Claude skills and agent skills

ryanportfolioSkill

optimize-context

ryanportfolio/Harness-Firmware/.claude/skills/optimize-context/SKILL.md

Use when the user asks to reduce per-turn context or token load, trim kernels, skills, or connectors, or propagate a generic context optimization to the starter.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

perf-loop

ryanportfolio/Harness-Firmware/.claude/skills/perf-loop/SKILL.md

Run measured optimization rounds with independent review for FPS, loading, latency, throughput, and resource use; with no named target, triage every dimension first. Use for /perf-loop or broad performance requests; skip isolated fixes.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

redesign-concepts

ryanportfolio/Harness-Firmware/.claude/skills/redesign-concepts/SKILL.md

Built UI → screenshots → Codex image_gen → 10 redesign concepts → owner picks → build plan. Use: /redesign-concepts, \"show what we have to Codex, get 10 better versions\", \"prototype improvements to current UI\". Brief only, nothing built → design-prototypes.

ryanportfolioSkill

refine

ryanportfolio/Harness-Firmware/.claude/skills/refine/SKILL.md

Use for an explicit workflow-improvement review, turning the user's preferences into rules or a skill, recurring task friction that may justify a narrow change to skills or project references, or the unattended weekly review (/refine weekly).

Often used withaddskill·daily-arxiv·astra-fullreview

ryanportfolioSkill

servers

ryanportfolio/Harness-Firmware/.claude/skills/servers/SKILL.md

Use on /servers, after starting a dev server, or when the user asks what is running, which port is which, why browsers are open, or to close old servers and browsers.

ryanportfolioSkill

showpiece

ryanportfolio/Harness-Firmware/.claude/skills/showpiece/SKILL.md

Push an artifact past what people expect from its kind, in any medium. Use for /showpiece, ambitious creative direction, portfolio-quality work, or replacing generic AI styling. Not for quiet or faithful work such as forms, dashboards, exact recreations or brand matching; use frontend-design or the project's UI skill. Skip routine edits unless explicitly invoked.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

sync-starter

ryanportfolio/Harness-Firmware/.claude/skills/sync-starter/SKILL.md

Use when the user asks to pull template improvements into a spawned repo, compare starter drift, or push a generic improvement back to the starter.

ryanportfolioSkill

why

ryanportfolio/Harness-Firmware/.claude/skills/why/SKILL.md

Pressure-test a recommendation with one fresh reviewer. Use when the user types /why, or before you present your own weighty recommendation (hard to undo, two or more real options, or real time or money at stake). Never trigger from ordinary why questions or paraphrases.

Often used withpoteto-help·principle-explain-the-number·make-bot-ui

ryanportfolioSkill

wow-loop

ryanportfolio/Harness-Firmware/.claude/skills/wow-loop/SKILL.md

Evidence-gated review and repair loop for one deliverable or a set of like items. Use on /wow-loop, requests for wow factor or dial it to 11, a target score to reach (\"get it to 8/10\", \"bring everything under 6 up to 6+\"), or substantial visual work (3D, animation, UI, rendered documents) that needs reference fidelity or repeated visual correction. Skip routine cosmetic edits and discussion of the skill itself.

ryanportfolioSkill

wrapup

ryanportfolio/Harness-Firmware/.claude/skills/wrapup/SKILL.md

Use on /wrapup or when the user asks if a session is done, good to archive, or what is left: one verdict from git, the PR, scratch files and running servers or browsers.

ryanportfolioSkill

addskill

ryanportfolio/savetokens/.agents/skills/addskill/SKILL.md

Create, import, update, or install repository or personal skills; includes runtime ownership, resources, and discovery validation.

ryanportfolioSkill

caveman

ryanportfolio/savetokens/.agents/skills/caveman/SKILL.md

Use for every session reply to the user: concise Caveman prose with built-in Unslop. User-facing deliverables use Writing instead.

Often used withcaveman-explore·investigate-first·cavecrew

ryanportfolioReads credentialsSkill

opus-fullreview

ryanportfolio/savetokens/.agents/skills/opus-fullreview/SKILL.md

Full multi-reviewer Claude review from Codex: Claude CLI runs impartial-review as Manager with fresh Opus sub-reviewers, then Codex verifies each finding. Use for $opus-fullreview or a full Claude/Opus review with sub-reviewers.

ryanportfolioSkill

automate-me

ryanportfolio/savetokens/.claude/skills/automate-me/SKILL.md

Use for \"automate me\", \"/automate-me\", \"create/update my -mode skill\", or \"turn my preferences into a skill\". Mines the current project's transcripts plus direct questions, then drafts a personal <handle>-mode skill.

Often used withpoteto-help·make-bot-ui·poteto-mode

ryanportfolioSkill

perf-loop

ryanportfolio/savetokens/.claude/skills/perf-loop/SKILL.md

Run measured optimization rounds with independent review for FPS, loading, latency, throughput, and resource use; with no named target, triage every dimension first. Use for /perf-loop or broad performance requests; skip isolated fixes.

Often used withdare

ryanportfolioSkill

refine

ryanportfolio/savetokens/.claude/skills/refine/SKILL.md

Use for an explicit workflow-improvement review, turning the user's preferences into rules or a skill, or recurring task friction that may justify a narrow change to skills or project references.

Often used withdaily-arxiv·exp-eval·exp-run

ryanportfolioSkill

showpiece

ryanportfolio/savetokens/.claude/skills/showpiece/SKILL.md

Create distinctive, crafted artifacts in any medium. Use for /showpiece, ambitious creative direction, portfolio-quality work, or substantial cleanup of generic AI styling. Skip routine edits unless explicitly invoked.

Often used withdare

ryanportfolioSkill

verify-this

ryanportfolio/savetokens/.claude/skills/verify-this/SKILL.md

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare, return VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Use for /verify-this, \"prove it works\", \"did this fix it\".

ryanportfolioSkill

why

ryanportfolio/savetokens/.claude/skills/why/SKILL.md

Pressure-test a recommendation with one fresh reviewer. Use when the user types /why, or before you present your own weighty recommendation (hard to undo, two or more real options, or real time or money at stake). Never trigger from ordinary why questions or paraphrases.

Often used withpoteto-help·principle-explain-the-number·make-bot-ui

ryanportfolioSkill

wow-loop

ryanportfolio/savetokens/.claude/skills/wow-loop/SKILL.md

Evidence-gated review and repair loop for one deliverable or a set of like items. Use on /wow-loop, requests for wow factor or dial it to 11, a target score to reach (\"get it to 8/10\", \"bring everything under 6 up to 6+\"), or substantial visual work (3D, animation, UI, rendered documents) that needs reference fidelity or repeated visual correction. Skip routine cosmetic edits and discussion of the skill itself.