What does this skill do, and when should you use it?
This skill defines cultural and collaboration norms for contributors and AI agents working on the Engram project. It prioritizes product coherence over local cleverness, discourages generic enterprise UI drift, and promotes explicit decisions and documented rules over tribal knowledge. The skill activates when starting substantial work, reviewing changes, or defining team conventions. It is a pure text guide with no scripts or external dependencies, portable across any Agent Skills client.
The skill provides a set of cultural rules and collaboration rules that guide behavior. It does not run commands; instead, it instructs agents to maintain product coherence, avoid fake UX, enforce organizational rules server-side, and capture repeating patterns as skills or conventions. It applies during feature development, code review, and convention definition.
- An Engram contributor starting a new feature wants to align with the overall product experience.
- A reviewer checks implementation direction against coherence principles.
- A team defining conventions wants to ensure explicit, documented decisions.
- A developer refactoring architecture verifies that behavior, naming, tests, docs, and UX are consistent.
How do you install this skill?
- Skill file license (Apache-2.0) conflicts with repository license (MIT), recommend correction.
- Skill provides no actionable commands, may have limited value for automation agents.
- No maintainer or update path information, long-term maintainability questionable.
This skill is part of the engram repository. Clone or download the repo and place the skills/cultural-norms folder into your agent's skills directory (e.g., ~/.claude/skills for Claude Code). See the repository README for detailed installation instructions.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/Gentleman-Programming/engram.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/cultural-norms" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Review this PR direction according to the cultural-norms skill.
- Apply cultural-norms before starting the new feature.
When starting substantial work, reviewing changes, or discussing team norms, invoke the skill in your prompt, e.g., 'Review this PR direction according to the cultural-norms skill.' or 'Apply cultural-norms before starting the new feature.' The agent will follow the rules.
What are this skill's strengths and limitations?
- Clear cultural and collaboration rules reduce ambiguity.
- Emphasizes product coherence to avoid generic UI drift.
- Encourages capturing repeating patterns for knowledge reuse.
- No external dependencies, easy to integrate.
- Rules are high-level principles without a concrete executable checklist.
- No automated validation or tests included.
- Relies on agent interpretation of natural language, which may vary.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Engram Cultural & Collaboration Norms this page | 54 · Use with care | ★ 7.1k | 4d ago | MIT |
| PR Submission Conventions | 40 · Not recommended | ★ 5.2k | 3d ago | Apache-2.0 |
| Swift Concurrency Pro | 65 · Recommended | ★ 561 | 4mo ago | MIT |
| cmux Architecture Skill | 63 · Recommended | ★ 28k | 1d ago | NOASSERTION |
| Tool Rename Compatibility Check ✓ Microsoft · Official | 63 · Recommended | ★ 193k | 3d ago | MIT |
How did FollowSkills review this skill?
Assessed skill is a cultural norms document, not involving sensitive data processing or system operations, low risk. License is stated as Apache-2.0, but no permissions, confirmations, or data flow mentioned, limited info, hence deduction.
Skill is static guidance, no scripts or instructions, relies on execution paths non-reproducible, but document consistent with repo, no contradictions. Static cap at 10.
Use cases clear (starting feature, reviewing changes, defining conventions), but lacks explicit non-fit boundaries, trigger conditions clear but not precise, environment fit not mentioned.
Document structure clear, has metadata and triggers, but lacks maintenance info, version update path, FAQs, and license inconsistency with repo, deduction.
Provides collaboration norms, as cultural guide may promote consistency, but no direct outputs, marginal value hard to verify, static cap at 7.
No tests or third-party evidence, relies on repo overall auditability, static cap at 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →