dimsdealldimsdeall/craftwhale/AGENTS.md

craftwhale

AGENTS.md0 starsChanged 2 months agoMITView on GitHub

Collection 30 Agent Skills + 8 Commands — 6 CORE (Spec → Ship) + 2 OPTIONAL. Contract: /constraints (once, optional) → /spec → prd.md (WHAT/WHY) → /plan → implementation-plan.md (HOW) + tasks/plan.md (ORDER) → /build → code.

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository30 other files it gives its agents.
- api-and-interface-designSkill
- brainstormingSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- constraint-driven-developmentSkill
- context-engineeringSkill
- database-schema-designerSkill
- debugging-and-error-recoverySkill
- deprecation-and-migrationSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- idea-refineSkill
- improve-codebase-architectureSkill
- incremental-implementationSkill
- interview-meSkill
- observability-and-instrumentationSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- using-agent-skillsSkill
- webapp-testingSkill
- write-feature-docsSkill

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Verify (6): debugging-and-error-recovery, browser-testing-with-devtools, webapp-testing (optional — web only, Playwright + with_server.py, …
line 10
Very specific:
After adding/editing a skill → test: npx skills add dimsdeall/craftwhale --list should show (Found 30 skills).
line 23
Very specific:
Don't know what to build / rough idea → brainstorming first, then interview-me / idea-refine
line 27

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

AGENTS.md — craftwhale (dimsdeall)

Collection 30 Agent Skills + 8 Commands — 6 CORE (Spec → Ship) + 2 OPTIONAL. Contract: /constraints (once, optional) → /spec → prd.md (WHAT/WHY) → /plan → implementation-plan.md (HOW) + tasks/plan.md (ORDER) → /build → code.

Inventory (do not delete — source of truth)

Define (5): brainstorming, interview-me, idea-refine, spec-driven-development, constraint-driven-development
Plan (3): planning-and-task-breakdown, context-engineering, using-agent-skills
Build (5): incremental-implementation, test-driven-development, api-and-interface-design, frontend-ui-engineering, source-driven-development
Verify (6): debugging-and-error-recovery, browser-testing-with-devtools, webapp-testing (optional — web only, Playwright + with_server.py, Anthropic), security-and-hardening, performance-optimization, doubt-driven-development
Review (4): code-review-and-quality, code-simplification, documentation-and-adrs, deprecation-and-migration
Ship & Operate (4): git-workflow-and-versioning, ci-cd-and-automation, shipping-and-launch, observability-and-instrumentation
Explain (3, optional — read-only): improve-codebase-architecture (mattpocock/skills), database-schema-designer (softaworks/agent-toolkit), write-feature-docs (warpdotdev/common-skills)
Shared references/: 7 checklists (accessibility, definition-of-done, observability, orchestration, performance, security, testing)
Commands commands/*.toml (8): CORE 6 /spec → brainstorming+idea-refine+interview-me+spec-driven → prd.md (WHAT/WHY, 8-section PRD), /plan → planning+context+api/database → implementation-plan.md (HOW, 5-layer Mermaid + DB ERD + API + frontend) + tasks/plan.md (ORDER, vertical slices), /build → incremental+TDD, /verify → debugging+security/perf/doubt+webapp-testing (web optional — skip if not web), /review → code-review+code-simplification+ADRs, /ship → shipping+CI/CD+observability+git — OPTIONAL 2 /constraints → constraint-driven (interview 4Q → CONSTRAINTS.md), /explain-code → improve-codebase-architecture+database-schema-designer+write-feature-docs (a/b/c, read-only)

Rules for AI agents working on this repo

Each skill = skills/<name>/SKILL.md with valid name + description frontmatter. name must equal folder name (lowercase, hyphen).
brainstorming is the first gate before any other skill — classifies Spike/Bounded/Architectural + hard-gate approval before coding. Do not skip.
Shared checklists in references/ — reference via relative path from the skill.
New skill: duplicate the nearest skill as template → edit frontmatter → push.
After adding/editing a skill → test: npx skills add dimsdeall/craftwhale --list should show (Found 30 skills).

Intent → Skill Mapping (for agents using this repo via `npx skills add dimsdeall/craftwhale`)

Don't know what to build / rough idea → brainstorming first, then interview-me / idea-refine
Want a spec/PRD → spec-driven-development
Have a spec, want to break it into tasks → planning-and-task-breakdown
Need repo context → context-engineering / source-driven-development
Writing code → incremental-implementation + test-driven-development (+ api-and-interface-design / frontend-ui-engineering if relevant)
Web verification (optional — only for webapp/UI) → webapp-testing (Playwright + with_server.py) or browser-testing-with-devtools — skip if not web
Bug / error → debugging-and-error-recovery (+ doubt-driven-development if high stakes)
Review → code-review-and-quality → code-simplification if needed
Commit/PR → git-workflow-and-versioning
CI/CD, release, monitoring → ci-cd-and-automation, shipping-and-launch, observability-and-instrumentation
Want to explain architecture/schema/feature (read-only) → /explain-code → improve-codebase-architecture / database-schema-designer / write-feature-docs
Want a quality bar → /constraints → constraint-driven-development

Provenance

1 skill brainstorming from obra/superpowers (MIT, S-rank)
1 skill improve-codebase-architecture from mattpocock/skills (MIT, 915K)
1 skill database-schema-designer from softaworks/agent-toolkit (MIT)
1 skill write-feature-docs from warpdotdev/common-skills (MIT)
1 skill webapp-testing from anthropics/skills (MIT, Playwright + with_server.py)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free