All authors
Claude Skills by everywan-dev
github.com/everywan-dev53 skills0 installs79 views
- Block Dangerous Git CommandsSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.Votes: 0GitHub stars: 2
- Break Work Into TicketsBreak a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).Votes: 0GitHub stars: 2
- Build A Domain ModelBuild and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.Votes: 0GitHub stars: 2
- Build A Throwaway PrototypeBuild a throwaway build-a-throwaway-prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.Votes: 0GitHub stars: 2
- Check If Data Is Safe To DeleteUse when deciding whether a table, a file, or a service can be deleted because it looks unused. Measure real access, rename before deleting, and check the units of every counter.Votes: 0GitHub stars: 2
- Check The Licence Before You CopyUse before pulling someone else's code, skills, prompts or configuration into your project, and before publishing anything that contains them. Turns "it was on GitHub" into an obligation you can actually meet.Votes: 0GitHub stars: 2
- Choose The Right Code ReviewUse when deciding how much review a change needs, and of what kind. What the change touches decides the level — not how big it looks, not how confident you feel.Votes: 0GitHub stars: 2
- Debug A Silent FailureUse when something did not happen and nothing complained — no error, no alert, an empty log, a change with no effect. Teaches how to read absence as a symptom and where silence gets manufactured.Votes: 0GitHub stars: 2
- Deploy To Production SafelyUse when a change is about to touch a running system. Backup, dry run, rollback and per-node verification, in that order.Votes: 0GitHub stars: 2
- Design Deep ModulesShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.Votes: 0GitHub stars: 2
- Detect Stale DocumentationUse when checking whether curated knowledge is still fresh, reading freshness verdicts, or investigating why a unit shows drifted or unknown. Triggers on requests like "check freshness", "run the probes", "is this knowledge still current", "why does kb-0002 say unknown", or "read the knowledge index".Votes: 0GitHub stars: 2
- Diagnose A Hard BugDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.Votes: 0GitHub stars: 2
- Document With EvidenceUse when recording a new piece of curated knowledge -- a finding, a decision, a measured fact worth keeping and later re-checking for freshness. Triggers on requests like "record this as knowledge", "write a knowledge unit for X", "capture this finding with evidence", or "add this to curated knowledge". Do not use for a quick personal or project preference; that belongs to the keep-agent-memory-accurate skill instead.Votes: 0GitHub stars: 2
- Edit A Live Config SafelyUse when editing a configuration file a running process is reading. Unique anchor, keep the inode, validate before applying, verify every node.Votes: 0GitHub stars: 2
- Find Architecture ImprovementsScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.Votes: 0GitHub stars: 2
- Generate A Setup WizardGenerate an interactive bash generate-a-setup-wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.Votes: 0GitHub stars: 2
- Get A Second Model OpinionUse when a claim needs a second opinion that does not share your blind spots. How to ask a different model, what to send it, and how to settle a disagreement.Votes: 0GitHub stars: 2
- Implement From A SpecImplement a piece of work based on a spec or set of tickets.Votes: 0GitHub stars: 2
- Investigate An Unfamiliar SystemUse when entering a system you did not build. The reading order that gets you oriented without breaking anything, and the false negatives that will fool you on the way.Votes: 0GitHub stars: 2
- Keep Agent Memory AccurateUse when recording or updating a persistent agent-memory fact -- a user preference, a project fact, feedback, or a reference note the harness should remember across sessions. Triggers on requests like "remember that I prefer X", "note this project fact", "update this memory", or "this preference changed". Do not use for curated knowledge with evidence and freshness tracking; that belongs to document-with-evidence.Votes: 0GitHub stars: 2
- Keep Secrets Out Of The RepositoryUse before committing configuration, when a secret has already been committed, or when adding a secret scanner. Covers why rotation beats scrubbing and why most scanners get switched off.Votes: 0GitHub stars: 2
- Know What A Change CostsUse before shipping something that runs repeatedly — a job, a query, an agent loop, a pipeline. Estimates the recurring cost of a change while it is still cheap to change, and decides where spending less is safe.Votes: 0GitHub stars: 2
- Look At The Rendered PageUse before claiming a web change works. Reading HTML and CSS is not seeing the page — render it, in every theme, and look.Votes: 0GitHub stars: 2
- Make The Next Failure LoudUse after an incident, or before shipping something whose failure would be invisible. Decides what to log, measure and alert on so the next failure announces itself instead of being discovered by a customer.Votes: 0GitHub stars: 2
- Map An Undocumented SystemUse when documenting a system or auditing what is already documented. Records the edge of what is known, so that silence stops reading as "nothing there".Votes: 0GitHub stars: 2
- Map The Attack SurfaceUse before exposing something, after inheriting a system you did not build, or when a security review says "looks fine". Finds who can reach what, the authorisation gaps scanners never report, and what not to put in the findings list.Votes: 0GitHub stars: 2
- Pick The Right SkillUse when you do not know which skill fits the situation you are in. A router over every skill in this collection, grouped by what you are actually about to do.Votes: 0GitHub stars: 2
- Plan Work Too Big For One SessionPlan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.Votes: 0GitHub stars: 2
- Research With Primary SourcesInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.Votes: 0GitHub stars: 2
- Resolve Merge ConflictsUse when you need to resolve an in-progress git merge/rebase conflict.Votes: 0GitHub stars: 2
- Review A Plan Before You BuildUse when a plan is written and about to be built. Reviews it from four deliberately different angles, because the objection that kills a plan is rarely the one its author was watching for.Votes: 0GitHub stars: 2
- Review Changes Against Spec And StandardsReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".Votes: 0GitHub stars: 2
- Review Code You Did Not WriteUse when you are about to approve, merge or ship code an agent or another person wrote and you do not fully understand. Turns "it looks right and the tests pass" into a review that could have rejected it.Votes: 0GitHub stars: 2
- Root Cause Analysis FirstUse when something is failing and you are about to change code or config to fix it. Blocks the fix until you can say why it happens, and shows how to hunt a cause instead of confirming a guess.Votes: 0GitHub stars: 2
- Route Work To The Right ModelUse before starting any change, to decide how much validation it needs and which model and effort to spend on it. Answers "is this a one-review change or a three-review change?" without arguing about it.Votes: 0GitHub stars: 2
- Set Up Pre Commit HooksSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.Votes: 0GitHub stars: 2
- Set Up The Issue TrackerConfigure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.Votes: 0GitHub stars: 2
- Set Up Verified DocumentationUse when a project wants to adopt the validated-memory method -- bootstrapping curated knowledge and agent memory for the first time, wiring the harness's persistent memory to this project, or verifying an adoption is set up correctly. Triggers on requests like "adopt validated-memory here", "set up curated knowledge for this project", "bootstrap the memory layer", or "wire the harness memory symlink".Votes: 0GitHub stars: 2
- Stress Test A DecisionGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.Votes: 0GitHub stars: 2
- Stress Test A Plan With DocsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.Votes: 0GitHub stars: 2
- Supersede Outdated DocsUse when a curated-knowledge unit turns out to be wrong, outdated, or replaced by better evidence. Triggers on requests like "correct kb-0003", "update this finding, it changed", "this knowledge unit is no longer true", or "supersede X with Y". Never use this to justify editing a unit's frontmatter or body in place.Votes: 0GitHub stars: 2
- Survive Someone Elses Breaking ChangeUse when something that worked yesterday stopped working and you changed nothing, or before upgrading a dependency, runtime or platform. Also covers not doing this to your own consumers.Votes: 0GitHub stars: 2
- TddTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.Votes: 0GitHub stars: 2
- Teach A ConceptTeach the user a new skill or concept, within this workspace.Votes: 0GitHub stars: 2
- Triage Issues And PrsMove issues and external PRs through a state machine of triage-issues-and-prs roles, categorise, verify, grill if needed, and write agent-ready briefs.Votes: 0GitHub stars: 2
- Turn A Decision Into A QuestionnaireTurn a decision you can't fully answer into a questionnaire for someone else to fill in.Votes: 0GitHub stars: 2
- Validate Your ValidatorUse when writing or trusting anything that decides pass/fail — a test, a linter, a scanner, a health check, a monitor. Makes the checker prove it can fail before you believe a green result.Votes: 0GitHub stars: 2
- Verify Before Saying DoneUse when about to report something as done, working or fixed. Turns "it looks right" into a check that could have failed.Votes: 0GitHub stars: 2
- Write A Handover That WorksUse when work has to survive a break in continuity — end of a session, end of a day, passing a task to someone else. Writes the handoff that carries the evidence and names what was never checked.Votes: 0GitHub stars: 2
- Write A Spec From A ConversationTurn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.Votes: 0GitHub stars: 2