practice-registry
This skill checks Scala, Python, TypeScript, JavaScript, and Rust code against company-specific coding practices before generation, during editing, and before…
Identity proven by GitHub's verified organisation badge (writer)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
- License
- Apache-2.0 (permissive)
- Pin
- 9dd6c92pinned Oct 9, 2026
- Context cost
- about 410 tokenswhen the skill loads
- GitHub stars
- 15on writer/cerebro
- Scripts
- None found
What it does
“Use when generating, editing, or reviewing Scala, Python, TypeScript, JavaScript, or Rust code so company-specific practices are checked before planning, after edits, and before final handoff.”
Generated summary from the skill's own text
This skill checks Scala, Python, TypeScript, JavaScript, and Rust code against company-specific coding practices before generation, during editing, and before submission. It uses the Practice Registry MCP server to scan code for compliance with organizational standards and flags issues that need resolution or approval.
When to use it
- Generating or modifying code in supported languages with established company practices
- Reviewing code changes to ensure compliance with organizational standards
- Integrating practice checks into development workflows before final handoff
- Scanning diffs for concrete practice violations and guidance
When not to
- Code in languages outside the five supported languages
- Working without access to a Practice Registry MCP server
- Situations where no company-specific practices are defined
Install
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add writer/cerebro --skill practice-registryInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install writer/cerebro practice-registry@9dd6c92664bc6d15430a821b97995b4a53294a6dInstalls the commit we checked (9dd6c92).
Copy by hand
Download the folder at 9dd6c92 and put it in .claude/skills/practice-registry for Claude Code and in .agents/skills/practice-registry for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "practice-registry" by Writer. Source, pinned to commit 9dd6c92664bc6d15430a821b97995b4a53294a6d: https://github.com/writer/cerebro/tree/9dd6c92664bc6d15430a821b97995b4a53294a6d/plugins/practice-registry-mcp/skills/practice-registry 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/practice-registry/ for Claude Code and .agents/skills/practice-registry/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Listing and checks: https://www.agentnative.dev/skills/writer/practice-registry
SKILL.md at the pin
--- name: practice-registry description: Use when generating, editing, or reviewing Scala, Python, TypeScript, JavaScript, or Rust code so company-specific practices are checked before planning, after edits, and before final handoff. --- # Practice Registry Use the Practice Registry MCP server for Scala, Python, TypeScript, JavaScript, and Rust code work. 1. Before non-trivial code generation or edits, call `preflight` when intent or files are known. 2. Call `check_plan` with the intent, files, language, framework, dependencies, and planned approach before writing code. 3. After edits, call `scan_diff` with the final diff for concrete changed-line findings. 4. Use `check_diff` for advisory practice guidance when the code shape is broader than a concrete Semgrep finding. 5. Before the final response, call `finalize_change` with the final diff and pass the matching `check_plan` observation id when available. 6. Trust the `passed` field. Treat only `allowed` and `follow_guidance` as pass decisions. 7. Use `explain_practice` before overriding a `discouraged`, `legacy_accepted`, or `needs_review` result. 8. Treat `banned` findings as blockers. Change the code before finishing. 9. Treat `legacy_accepted` as allowed only for the recorded context. Do not add new handwritten uses of legacy patterns. 10. Use `propose_practice` for repeated uncovered decisions and `record_exception` for scoped exception requests. 11. Resolve `needs_review` through the named owner or `record_approval`. Research approval requires an indexed practice plus at least two directly supporting HTTPS sources from independent publishers and domains. 12. Do not use research approval to approve an exception. Exceptions still require the recorded owner decision. If hooks or CI report a practice finding, fix the code and rerun the same check before summarizing the work.
From writer/cerebro at 9dd6c92, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.
View SKILL.md on GitHub at 9dd6c92Files
- SKILL.md1.9 KB · 2da2238de8de
1 file, 1.9 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at 9dd6c92More from Writer
agent-execution-receipts
This skill inspects signed execution receipts and correlates them with provider audit logs to determine whether an agent action has local evidence, a…
Claude Code, Codex, Cursor +4 · about 290 tokens · pinned 6 days ago
account-targeting-and-research
This skill helps sales and marketing teams identify and research enterprise accounts most likely to buy.
Claude Code, Codex, Cursor +4 · about 2.6K tokens · pinned 6 days ago
b2b-content-and-campaigns
This skill helps the agent create enterprise B2B marketing content and campaigns, including case studies, executive thought leadership, email programs, web…
Claude Code, Codex, Cursor +4 · about 1.4K tokens · pinned 6 days ago
business-case-and-proposal
This skill helps agents construct enterprise business cases, ROI and TCO models, executive summaries, proposals, RFP responses, security questionnaires, and…
Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago
competitive-and-objections
This skill equips agents to build honest competitive battle cards, handle sales objections, and analyze win/loss outcomes.
Claude Code, Codex, Cursor +4 · about 2.5K tokens · pinned 6 days ago
customer-facing-quality-gate
This skill performs a final review of customer-facing content before it leaves the organization, checking every factual claim against sources, flagging…
Claude Code, Codex, Cursor +4 · about 3.9K tokens · pinned 6 days ago
Related in Coding workflow
final-release-review
Audits Python SDK release candidates or plans against the previous release, comparing diffs for regressions, API changes, and version compatibility.
by OpenAIOfficial publisher
Contains scripts
Claude Code, Codex, Cursor +3 · about 5.4K tokens · pinned 6 days ago
n8n-code-nodes-official
This skill guides agents to use n8n Code nodes correctly as a last resort.
by n8nOfficial publisher
Claude Code, Codex, Cursor +4 · about 2.9K tokens · pinned 6 days ago
migrating-airflow-2-to-3
This skill guides agents through migrating Apache Airflow 2.x DAG code to Airflow 3.x, handling breaking changes in imports, operators, context variables, and…
by AstronomerOfficial publisher
Claude Code · about 2.1K tokens · pinned 6 days ago
no-bare-casts
This skill enforces a decision tree for TypeScript casts, requiring developers to eliminate bare `as` casts through type refinement, runtime checks, or using…
by PrismaOfficial publisher
Claude Code, Codex, Cursor +4 · about 650 tokens · pinned 6 days ago
coding-workspace-fixture
This skill lets the agent evaluate and modify a small TypeScript project located in the coding-workspace-fixture directory.
by SentryOfficial publisher
Contains scripts
Claude Code, Codex, Cursor +3 · about 56 tokens · pinned 6 days ago
managing-python-dependencies
This skill ensures the agent manages Python dependencies correctly by detecting the project's existing dependency manager and using the appropriate tool.
by GoogleOfficial publisher
Claude Code, Codex, Cursor +4 · about 740 tokens · pinned 6 days ago
Open roles at Writer
5 of 15 open roles on the jobs board
- Security engineer, detection and response (UK)
London, UK (Remote)
- Security engineer, application security (UK)
London, United Kingdom (Hybrid)
- Infrastructure engineer
New York City, NY, USA | Seattle, WA, USA | San Francisco, CA, USA | London, UK (Hybrid)
- Staff security engineer, application security
New York City, NY, United States | Seattle, WA, United States | San Francisco, CA, United States (Hybrid)
- AI engineer (UK)
London, UK (Hybrid)