All categories
Development
Programming, frameworks, implementation, frontend, backend, and app development
- 70,259
- 2,928
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse development skills
Showing 25–48 of 70,259 skills
- Retention ProbeTests if this session still holds the always-on instruction file. Use when a repo rule seems missing, in a new subagent or after compaction.Votes: 0GitHub stars: 2
- Repair In PlaceFixes a named defect in the lane's own worktree from its findings, with no new plan. Use at REPAIR after verify or validate failed.Votes: 0GitHub stars: 2
- Release ProcessCuts a release with basicly release, pushes it and confirms it published. Use when cutting, tagging or checking a release.Votes: 0GitHub stars: 2
- PythonWrites typed Python with pathlib and Windows-safe subprocesses, and judges if an abstraction earns its keep. Use for .py edits, an except clause, a size gate or a silenced warning.Votes: 0GitHub stars: 2
- Plain EnglishWrites plain prose for readers of any language: READMEs, release notes, design docs, records. Use when writing text for a person.Votes: 0GitHub stars: 2
- NodeRuns Node and npm for the markdownlint hook and other tools. Use when npm or npx fails or resolves the wrong node binary, often on WSL.Votes: 0GitHub stars: 2
- No CommentsEdits code in a repo that bans prose comments: where a fact goes, which directives stay. Use when editing code or when the no-comments gate refuses.Votes: 0GitHub stars: 2
- Interface FactsEstablishes a third-party CLI flag, API field, model, price or limit from the tool and live vendor docs. Use before code depends on it.Votes: 0GitHub stars: 2
- Harness LoopDrives tracked work through the basicly loop, intake to ship. Use to start or resume work, or to move an issue past a checkpoint or gate.Votes: 0GitHub stars: 2
- Harness ClientAttaches to a running supervisor: shows what the factory does and records answers to its decisions. Use while a supervisor runs or a lane waits on a human judgment.Votes: 0GitHub stars: 2
- Find SkillsSearches the catalog, then skills.sh, for an existing community skill out there, and installs one only after the user agrees. Use when asking: is there a skill for this?Votes: 0GitHub stars: 2
- Falsify FirstTries to break a claim, invariant or measurement with a concrete counterexample. Use before it enters a plan, a design or a gate, or before a high-risk number, root cause or coverage claim enters a report.Votes: 0GitHub stars: 2
- Decompose PlanCuts work into children the plan gate accepts: EARS criteria, scope globs, dependencies, a demo command. Use at DECOMPOSE or when a plan gate refuses a child.Votes: 0GitHub stars: 2
- Conventional CommitsWrites a commit subject that passes the hooks: type, scope, breaking-change marker, record id. Use for a commit message or after a hook refused one.Votes: 0GitHub stars: 2
- Cli ToolsPicks the fast tool for a shell task: rg to find each file that mentions a word, fd to list files, jq or yq for a JSON or YAML field, curl for an HTTP endpoint.Votes: 0GitHub stars: 2
- Catalog AuthoringAuthors catalog sources (skills, fragments, styles) in YAML and projects them. Use when adding a new skill or fragment to the catalog, or before editing a generated file.Votes: 0GitHub stars: 2
- Best Practices AuditAudits skills, instructions, hooks, agents and permissions against the newest vendor docs. Use after a Claude Code or Codex release.Votes: 0GitHub stars: 2
- Ai VerifyVerify a Laravel change before calling it done, and orient in an unfamiliar Laravel codebase. Use after editing PHP, Blade, routes, config or migrations; when asked to "check", "verify" or "make sure it works"; before committing; or before changing code you have not read (what calls it, which tests cover it).Votes: 0GitHub stars: 3
- LlmgraphUse when about to change a function's signature or behaviour, or to rename or remove a function, method or class (not on every edit), and whenever an LLMGRAPH answer says maybe_more or cannot_see. Explains which of the five LLMGRAPH questions to ask and how to read the labels, reasons and assumptions.Votes: 0GitHub stars: 2
- RemoveRemove jit-speckit from the current project only (the plugin stays in Claude Code): unregisters the spec-kit extension and preset, deletes the files it created, undoes its git hook setup and strips its block from the constitution. Specs and user edits stay. Use for /jit-speckit:remove or when the user wants a clean reinstall.Votes: 0GitHub stars: 2
- NextShow a spec-kit feature's progress (a task is done when its issue is closed) and start the next open task with /speckit-implement; with several features, asks which. Use when the user asks what's next or has just merged a task PR.Votes: 0GitHub stars: 2
- NewStart a new project with jit-speckit: talk through the stack, architecture and infrastructure with the user, catch missing or risky choices (tests, logging, errors, secrets, backups, over-engineering), then set up the project's tooling for any stack (current versions, linters, tests, lockfile, CI, containers) from primary sources, with no application code, prove it runs green, set up jit-speckit, and suggest a foundation spec. Use for /jit-speckit:new or when the user wants to start a project.Votes: 0GitHub stars: 2
- LevelChange a jit-speckit project's complexity level (lite, standard, full): updates the branch flow, the constitution defaults block, the CI and security scaffolding and the git hooks.Votes: 0GitHub stars: 2
- InitSet up the current project (new or existing) with spec-kit and jit-speckit: one task = one issue = one branch = one PR, security checks on every commit, push and PR, and best-practice defaults sized by complexity level (lite, standard, full).Votes: 0GitHub stars: 2