Calvin-LLC
- 33 skills
- 0 followers
- 23 hours ago last updated
- ▌ Technical Writing · calvin-llc bundleUse for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, commit messages, or any prose the reader must understand on first read: Diátaxis modes, Google developer style, STE, Global English.
- ▌ Writing For Agents · calvin-llcUse when authoring or pruning the content of a skill, AGENTS.md, SOUL.md, or a brief. Not for installing or syncing skills, nor for prose style edits.
- ▌ Benchmark Checklist · calvin-llcVet a performance measurement (limiter, tuning, limits, errors, repeatability, relevance, whether the work ran) before reporting a speedup or regression. Use when you run a benchmark or report a number you measured.
- ▌ Improve Codebase Architecture · calvin-llc bundleUse when asked to improve a codebase's architecture or find what to refactor. Scans for deepening opportunities, presents them as a visual HTML report, then grills through whichever one you pick.
- ▌ Readme Clean · calvin-llc bundleUse when asked to clean up, optimize, rewrite, or de-slop a README: rewrites it plain and concise, checks every claim against the repo, and proves no technical fact was dropped.
- ▌ Figure It Out · calvin-llcUse for /figure-it-out, 'figure it out', a large migration, an ambitious multi-part change, work a human reviews after stepping away, or when no narrower playbook fits. Designs an auditable bespoke playbook with rigor scaled to the task.
- ▌ Gemini Vision · calvin-llc bundleUse when inspecting or reviewing UI screenshots, mockups, diagrams, or wireframes for layout, hierarchy, readability, or visual bugs. Not for pixel or color analysis of camera or capture images, nor for routine text edits.
- ▌ Writing Plans · calvin-llcWrite an implementation plan from a spec or when the user asked for a plan, before touching code.
- ▌ Diagnosing Bugs · calvin-llcDiagnose a hard bug or performance regression by first building one command that reproduces the exact symptom. Use when something is broken, throwing, failing, flaky or slow and the cause is not obvious. Use how for how code works, why for history.
- ▌ Reference Mining · calvin-llc bundleUse when checking whether a reference project already solves a problem ("do the references do this", prior art, a mechanism hunt) or when improving a target repo from one. Evidence, not a template; not for copying code or reviewing one repo alone.
- ▌ To Questionnaire · calvin-llcTurn a decision you can't resolve alone into a questionnaire someone else fills in. Use when blocked on knowledge another person holds (a lead, a client, a reviewer) and you need it pulled out of them async. Do not use for questions you can answer by running or reading something.
- ▌ Poteto Mode · calvin-llc bundleUse for poteto, /poteto-mode, or requests to work in this style. Playbook-routed tasks, deliberate subagents, verified work, simple code, concise unslopped replies.
- ▌ Blast Radius · calvin-llcFind what a change could break outside the diff and prove the one fact it is safe because of by running real code. Use for 'blast radius of X', 'what could this break', or a small diff you do not trust. Use how for what code does, why for motivation.
- ▌ Repo Retro · calvin-llc bundleReview recent agent sessions in this repo for wasted navigation, failed searches, stale docs and command loops. Ranks findings by cost and logs metrics so the next run shows whether fixes worked. Proposes only; edits nothing until approved.
- ▌ Arch Export · calvin-llc bundleUse when the user wants a sanitized architecture brief, or a prompt to paste into an outside model (Perplexity, ChatGPT, Claude) with no repo access, to review a design, defect, or finished artifact.
- ▌ Arch Import · calvin-llcUse after pasting an outside reviewer's reply to an `arch-export` brief; adjudicates it against the real code, applies cheap safe wins, and ends with a decision ledger and build order.
- ▌ No Comments · calvin-llc bundleUse when asked to strip, audit, or clean up code comments: deletes unproven, narrating, and stale comments from a diff or file set, in the current session.
- ▌ Impeccable · calvin-llc bundleUse when designing, critiquing, or improving a frontend or native UI: pages, dashboards, components, forms, layout, typography, color, motion, UX copy, design systems. Not for backend-only or non-UI tasks.
- ▌ Sharpen · calvin-llcUse for /sharpen, or before starting a task that is vague, over-specified, or open-ended: find the expert approach, what the user is really after, and the right level of specification.
- ▌ Grill Me · calvin-llc bundleUse for grill me, interrogate, which approach, challenge this, stress-test this plan, steer. Asks one non-jargon fork question, grills a plan's hidden decisions, or runs a multi-model design review. Not for rewording or explaining.
- ▌ Architect · calvin-llc bundleUse for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape: sketch types, signatures, and module structure before code, then implement against the agreed sketch.
- ▌ Declauding · calvin-llc bundleLoad at the start of any task whose deliverable is prose another person will read — a PR description, commit message, README, doc, postmortem, blog post, issue or review comment, report, release note or essay — before drafting it, whether the result is pushed, posted, published or saved to a file, without being asked. Draft, then run this pass on the draft before handing it over. Also use when someone says "de-claude", "de-slop", "humanize this", "this reads like AI", "make it sound human", or asks for a voice, tone or register edit. Rewrites the constructions that mark prose as model-written (staged reveals, verdict headers, aphoristic closers, "it's not X, it's Y", em-dash drama, forced triads, flat-certainty adverbs, noun stacks, dropped 'that') into plain technical prose and checks the rewrite kept every claim. Not for fiction, poetry, code, or quoted text; for a full adversarial review of a deliverable use challenging.
- ▌ Deslop · calvin-llcUse for a code hygiene or cleanup audit that measures complexity, nesting, file length, duplicates, dead code, type escapes, and coverage against numeric ceilings; not for subjective style review.
- ▌ Recall · calvin-llc bundleReconstruct your recent working context from agent session history and live git state, then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.
- ▌ Unslop · calvin-llcUse when writing or editing text a person will read (docs, READMEs, replies, commit messages): cuts AI tells (puffery, filler, em dashes, jargon) and adds a human voice.
- ▌ Babysit · calvin-llc bundleUse when asked to babysit a PR or stack, get it green, address review comments, or push to main and watch CI and the deploy until live; drives a PR to merge-ready, a push to confirmed live.
- ▌ Correct · calvin-llc bundleUse when the user is correcting the same agent mistake again, or for /correct: find the mistakes agents repeat in this repo and make each one impossible, by architecture, then types, then a lint, then a test, docs last.
- ▌ Why · calvin-llcUse for why code exists, why we picked Y, regressions, or postmortems. Cite git and gh. Use how for how it works.
- ▌ Init · calvin-llcBuild or refresh a repository's AGENTS.md from what the repo actually does. Use when asked to run /init, initialize a repo for agents, write or update AGENTS.md, onboard an agent into a codebase, or find out how a project is built and tested. Detects the command surfaces, runs each candidate command before writing it down, and never records a fact it did not verify.
- ▌ Wcag · calvin-llc bundleUse when auditing a page for web accessibility (WCAG 2.2 A/AA); runs five real-browser passes and reports violations with selectors and snippets.
- ▌ Commit · calvin-llc bundleUse before making any git commit: one major feature per commit on main, a 1-2 line overview message, never push without explicit user approval.
- ▌ How · calvin-llc bundleUse when asked how a subsystem, feature, or flow works, where it lives, or what owns it, including whether it is implemented yet or what is architecturally wrong with it. For why it exists, use the why skill.
- ▌ Harden · calvin-llc bundleEvidence-driven codebase hardening. Audits security (OWASP Top 10:2025), supply chain (inventory vs SBOM vs SLSA v1.2), reliability (OTel + operational limits), tests (sandboxed tiers), and accessibility (WCAG 2.2 AA). Every finding is quoted, matrix-scored, and cited. Does not fix. Reports with file:line and a verification plan. Use when asked to harden, audit security, run /harden, or review OWASP/WCAG/SLSA posture.