Coding & Dev Tools
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
-
maeenseed Skill Social Media Content StrategistOwns ongoing social content strategy. Use for platform roles, content pillars, recurring formats, editorial calendars, and organic planning.
-
akash-joshi Skill DiscussIdentify gray areas in proposed work and capture decisions before planning. Use at the start of a new feature or piece of work to clarify HOW (not what) to build — surface implementation choices the user cares about, walk through them with concrete options, and produce a context file that plan mode or downstream agents can consume. Lightweight extraction of gsd-discuss-phase, no .planning/ scaffold required.
-
akash-joshi Bundle Playwright CLIAutomate browser interactions, test web pages and work with Playwright tests.
-
akash-joshi Skill Pr DescriptionWrite or revise a pull request or merge request description, or a commit message body. Load before drafting any PR/MR body, when rewriting one that reads as padded or unclear, and when a reviewer calls a description slop. Covers what to lead with, what to cut, and how to frame severity honestly. For voice (British English, no em-dashes, no bold-heading bullets) load writing-style as well.
-
akash-joshi Bundle VoicenotesSearch, retrieve and create notes in Voicenotes — semantic search, full transcripts, tag/date filtering, and text note creation through natural conversation.
-
akash-joshi Skill Tiger Style CodingApply TigerBeetle's Tiger-Style rules to any codebase. Load when writing, reviewing, or refactoring code — or when instructing AI coding agents (Claude Code, Codex, subagents) on style. Enforces safety > performance > developer experience priority order, function-length caps, runtime assertions, bounded loops, and dependency discipline. Works across TypeScript, JavaScript, Python, Go, Rust, and any language with runtime assertions.
-
akash-joshi Skill Ship V1Build and ship a first version of a validated startup idea. Use when the user has a validated idea and an entry angle and asks "how do I build this," "what should my MVP be," "how do I ship," "how do I start building," or mentions v1, MVP, or launching. This is the "Heat & Ship" stage of the B.R.O.T.H. framework. For choosing the entry angle first, see market-entry-strategies. For the demand mindset underneath it all, see demand-first-validation.
-
akash-joshi Skill Keyword SearchFind people actively looking for your service right now using platform search. Use when the user wants to find clients on Twitter/X, LinkedIn, or Telegram by searching for hiring posts, help requests, or project announcements. Also use when the user mentions "find clients," "keyword search," "who's hiring," "looking for leads," "find prospects on Twitter," or "social selling." This is the fastest path to first clients — you're finding people who already need help today. For writing the outreach message after finding them, see cold-dm. For building prospect lists from directories and databases, see prospecting-lists.
-
akash-joshi Skill Follow Up SequencesBuild multi-channel follow-up sequences that close deals. Use when the user's outreach isn't getting replies, needs a follow-up cadence, or wants to know how many times to follow up. Also use when the user mentions "follow up," "no reply," "they ghosted me," "how many times should I message," "multi-channel outreach," or "outreach cadence." Most deals close on the 3rd-5th touch, not the first. For writing the initial DM, see cold-dm.
-
akash-joshi Skill Profile OptimizationOptimise your social profiles to convert visitors into clients. Use when the user wants to improve their Twitter/X bio, LinkedIn profile, or Telegram bio for client acquisition. Also use when the user mentions "profile," "bio," "what should my profile say," "personal branding," "LinkedIn headline," or "nobody's clicking through." Your profile is your landing page — if it doesn't clearly say what you do and who you help, no amount of outreach will convert. For writing the outreach itself, see cold-dm.
-
akash-joshi Skill Market Entry StrategiesChoose the angle to enter a proven, competitive market with a startup idea. Use when the user has picked an idea but a competitor already exists, or asks "how do I compete," "how do I differentiate," "someone already does this, what now," or mentions going downmarket, upmarket, or entering an adjacent market. This is the "Tactics Time" stage of the B.R.O.T.H. framework. For validating demand first, see demand-first-validation. For building once the angle is set, see ship-v1.
-
cypher0n3 Bundle Just CI`just ci` final check must pass before execution is complete. Use this skill when finishing work in a repository that has a `just ci` recipe.
-
cypher0n3 Bundle Merge PrepPrepare for merge by cleaning up and consolidating commits. Invoke only when explicitly called by user.
-
cypher0n3 Bundle Make CommitReview staged changes and make a git commit. Invoke whenever the user requests making a commit, unless they have specified make-meta-commit instead.
-
cypher0n3 Bundle Spec AuthoringApplies repository-specific technical-specification standards to design and specification documents. Use this skill when drafting, editing, or reorganizing a technical specification.
-
cypher0n3 Bundle Strip AI TellsRewrites AI-sounding prose until it reads as human-written. Use this skill when a draft reads like AI wrote it: em dashes, negative parallelism, empty intensifiers, and filler triads.
-
cypher0n3 Bundle Make Meta CommitReview staged changes in this repo and its submodules and make git commits. Invoke only when explicitly called by user.
-
cypher0n3 Bundle Senior DeveloperEnforces senior developer coding standards: simple readable code, spec compliance, testability, and strict coverage. Use this skill when writing, fixing, refactoring, or testing code in any language.
-
cypher0n3 Bundle Tech Specs UpdateUpdate the related tech specs and requirements as part of planned work. Invoke only when explicitly called by user.
-
cypher0n3 Bundle Python Test AutomationGuides writing Python functional and end-to-end tests that validate application behavior. Use this skill when writing or refactoring Python test automation.
-
cypher0n3 Bundle Requirements AuthoringApplies repository-specific requirements standards to requirement documents. Use this skill when creating, editing, or reorganizing requirements.
-
cypher0n3 Bundle Senior Go Dev ReviewerPerforms adversarial Go code review against specs, best practices, and production readiness. Use this skill when reviewing a Go change, pull request, or branch.
-
cypher0n3 Bundle Feature Files AuthoringApplies repository-specific Gherkin and BDD conventions to feature files. Use this skill when creating or editing `.feature` files.
-
cypher0n3 Bundle Promote Specs LosslesslyPreserves every material detail when promoting drafts, design notes, or plans into canonical requirements and specifications. Use this skill when integrating draft material into canonical documents.
-
dikamilo Skill Dx NewStart a new piece of work — creates a change or an effort and points you at the next step.
-
dikamilo Skill Dx TddExecute the next pending phase of a change's plan test-first — red, green, refactor — and commit.
-
dikamilo Bundle Dx InitScaffold the dx- SDLC state tree (context/) in this project and seed the baseline standards.
-
dikamilo Skill Dx PlanInterview and write plan.md for a change — matches standards, surfaces priors, owns Progress.
-
dikamilo Skill Dx FrameInterview to settle the problem framing, alternatives, and user cases for a change or effort before planning — writes frame.md. Run again on one of an effort's slices to add that slice's own user cases.
-
dikamilo Skill Dx LessonRecord one finding — a warning or a decision-with-rationale — as an append-only entry in foundation/lessons.md.
-
tiangong-lca Bundle Lca Publish ExecutorPublish local LCA artifact bundles through the unified `tiangong-lca publish run` contract. Use when another skill already produced local publish artifacts and needs one stable publish request instead of per-skill glue.
-
tiangong-lca Bundle Flow Governance ReviewRun the CLI-backed flow governance commands for QA, remediation, deterministic process-flow repair, and publish preparation. Use `node scripts/run-flow-governance-review.mjs COMMAND ...` when you need the supported `tiangong-lca qa flow` and `tiangong-lca flow ...` workflows from a skill wrapper.
-
tiangong-lca Bundle Tidas Contract ContextFetch source-bound TIDAS schema, methodology YAML, CLI-owned runtime ruleset projection, and AI context-pack artifacts through the tiangong-lca CLI. Use before AI authoring or repairing TIDAS process, flow, source, contact, unitgroup, flowproperty, lifecyclemodel, or lciamethod data.
-
tiangong-lca Bundle Tiangong Lca Remote OpsWrap TianGong CLI process maintenance commands for authenticated remote process refreshes and local post-write verification. Use when tasks need current-user process reference refreshes, resumable process maintenance artifacts, or strict local verification of fetched process rows.
-
tiangong-lca Bundle Process Scope StatisticsDelegate to the TianGong CLI to snapshot visible or owner-filtered process rows and compute repeatable coverage statistics for domains, crafts/routes, unit-process rows, and products. Use when you need stable process-scope metrics, especially for `state_code=0/100` maintenance planning.
-
tiangong-lca Bundle Lifecycleinventory ReviewQA process-level or lifecyclemodel-level lifecycle inventory outputs from local TianGong build runs, plus frozen remote TianGong process snapshots. Use when auditing process_from_flow batches, remote process rows fetched through the canonical snapshot wrapper, or lifecyclemodel build artifacts through the unified CLI with reproducible QA inputs and outputs.
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include social-media-content-strategist, discuss, playwright-cli. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.