Showing 46831–46860 of 77205 skills
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
BumpyClock/agent-templates
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
BumpyClock/agent-templates
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.
BumpyClock/agent-templates
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
BumpyClock/agent-templates
Review code changes using Hyperlane monorepo coding standards. Use when reviewing PRs, checking your own changes, or doing self-review before committing.
recoil-labs/recoil-link
The alphabetical-sort invariants the hyperlane-registry CI / CodeRabbit enforces on warp route YAML (deploy.yaml and config.yaml) — top-level chain entries sorted by chain name, and keys within each entry in strict alphabetical order — plus the canonical per-file key orderings and a verification pass. Referenced by any warp deploy/update skill that writes or edits a registry YAML file.
recoil-labs/recoil-link
Canonical legend for expanding a `less than KEY_PROTOCOL_VALUEgreater than ` placeholder into a shell substitution based on the key-context artifact's `source` field, plus the mandatory `pnpm --silent` rule that keeps the resolved key out of logs and the display-the-key-name-before-CONFIRM disclosure. Referenced by every warp deploy/update skill that passes a `--key.protocol` flag.
recoil-labs/recoil-link
agentskillexchange/skills
agentskillexchange/skills
agentskillexchange/skills
agentskillexchange/skills
Run a multi-agent build session: the main session acts as manager — cutting a goal into units, spawning implementer, tester, and adviser subagents, and running the test-and-review loop to completion under anti-thrash guardrails.
NagareNegishi/Job-Application-Tracker
Apply whenever writing or editing code in any language, even if comments are not explicitly requested. Enforces comment and documentation discipline: concise file headers, function docs in the language's native format, inline comments for non-obvious logic, and protection of existing comments. Not required during suggestion-only or discussion when no file is written.
NagareNegishi/Job-Application-Tracker
Audit the repository for comment coverage and bring under-commented source up to standard. Walks one file at a time, proposes comments per file for approval, and tracks progress to resume across sessions. Invoke with /comment-audit.
NagareNegishi/Job-Application-Tracker
Upgrade outdated dependencies one package at a time, with a changelog check for breaking changes and a test run between upgrades. Invoke with /dependency-upgrade; pass package names to limit scope.
NagareNegishi/Job-Application-Tracker
Use this skill whenever the user needs help choosing between programming technologies, libraries, frameworks, tools, patterns, or architectural approaches. Covers all programming domains. Trigger even if the user doesn't say "suggest" explicitly — any programming decision where options exist and verification matters should use this skill.
NagareNegishi/Job-Application-Tracker
Improve the visual design of the job tracker React frontend. Use when asked to improve, redesign, restyle, or enhance the UI in job-tracker-ui/.
NagareNegishi/Job-Application-Tracker
Write documents in a plain, human voice and remove phrasing that reads as machine-generated. Use this skill EVERY time you produce a written artifact meant to be read by a person: READMEs, official documentation, design or planning docs, summaries, reports, proposals, release notes, changelogs, commit messages, GitHub issues, pull request descriptions, letters, emails, blog posts, and similar deliverables. Trigger it whenever the task is "write/draft/generate a doc" rather than answering a question in chat. Do NOT trigger it for direct conversational replies, inline explanations, or code. Run it in two passes: write the document, then re-read the finished draft and rewrite anything that signals a machine wrote it, presenting only the corrected version.
NagareNegishi/Job-Application-Tracker
Create or reconcile a repository's labels from the preset in `labels.yml`. Writes labels only — never deletes, never touches labels outside the preset. Invoke with /label-setup.
NagareNegishi/Job-Application-Tracker
At session end, write the one-file session baton (docs/session/baton.md): a high-level summary of what this session was about, the goal, and the single next task. Overwrites the file — no change lists, no task lists, no detail. Read-only on git; writes only the baton. Use `session-wrapup` for git state and progress.md.
NagareNegishi/Job-Application-Tracker
Close out a working session: update `docs/progress.md`, report uncommitted and unpushed work, and list the session's decisions and open threads. Read-only on git — never commits, stages, or pushes.
NagareNegishi/Job-Application-Tracker
Apply whenever the task is diagnosing a bug, a failing test, or unexpected behavior — even if the user only says "fix it". Core rule: never fix what has not been reproduced. Not required for feature work, or when the user has already stated the cause and only wants the change made.
NagareNegishi/Job-Application-Tracker
Improve the visual design of the job tracker React frontend. Use when asked to improve, redesign, restyle, or enhance the UI in job-tracker-ui/.
NagareNegishi/Job-Application-Tracker
Canonical entry skill whenever a shared change may need to reach sovereign node repositories. Routes package publication, exact package bumps, pinned workflows, fail-closed codemods, literal source ports, and node-owned product changes to separate knowledge atoms.
cogni-dao/cogni
Redirect for requests phrased as node-template sync. Load node-sync-prs, which owns every supported path from shared change to sovereign node repository.
cogni-dao/cogni
Use when implementing a code change, opening a code PR, or resuming its CI, flight, merge, or promotion. Routes delivery to the current node's contracts. Routes each work-item status to its lifecycle command. Explanations and knowledge-only contributions use their task-specific guidance.
cogni-dao/cogni
Use before authoring or reviewing a Cogni knowledge entry with entryType html — a diagram, matrix or status grid for human review. Html is diagram-first, themed by the renderer, and nearly prose-free; anything an agent must recall stays a markdown text atom.
cogni-dao/cogni
Generate guided Chinese software copyright application materials from a real project. Use this skill when the user asks for 软件著作权, 软著申请资料, 软著代码材料, 操作手册, 申请表信息, or wants Word/TXT materials for software copyright registration. The workflow analyzes the imported project, extracts real source code, creates Markdown drafts for user confirmation, then uses bundled DOCX tooling to produce final Word documents and TXT.
aboylabs/ai-agent-skills
塔勒布(Nassim Nicholas Taleb)的思维框架与表达方式。基于40+个来源的深度调研, 提炼6个核心心智模型、9条决策启发式和完整的表达DNA。 用途:作为思维顾问,用塔勒布的视角分析问题、审视决策、质疑主流叙事。 当用户提到「用塔勒布的视角」「塔勒布会怎么看」「塔勒布模式」「反脆弱视角」「taleb perspective」时使用。 即使用户只是说「会不会黑天鹅」「这个有尾部风险吗」「skin in the game」「有没有反脆弱的方法」「杠铃策略怎么用」也可触发。 不要在用户只是做一般风险评估或问「靠不靠谱」时触发——只在涉及极端风险、反脆弱、预防原则等塔勒布核心概念时激活。
alchaincyf/taleb-skill
Use this skill when planning or executing the human side of an Agentforce or Einstein AI feature rollout — user trust-building, AI-specific training, structured feedback collection via the Feedback API, and adoption measurement via Agentforce Analytics. NOT for turning the Einstein for Sales features on — use agentforce/agentforce-sales-ai-setup. NOT for rollout training with no AI in scope — use admin/change-management-and-training.
PranavNagrecha/AwesomeSalesforceSkills