Claude skills and agent skills

ryanportfolioSkill

writing

ryanportfolio/Harness-Firmware/.agents/skills/writing/SKILL.md

Write or edit audience-facing prose: docs, UI copy, emails, release notes, and application answers. Use also for voice matching, clarity review, or AI-tell cleanup. Ordinary session replies follow session conventions.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

adopt-repo

ryanportfolio/Harness-Firmware/.claude/skills/adopt-repo/SKILL.md

Mirror an existing external repo privately under the user's account and overlay the firmware: clone upstream, strip template-only files, privacy-sweep, run init-project. Use on /adopt-repo <url> or 'pull this repo into our firmware'.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

advocate

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

Use only when the user explicitly invokes /advocate to challenge a change just made before it lands. Do not trigger from natural-language requests.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

apply-firmware

ryanportfolio/Harness-Firmware/.claude/skills/apply-firmware/SKILL.md

Use on /apply-firmware or to bring the current folder (a plain folder, an existing repo, or an older or partial firmware copy) up to full Harness Firmware in place. To mirror an external repo instead, use adopt-repo.

ryanportfolioSkill

astra-fullreview

ryanportfolio/Harness-Firmware/.claude/skills/astra-fullreview/SKILL.md

Full multi-agent Codex review on gpt-6-astra at medium reasoning. Same verified lifecycle as codex-fullreview. Use for /astra-fullreview or 'full Astra review with sub-reviewers'.

ryanportfolioSkill

astra-review

ryanportfolio/Harness-Firmware/.claude/skills/astra-review/SKILL.md

Cross-vendor review configured for gpt-6-astra at medium reasoning. Same verified CLI lifecycle as codex-review. Use for /astra-review or 'have Astra review this'.

Often used withaddskill·dare·advocate

ryanportfolioSkill

brainstorming

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

Use when brainstorming or designing a product, interface, workflow, architecture, or behavior change with unresolved goals or material tradeoffs; not for routine or fully specified work.

Often used withchinese-code-review·addskill·chinese-commit-conventions

ryanportfolioSkill

bro

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

Plain-language restatement. Use on /bro anywhere in a message, \"plain english\", \"plain language\", \"dumb it down\", \"I don't understand\", or \"what does that mean\".

Often used within-your-own-words·poteto-help·make-bot-ui

ryanportfolioSkill

codex-fullreview

ryanportfolio/Harness-Firmware/.claude/skills/codex-fullreview/SKILL.md

Full multi-agent Codex review: codex exec runs $impartial-review as Manager with fresh-context sub-reviewers (gpt-6.1-sol, high), then each finding is verified. Trigger: /codex-fullreview, \"full Codex review with sub-reviewers\".

ryanportfolioSkill

codex-image-gen

ryanportfolio/Harness-Firmware/.claude/skills/codex-image-gen/SKILL.md

Image asset needed (icon, sprite, texture, splash, logo, marketing art, illustration) from inside Claude Code → drive Codex image_gen via codex exec. Use: \"generate an image\", \"make an icon\", \"use gpt-image / my Codex sub\", placeholder asset → real art.

ryanportfolioSkill

codex-review

ryanportfolio/Harness-Firmware/.claude/skills/codex-review/SKILL.md

Cross-vendor second-opinion review. Drives OpenAI Codex CLI (codex exec review, gpt-6.1-sol, high reasoning) over a PR, branch, commit, or uncommitted diff, then verifies each finding. Trigger: /codex-review, \"have Codex/Sol review this\".

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

coordinate

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

Coordinate with another Claude Code session the user names: read what it did and recommends, critique it, send your own recommendation, let it answer, and once you agree have it proceed to done, pinging the user only when a step needs them. Use on /coordinate <session>, or when the user asks you to coordinate, review or go back and forth with another session.

ryanportfolioSkill

deep-plan

ryanportfolio/Harness-Firmware/.claude/skills/deep-plan/SKILL.md

Use for /deep-plan: interview a loose idea in short rounds of decisions and stop for an explicit go before anything is built.

ryanportfolioSkill

design-prototypes

ryanportfolio/Harness-Firmware/.claude/skills/design-prototypes/SKILL.md

Brief → distinct image concepts (sections, features, interactions, branding) → compare → refine pick, before build. Use: /design-prototypes, prototype visual directions, compare design options, refine chosen concept. Built UI → redesign-concepts.

ryanportfolioSkill

fable-mode

ryanportfolio/Harness-Firmware/.claude/skills/fable-mode/SKILL.md

Use for difficult multi-step work, uncertain diagnoses, repeated failures, 'did it work/is it fixed/prove it' questions, or tasks where verification and handoff need particular care. Skip routine changes.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

forge-repo-ui-skill

ryanportfolio/Harness-Firmware/.claude/skills/forge-repo-ui-skill/SKILL.md

Use when the user wants a repository-specific UI or design skill synthesized from current agent skills; not for ordinary UI implementation or backend-only work.

ryanportfolioReads credentialsSkill

impartial-review

ryanportfolio/Harness-Firmware/.claude/skills/impartial-review/SKILL.md

Use when the user asks to review, audit, or stress-test recent code changes with fresh independent agents; requires exposed multi-agent tools or an authenticated Codex CLI.

ryanportfolioSkill

long-horizon

ryanportfolio/Harness-Firmware/.claude/skills/long-horizon/SKILL.md

Use for work too big for one context window: long multi-step tasks, progress lost to compaction or failed retries, work spanning hours or sessions, or when the user says /long-horizon or asks to run a task in verified rounds.

Often used withaddskill·dare·astra-fullreview

ryanportfolioSkill

long-horizon-workflows

ryanportfolio/Harness-Firmware/.claude/skills/long-horizon-workflows/SKILL.md

Long-horizon rounds run through the Workflow tool: one script per batch, with a fresh baseline, candidate executors, a blind pick, and independent judges for every round, schema verdicts and a run journal. Use on /long-horizon-workflows or to run a big task in Workflow-audited rounds. Claude Code only.

ryanportfolioSkill

merge

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

Merge PRs through a Codex review loop: /codex-fullreview, fix, then /codex-review reruns (3 max) until clean, then CI and squash-merge. Runs only when the user types /merge; from then on, every PR in the session goes through the same loop and merges.