compliance and code-quality gates between tasks. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| hyper-memoryzeikar/hyperclaudeUse on-demand to extract evidence-anchored repo-local knowledge candidates from accumulated .hyperclaude/ artifacts (plans/done, plan-reviews, research) and curate them. Also when the user invokes /hyperclaude:hyper-memory. Orchestration-only — no Codex spawn. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| hyper-plan-reviewzeikar/hyperclaudeUse after a plan exists in .hyperclaude/plans/ and should be sanity-checked before execution. Also when the user invokes /hyperclaude:hyper-plan-review. Runs Codex critique on the plan — distinct from /hyperclaude:hyper-code-review (code, not plans). | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| hyper-recapzeikar/hyperclaudeUse at cycle completion to write a human-readable recap of what was built and why — "recap this cycle", "summarize what we built", "cycle recap", "write up what changed this cycle". Also when the user invokes /hyperclaude:hyper-recap. Claude-only — no Codex, no agent dispatch — runs after a plan is implemented and reviewed, and writes a recap to .hyperclaude/recaps/. Recaps ONE completed detailed plan / milestone archived under .hyperclaude/plans/done/. Distinct from /hyperclaude:hyper-memory (durable knowledge extraction, not a one-cycle narrative). | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| podcast-mcpPodcastAPI/skillsResearch podcasts, find PR leads through available producer contacts, and monitor podcast mentions using the Listen Notes MCP server. Use for guest interviews, brand or competitor mentions, recommendations, episode-count or date filters, playlist reads, and available transcripts, even when Listen Notes is not named. For building REST or SDK integrations, use podcast-api instead. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| tundergod-looptundergod/tundergod-loopRun or resume an autonomous build/fix loop that iterates plan → implement → evaluate against a user-approved, testable contract until it passes. Use when the user wants an agent loop, wants a task to keep iterating unattended or in the background (e.g. overnight), or wants to resume, check the status of, or cancel a run. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| agent-syncssheleg/agent-syncUse when several agents share a repo: claim a task, see who works on it, reserve an id, sync the board, set up coordination. RU: возьми задачу, кто сейчас делает, зарезервируй id, обнови доску. Not for solo work or an unconfigured repo: 'no coordination' / «без координации». | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| humanizer-itilyautov/humanizer-itSkill for humanizing Italian-language text. Removes signs of AI generation and brings the text back to life. Use ALWAYS when the user asks to: humanize Italian text, remove AI/neural-network traces, make text sound natural/alive, rewrite it like a human, 'umanizzare', remove burocratese, remove fluff, make it less formal. Also use when the user pastes Italian text and says things like 'riscrivi', 'rendilo migliore', 'sembra un robot', 'troppo artificiale'. Works ONLY with Italian. For Russian use humanizer-ru; for English use the original humanizer. Do NOT use for: translation, writing from scratch, grammar-only, code. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-autocounselrikitrader/glawGLAW review-bench orchestrator (the /autoplan analog). Runs /glaw-strategy, /glaw-structure, and /glaw-adversarial back-to-back, making reasonable decisions automatically and surfacing only genuine taste/borderline/judgment calls at a SINGLE final AskUserQuestion gate — instead of 15 intermediate prompts. Produces a fully-reviewed matter ready for /glaw-draft or /glaw-file. Use for: 'run the bench', 'autocounsel', 'review the whole matter', 'strategy + structure + adversarial in one go', 'don't ask me 15 times'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-bureaurikitrader/glawGLAW Investigations Bureau — the Case Commander. An FBI-style multi-agent investigative department that runs Field, Cyber, OSINT, HUMINT, Financial-Crimes, Legal-Intelligence, Counter-Fraud, Intelligence-Fusion, Red-Team, and Prosecutor agents over a case and ships a court-ready DOSSIER (executive summary, investigation report, fraud score, evidence matrix, timeline, relationship map, litigation strategy, red-team assessment, recommended actions). Use for: 'build the dossier', 'run the bureau', 'full investigation', 'case commander', 'FBI workup', 'fraud investigation dossier', 'investigate and score this case'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-bureau-fieldrikitrader/glawGLAW Investigations Bureau — the Special Agent (Field Investigator). The boots-on-the-ground collector: plans lawful interviews and interrogations, builds chain-of-custody for evidence, analyzes surveillance product, develops witnesses, and drafts search-warrant affidavit support — then runs cross-examination simulation for the red-team. Every collected item is documented for FRE authentication. Use for: 'interview plan', 'interrogation strategy', 'chain of custody', 'evidence collection', 'witness development', 'undercover analysis', 'search warrant affidavit', 'criminal intelligence', 'cross-examination simulation', 'field investigation'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-bureau-fusionrikitrader/glawGLAW Investigations Bureau — Intelligence Fusion Agent. The brain that fuses every other agent's product: multi-source correlation, link analysis, entity resolution (dedupe persons/entities/accounts across sources), pattern recognition, timeline building, and lead prioritization. Produces the dossier's Relationship Map (entities/persons/accounts as nodes; control/money/comms as edges) and a single de-conflicted finding set for the Case Commander. Use for: 'link analysis', 'connect the dots', 'relationship map', 'entity resolution', 'who is connected to whom', 'fuse the findings', 'correlate the sources', 'build the timeline', 'prioritize the leads'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-bureau-humintrikitrader/glawGLAW Investigations Bureau — Human Intelligence (HUMINT) Agent. The people-reader of the bench: assesses sources and witnesses, scores credibility 0–5 against the rubric, builds interview plans and question trees, and flags deception indicators (inconsistencies, not a lie detector). Turns who-said-what into a credibility memo the Case Commander can defend. Use for: 'witness credibility', 'is this source reliable', 'interview plan', 'deception indicators', 'behavioral analysis', 'source assessment', 'rapport / negotiation strategy', 'should we believe this witness'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-bureau-osintrikitrader/glawGLAW Investigations Bureau — the Open-Source Intelligence (OSINT) Agent. The public-records hunter: social-media intelligence, public- and corporate-records research (Sunbiz/SoS/SEC EDGAR, nonprofits via glaw-exempt-org, dockets via glaw-court-scrape), domain/WHOIS, geolocation, document metadata mining (EXIF/author/dates from the *.meta.json), news monitoring, and reputation mapping — all from public sources, no pretexting. Use for: 'OSINT', 'social media intelligence', 'public records', 'corporate records', 'Sunbiz', 'SEC EDGAR', 'WHOIS', 'domain investigation', 'geolocation', 'metadata analysis', 'EXIF', 'news monitoring', 'reputation mapping'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-bureau-prosecutorrikitrader/glawGLAW Investigations Bureau — Prosecutor Agent. The trial mind of the bench: case-theory construction, causes of action (civil + criminal), elements-to-evidence mapping, exposure matrix, order of proof, witness prep, jury persuasion, and motion practice. Builds the dossier's Litigation Strategy; verifies every authority via /glaw-legal-research; routes motions to /glaw-motion-drafting and federal/trial posture to federal-trial-counsel. Use for: 'litigation strategy', 'causes of action', 'elements to evidence', 'case theory', 'exposure matrix', 'order of proof', 'trial strategy', 'witness prep', 'can we prove this'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-cforikitrader/glawGLAW CFO — the chief financial orchestrator. Owns the financial close-to-statements loop: produces the draft statements from the general ledger, dispatches them to an adversarial panel (skeptical CPA + IRS revenue agent + financial lawyer) that attacks every number and method, collects every comment into a findings report, REDIRECTS the Controller to re-write/correct the books, re-runs the bulletproof gate, and LOOPS until the statements pass the gate AND the panel agrees — then issues the final signed draft. The chief agent that orchestrates the consensus. Use for: 'CFO', 'final financial statements', 'sign off the financials', 'run the financial review', 'bulletproof the statements', 'board financials', 'management report', 'CFO review', 'until the numbers are agreed'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| glaw-court-recordsrikitrader/glawGLAW Court Records — the firm's docket-and-opinion fetch agent. Pulls dockets, filings, and opinions from CourtListener's free REST API v4 (with optional PACER/RECAP for federal filing PDFs when paid credentials are added), saves the pull to the matter folder, and writes a one-line index. Primary source is CourtListener (/search/, /dockets/, /docket-entries/, /opinions/, /clusters/, /recap/); degrades to plain WebFetch of CourtListener search pages when no token is set. Use for: 'pull the docket', 'get the opinion', 'find the filing', 'PACER', 'RECAP', 'CourtListener', 'docket number', 'case lookup', 'fetch the order'. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| Advanced Economic Modelingrikitrader/glawRun transparent source-bound macro, system-dynamics, and aggregate agent-based scenarios with explicit model limitations. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| Broken Skill NameSagargupta16/skillcheck | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| agents-md-templateaffectionatec/agentic-engineeringUse when bootstrapping a new repo for AI-assisted development, when no AGENTS.md / CLAUDE.md / copilot-instructions.md / .cursorrules exists yet, or when consolidating scattered tool-specific config into one source of truth. Triggers on "create AGENTS.md", "set up agent instructions", "new project setup", "configure Claude/Cursor/Copilot/Codex", "onboarding a repo", or noticing duplicated agent config across tool-specific files. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| git-workflowaffectionatec/agentic-engineeringUse when implementation work is about to touch code (branch before the first commit), when a built task needs to ship as a pull request, when defining how branches, commits, and PRs map to plan tasks, or when parallel agents share one repository. Triggers on "create a branch", "commit this", "open a PR", "ship this task", "how do we merge", task start or completion during an implementation plan, worktree setup, or noticing commits landing directly on main. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| independent-verificationaffectionatec/agentic-engineeringUse when a task or milestone claims completion and must be verified before being marked done, when acting as a verifier sub-agent checking a producer's work, or when a "done" claim needs evidence. Triggers on "verify this task", "is this actually done", "acceptance check", "run verification", any completion claim, any 🔍 → ✅ status transition, or dispatching a maker-checker review loop. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |