optimus-prime

Name: optimus-prime
Author: avibebuilder

109stars17forks

How to install optimus-prime?

avibebuilder/claude-prime/optimus-prime

$npx -y skills add avibebuilder/claude-prime --skill optimus-prime

Installs into the current project.

Summary

Generates a Claude Code configuration tailored to a specific project. Use whenever the user wants to prime a project, set up claude for a repo, bootstrap claude config, or re-prime/refresh an already-primed project (for example after /prime-sync pulled new starter content). Tri

Files · 1

View on GitHub

SKILL.md

1	Ultrathink.
2
3	## Mission
4
5	Generate a Claude configuration that fits the specific project. Every skill, rule, and CLAUDE.md entry must exist because this project needs it — not because a template included it. Analyze the real codebase deeply, understand its conventions and patterns, and build a config that makes Claude work well here.
6
7	## Modes
8
9	- Fresh prime — no claude config yet. Build from scratch.
10	- Re-prime — claude config already exists. Preserve intentional project work, refresh what is stale or generic, fill gaps.
11
12	Default to re-prime whenever meaningful existing config is found. Never overwrite it wholesale without user approval.
13
14	## Flow
15
16	1. Analyze the repo deeply — stack, conventions, boundaries, docs, existing config. See [analysis-checklist.md](./references/analysis-checklist.md).
17	2. Propose findings using the Output Format below. Do not touch meaningful files before approval.
18	3. Create skills via `/skill-creator` — every skill must go through skill-creator to ensure quality and project fit. Starters in `.claude/starter-skills/` are reference input to accelerate creation, not templates to copy.
19	4. Generate or refine CLAUDE.md — lean, high-signal, always-on context only. Point to docs/READMEs for detail.
20	5. Rules only if needed — apply the rule test. Zero rules is valid.
21	6. Offer CLAUDE.local.md — personal preferences (role, sandbox URLs, preferred test data, workflow quirks), gitignored.
22	7. Clean up — delete `.claude/starter-skills/` after processing. Keep protected skills. Confirm all deletions.
23	8. Verify — references resolve, stack claims match evidence, config is project-specific not generic.
24	9. Offer skill optimization — after everything is set up, offer optimization paths sized to how many new skills were created. ≤3 skills: recommend full optimization for all. >3 skills: recommend full optimization for user-designated core skills only + description optimization for the rest (avoids long execution time and token burn). Always emphasize that full optimization takes meaningful time and tokens. Run sequentially — never in parallel; concurrent runs overload the user's machine.
25
26	Follow full step-by-step in [setup-project.md](./references/setup-project.md).
27
28	## Placement Decision Matrix
29
30	Every piece of knowledge must earn its place. Use this to decide where it belongs:
31
32	\| Detected need \| Where it belongs \| Test \|
33	\|---\|---\|---\|
34	\| General framework/library knowledge \| Skill (via `/skill-creator`) \| Would a reusable skill teach this across projects? \|
35	\| Project-specific constraint that still produces wrong code with the right skill loaded \| `.claude/rules/<name>.md` with `paths:` \| With the relevant skill activated, will code still be wrong without this? \|
36	\| Identity, commands, stack, key architecture, reference pointers \| `CLAUDE.md` \| Should this be always-on for most tasks in this repo? \|
37	\| Detailed architecture or domain explanations \| Existing `docs/`, READMEs — referenced from CLAUDE.md \| Valuable but too detailed for always-on? \|
38	\| Dense agent-oriented reference material - referenced from CLAUDE.md \| `.claude/project/` (optional) \| Do agents need a tighter reference than the human docs provide? \|
39
40	## Principles
41
42	- Domain-scoped, project-fitted. Skills target a capability, not the project itself — with this project's patterns baked in. Generic templates and project-named catch-alls both degrade context quality.
43	- Repo evidence is the source of truth. Verify conventions from actual source files, configs, and docs. Do not assert what you haven't confirmed.
44	- Lean context, high signal. Follow the context engineering philosophy — load only what's needed, when it's needed. CLAUDE.md carries always-on essentials. Skills load on demand. Rules auto-attach by path.
45	- Rules are optional and path-scoped. Only create a rule when the rule test passes. Do not modify `_apply-all.md` — it is a universal boilerplate rule from prime, not project config.
46	- Reuse over duplication. If the project has strong docs, point to them. Do not re-author parallel agent docs unless existing material is too noisy or incomplete.
47
48	## Output Format
49
50	Before making non-trivial changes, report findings in this shape:
51
52	### Current State
53	W

People who liked this also viewed

6 picks

Type

optimus-prime

109stars17forks

View on GitHub

How to install optimus-prime?

avibebuilder/claude-prime/optimus-prime

$npx -y skills add avibebuilder/claude-prime --skill optimus-prime

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Ultrathink.
2
3	## Mission
4
5	Generate a Claude configuration that fits the specific project. Every skill, rule, and CLAUDE.md entry must exist because this project needs it — not because a template included it. Analyze the real codebase deeply, understand its conventions and patterns, and build a config that makes Claude work well here.
6
7	## Modes
8
9	- Fresh prime — no claude config yet. Build from scratch.
10	- Re-prime — claude config already exists. Preserve intentional project work, refresh what is stale or generic, fill gaps.
11
12	Default to re-prime whenever meaningful existing config is found. Never overwrite it wholesale without user approval.
13
14	## Flow
15
16	1. Analyze the repo deeply — stack, conventions, boundaries, docs, existing config. See [analysis-checklist.md](./references/analysis-checklist.md).
17	2. Propose findings using the Output Format below. Do not touch meaningful files before approval.
18	3. Create skills via `/skill-creator` — every skill must go through skill-creator to ensure quality and project fit. Starters in `.claude/starter-skills/` are reference input to accelerate creation, not templates to copy.
19	4. Generate or refine CLAUDE.md — lean, high-signal, always-on context only. Point to docs/READMEs for detail.
20	5. Rules only if needed — apply the rule test. Zero rules is valid.
21	6. Offer CLAUDE.local.md — personal preferences (role, sandbox URLs, preferred test data, workflow quirks), gitignored.
22	7. Clean up — delete `.claude/starter-skills/` after processing. Keep protected skills. Confirm all deletions.
23	8. Verify — references resolve, stack claims match evidence, config is project-specific not generic.
24	9. Offer skill optimization — after everything is set up, offer optimization paths sized to how many new skills were created. ≤3 skills: recommend full optimization for all. >3 skills: recommend full optimization for user-designated core skills only + description optimization for the rest (avoids long execution time and token burn). Always emphasize that full optimization takes meaningful time and tokens. Run sequentially — never in parallel; concurrent runs overload the user's machine.
25
26	Follow full step-by-step in [setup-project.md](./references/setup-project.md).
27
28	## Placement Decision Matrix
29
30	Every piece of knowledge must earn its place. Use this to decide where it belongs:
31
32	\| Detected need \| Where it belongs \| Test \|
33	\|---\|---\|---\|
34	\| General framework/library knowledge \| Skill (via `/skill-creator`) \| Would a reusable skill teach this across projects? \|
35	\| Project-specific constraint that still produces wrong code with the right skill loaded \| `.claude/rules/<name>.md` with `paths:` \| With the relevant skill activated, will code still be wrong without this? \|
36	\| Identity, commands, stack, key architecture, reference pointers \| `CLAUDE.md` \| Should this be always-on for most tasks in this repo? \|
37	\| Detailed architecture or domain explanations \| Existing `docs/`, READMEs — referenced from CLAUDE.md \| Valuable but too detailed for always-on? \|
38	\| Dense agent-oriented reference material - referenced from CLAUDE.md \| `.claude/project/` (optional) \| Do agents need a tighter reference than the human docs provide? \|
39
40	## Principles
41
42	- Domain-scoped, project-fitted. Skills target a capability, not the project itself — with this project's patterns baked in. Generic templates and project-named catch-alls both degrade context quality.
43	- Repo evidence is the source of truth. Verify conventions from actual source files, configs, and docs. Do not assert what you haven't confirmed.
44	- Lean context, high signal. Follow the context engineering philosophy — load only what's needed, when it's needed. CLAUDE.md carries always-on essentials. Skills load on demand. Rules auto-attach by path.
45	- Rules are optional and path-scoped. Only create a rule when the rule test passes. Do not modify `_apply-all.md` — it is a universal boilerplate rule from prime, not project config.
46	- Reuse over duplication. If the project has strong docs, point to them. Do not re-author parallel agent docs unless existing material is too noisy or incomplete.
47
48	## Output Format
49
50	Before making non-trivial changes, report findings in this shape:
51
52	### Current State
53	W

People who liked this also viewed

6 picks

Type