Skill reviews

Expert guidance for developing with the tinystruct Java framework. Use when working on the tinystruct codebase or any project built on tinystruct — including generating the bin/dis

• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (7 tags): a typed call is more reliable

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platfor

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• 4 mutating operations with no state check

Create reproducible, cross-platform (macOS/Linux) development environments with Flox, a declarative Nix-based environment manager. Use when setting up project toolchains, installin

• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. Covers machine-decidable goals,

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start

Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification thro

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Produce low-fidelity black-and-white UI wireframes as SVGs or viewer pages. Use when asked to wireframe, sketch a screen, draft a layout, make a low-fi mockup, or publish wireframe

• References files that are not bundled: assets/template.svg, assets/template-mobile.svg
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill

For product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-cas

• References files that are not bundled: examples/example-{helix,holm,atlas,bluehouse}.html
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (5 tags): a typed call is more reliable

Prepare required media inputs within an existing OD Next plan. Reuse capability evidence, acquire and measure assets efficiently, and resolve asynchronous jobs without removing req

• References files that are not bundled: assets/stock/, assets/stock/credits.json
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: assets/stock/, assets/stock/credits.json

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• Linear process with no failure handling

Turn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when t

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (6 tags): a typed call is more reliable
• Does not say what the result is

Decide whether work needs a feature flag (any change to product behavior users can see does), then declare it, roll it out (per organization, for everyone, cloud or self-hosted), r

• References files that are not bundled: scripts/features-sync.mjs
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Live developer experience audit. (gstack)

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 34 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 24 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Restrict file edits to a specific directory for the session. (gstack)

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

OpenAI Codex CLI wrapper — three modes. (gstack)

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 21 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Use when creating, changing, or validating an agent preset or other Cordis composition for this harness, including deciding host versus preset placement and checking that an author

• The skill tells the model to perform an irreversible action with no human approval
• Prose only: no discrete steps
• Does not say what the result is

Use when a deepseek-harness change breaks an externally perceptible surface (CLI, profiles, cordis.yml or settings keys, persisted user data, SDK or wire APIs, published package en

• References files that are not bundled: ../../../docs/cookbook/reviewing-persistence-type-changes.md, ../dsh-doc/templates/upgrade-guide.md, ../../notes/README.md
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts;

• References files that are not bundled: ../dsh-prose-standard/SKILL.md, ../../notes/archived/process/2026-08-09-committed-artifact-citations.md, ../../../docs/AGENTS.md
• The skill tells the model to perform an irreversible action with no human approval
• 5 referenced file(s) missing: ../dsh-prose-standard/SKILL.md, ../../notes/archived/process/2026-08-09-committed-artifact-citations.md, ../../../docs/AGENTS.md

Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches,

• References files that are not bundled: ../dsh-ci-test-reliability/SKILL.md, ../../../packages/test-support/remote-mock/README.md
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable

Record browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and determinis

• References files that are not bundled: ../../notes/archived/process/2026-08-08-browser-gif-evidence-chain.md, <path/to/demo.gif>
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Sync delta specs from an OpenSpec change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change. Also use when the

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (7 tags): a typed call is more reliable

Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what pe

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (19 tags): a typed call is more reliable

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (42 tags): a typed call is more reliable