Build project instructions
Writes project-level instructions and a knowledge-file outline for a recurring project in an AI assistant, with a playbook for each repeated task and test prompts.
Many assistants let people group conversations into a project with standing instructions and uploaded reference files. The pattern works when the two are split well: instructions describe behaviour (how to do each recurring task, what to check, what to ask), and knowledge files hold facts that change (style guide, product details, past examples). Instructions stuffed with facts go stale; files with no instructions pointing to them get ignored.
Only if [RECURRING_TASKS] is given:
- List the assumptions you are making. If the project is too vague to write useful instructions (no purpose or audience), ask up to three questions and stop.
- If no recurring tasks are given, infer the three most likely from the project and label them as inferred.
- Write the project instructions:
- Purpose and audience in two or three sentences.
- Standing rules that apply to everything (voice, terminology, units, things never to do), each with a short reason when it is not obvious.
- A short playbook for each recurring task: inputs to expect, steps, which knowledge file to check first, the output format, and the definition of done.
- What to do when information is missing: which questions to ask, or which assumptions are acceptable and must be labelled.
- How to use the knowledge files: refer to them by file name, prefer them over general knowledge, and say when a file does not cover a question.
- Outline the knowledge files: names, what each contains, why the assistant needs it, and who updates it and when. Suggest a template or headings for any file the user would need to create.
- Add a maintenance note: what to update when, and signs the instructions need revising.
- Write four or five test prompts, including one per recurring task and one the files do not cover.
- Keep instructions model-agnostic and under about 800 words; move facts into files.
- Use placeholders such as [BRAND_COLOURS] for facts you do not have. Never invent names, figures or policies.
- Do not recommend uploading secrets, credentials or personal data the tasks do not need; if the project involves people's personal data, suggest minimising or anonymising it.
- Write the instructions in second person, addressed to the assistant.
Assumptions
Project instructions
Fenced code block, ready to paste.
Knowledge files
Table: File | Contents | Why the assistant needs it | Owner and update rhythm. Then any templates as short heading lists.
Maintenance
Test prompts
Table: Prompt | Tests | Good result.
1 required value still a placeholder; the assistant will ask for it.
details
- kind
- Prompt: a task you run by name to get one finished thing back
- domain
- Prompting and assistants
- category
- Assistant setup
- level
- Intermediate
- made for
- Anyone, personal use, People manager, Content creator, Consultant / freelancer
- risk
- read-only
- version
- v1.0.0 · incubating
- reviewed
- 2026-10-02
- works in
- Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Antigravity, OpenCode, Windsurf, Zed, Continue, AGENTS.md, ChatGPT, claude.ai
use in
npx @hermes-hq/hodios install build-project-instructions --target claude-codenpx skills add hermes-hq/hodios-dist --skill build-project-instructions -a claude-codeclaude plugin marketplace add hermes-hq/hodios-distclaude plugin install hodios-prompting@hodiosThe plugin brings every entry in this domain at once.
pairs well with
All of Assistant setupWrite custom instructions
Writes personal custom instructions for an AI assistant from your role, preferences and pet peeves, turning them into specific behaviours, with test prompts to check the difference.
write-custom-instructionsWrite a system prompt
Writes a system prompt for a custom assistant from its purpose, audience, boundaries and tone, with handling for missing information and off-topic requests, plus a set of test questions.
write-system-promptPrompt engineer
Prompt engineer who writes clear, testable instructions, iterates against real examples and evals, and avoids model-specific tricks. Use for designing, debugging and maintaining prompts.
prompt-engineerCandid feedback rules
Standing rules that make an assistant candid - no flattery, real disagreement when warranted, stated confidence, admitted uncertainty, and position changes only for good reasons.
candid-feedback-rulesMap where AI helps in your work
Maps a person's recurring work tasks to where an AI assistant helps, what to keep human, the prompt or setup for each and a check step, ranked by the time it could save.
map-ai-use-casesReview custom instructions
Reviews existing custom or project instructions for an AI assistant, finds conflicts, vague rules, outdated facts and missing context, and returns a tighter version with test prompts.
review-custom-instructions