devskills

In the author's own words, from each skill's SKILL.md — showing the first 30 of 58 files.

• ds-agent-review

  Security review of an AI agent system — tool permissions, prompt-injection exposure, memory isolation, approval gates, agent-to-agent trust, and cost limits. Reviews configuration and code you point it at, including a deployed system's config; static and read-only, it never probes a live target.

  skills/ds-agent-review/SKILL.md on GitHub (opens in a new tab)

• ds-architecture-plan

  Analyze an existing codebase's architecture and produce a sequenced refactoring plan — assess module boundaries, dependency structure, and layering, then lay out ordered, risk-tagged steps. Language-agnostic. Reports a plan; changes nothing.

  skills/ds-architecture-plan/SKILL.md on GitHub (opens in a new tab)

• ds-arena

  Fan one task out to several candidates on different models, cross-judge them against a rubric, pick a base, graft the winners' parts into it, and record the synthesis in ARENA.md. Given a review skill as the task, the candidates are findings lists and the merge is a verified, bucketed union.

  skills/ds-arena/SKILL.md on GitHub (opens in a new tab)

• ds-blast-radius

  Trace what a change could break beyond the diff, name the one fact that makes it safe, prove that fact by running code, and emit the minimal test that would catch the break. `/ds-bug-review` hunts defects inside the diff; this hunts the breakage outside it.

  skills/ds-blast-radius/SKILL.md on GitHub (opens in a new tab)

• ds-blueprint

  Design a target architecture for a new system — module boundaries, dependency rules, seams, and build order — from its requirements. Reports a blueprint; changes nothing.

  skills/ds-blueprint/SKILL.md on GitHub (opens in a new tab)

• ds-bug-review

  Run a strict correctness review of code changes — hunt real bugs, not style or structure. Reports a findings list by default; `--fix` applies the mechanical, unambiguous fixes (logic-changing or uncertain ones stay reported).

  skills/ds-bug-review/SKILL.md on GitHub (opens in a new tab)

• ds-clarity-review

  Review prose for clarity against the Federal Plain Language Guidelines — any text: docs, comment prose, commit text, UI and error strings. Not `/ds-deslop` (code slop) or `/ds-comment-review` (whether a comment earns its place): this judges only whether a reader understands the words. Reports before/after findings; `--fix` applies the rewrites.

  skills/ds-clarity-review/SKILL.md on GitHub (opens in a new tab)

• ds-code-quality-review

  Run an extremely strict maintainability + single-source-of-truth review of code changes — abstraction quality, file sprawl, spaghetti-condition growth, and duplicate/competing implementations. Reports findings by default; `--fix` applies the mechanical, unambiguous ones — structural/code-judo restructurings rest on judgment and stay reported.

  skills/ds-code-quality-review/SKILL.md on GitHub (opens in a new tab)

• ds-comment-review

  Run a strict review of code comments — flag the comments that don't earn their place and tighten the rest to the discipline. Language-agnostic. Reports a findings list by default; `--fix` applies the edits in place.

  skills/ds-comment-review/SKILL.md on GitHub (opens in a new tab)

• ds-data-mode

  Activate data mode for this session.

  skills/ds-data-mode/SKILL.md on GitHub (opens in a new tab)

• ds-data-review

  Run a strict data review of code changes — find data-correctness, integrity, and migration-safety defects. Store-agnostic (relational or NoSQL). Reports a findings list by default; `--fix` applies the mechanical, unambiguous fixes (logic-changing or uncertain ones stay reported).

  skills/ds-data-review/SKILL.md on GitHub (opens in a new tab)

• ds-debug

  Find the root cause of a failure with the scientific method — reproduce, isolate, fix, then prove it.

  skills/ds-debug/SKILL.md on GitHub (opens in a new tab)

• ds-deslop

  Remove AI-generated code slop introduced on the current branch and align it with the surrounding codebase.

  skills/ds-deslop/SKILL.md on GitHub (opens in a new tab)

• ds-doc-quality-review

  Run a strict review of documentation quality — accuracy against the code, broken links and stale counts, coverage gaps, and bloat. Reports a findings list by default; `--fix` applies the mechanical, unambiguous fixes.

  skills/ds-doc-quality-review/SKILL.md on GitHub (opens in a new tab)

• ds-explore

  Suggest candidate approaches to a problem — research and lay out options, but never decide.

  skills/ds-explore/SKILL.md on GitHub (opens in a new tab)

• ds-git-mode

  Activate git mode for this session.

  skills/ds-git-mode/SKILL.md on GitHub (opens in a new tab)

• ds-go-review

  Review Go code with Tiger Style constraints and Go idioms.

  skills/ds-go-review/SKILL.md on GitHub (opens in a new tab)

• ds-grill-me

  Interview the user relentlessly about a plan or design until reaching shared understanding.

  skills/ds-grill-me/SKILL.md on GitHub (opens in a new tab)

• ds-handoff

  Compact the current conversation into a handoff document so a fresh agent can continue the work.

  skills/ds-handoff/SKILL.md on GitHub (opens in a new tab)

• ds-how

  Explain how a subsystem works as a mental model — overview, key concepts, the runtime flow, where things live, gotchas. `/ds-zoom-out` places an area among its neighbours before a change; this walks the machinery inside it.

  skills/ds-how/SKILL.md on GitHub (opens in a new tab)

• ds-humanize

  Remove the AI tells from prose — the patterns that read as machine-written. Not `/ds-deslop` (code slop) or `/ds-comment-review` (whether a comment earns its place), and not `/ds-clarity-review` (whether a reader understands) or `/ds-doc-quality-review` (the document as artifact — bloat, redundancy, structure): this judges only whether the text sounds machine-written.

  skills/ds-humanize/SKILL.md on GitHub (opens in a new tab)

• ds-interaction-mode

  Activate interaction mode for this session.

  skills/ds-interaction-mode/SKILL.md on GitHub (opens in a new tab)

• ds-java-review

  Review Java code with Tiger Style constraints and Java idioms.

  skills/ds-java-review/SKILL.md on GitHub (opens in a new tab)

• ds-notebook-review

  Run a strict review of Jupyter notebooks — find notebook-state, output-hygiene, reproducibility, and data-science correctness defects a line-by-line code review can't see. Reports a findings list by default; `--fix` applies the mechanical, unambiguous fixes (logic-changing or uncertain ones stay reported).

  skills/ds-notebook-review/SKILL.md on GitHub (opens in a new tab)

• ds-onboarding

  Onboard a new team member to a project: team context, ownership, rituals, and the first safe contribution path — not a generic code tour.

  skills/ds-onboarding/SKILL.md on GitHub (opens in a new tab)

• ds-osv

  Scan project dependencies for known vulnerabilities using OSV Scanner.

  skills/ds-osv/SKILL.md on GitHub (opens in a new tab)

• ds-perf-plan

  Analyze code for optimization opportunities and produce a graded performance plan — a ranked set of moves, each tagged by the architectural cost it incurs (L1/L2/L3). Language-agnostic. Reports a plan; changes nothing.

  skills/ds-perf-plan/SKILL.md on GitHub (opens in a new tab)

• ds-project-checkpoint

  Write the session's durable state to .project/state.md so the next session can pick it up.

  skills/ds-project-checkpoint/SKILL.md on GitHub (opens in a new tab)

• ds-project-map

  Map the current repository into `.project/map.md`.

  skills/ds-project-map/SKILL.md on GitHub (opens in a new tab)

• ds-project-resume

  Read .project/ state and report where to pick up.

  skills/ds-project-resume/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 412k stars · 5 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 293k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 227k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 181k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 143k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 139k stars · 1 skill