chore(skills): vendor grill-with-docs, to-prd and to-issues

[davidp57]

Résumé

Copie de trois skills d'aide à la rédaction depuis le set global vers .claude/skills/, pour qu'ils soient versionnés et partagés avec le repo :

• grill-with-docs (+ ADR-FORMAT.md, CONTEXT-FORMAT.md)
• to-prd
• to-issues

Contenu réel copié (pas des symlinks), donc portable pour tout clone du dépôt.

🤖 Generated with Claude Code

Summary by Sourcery

Vendor three Claude authoring skills into the repository so they are versioned and available to all clones.

New Features:

• Add the grill-with-docs skill for domain-aware design grilling with inline CONTEXT and ADR updates.
• Add the to-issues skill for breaking plans or PRDs into vertical-slice implementation tickets.
• Add the to-prd skill for synthesizing a PRD from existing conversation and codebase context.

Documentation:

• Include CONTEXT-FORMAT and ADR-FORMAT documentation to standardize glossary and ADR structures used by grill-with-docs.

[sourcery-ai]

Reviewer's Guide

Vendoring three existing AI skills into the repository so they are versioned, portable, and share project-specific documentation formats for domain context and ADRs.

File-Level Changes

Change	Details	Files
Introduce the grill-with-docs skill locally, including its detailed interaction script and supporting documentation formats for CONTEXT and ADR files.	Add SKILL definition describing how to run a grilling session against domain model, glossary, code, and documentation, including rules for updating CONTEXT.md and offering ADRs. Add CONTEXT-FORMAT documentation outlining structure, rules, and multi-context handling for CONTEXT.md glossary files. Add ADR-FORMAT documentation specifying minimal ADR template, numbering, directory layout, and criteria for when to record architectural decisions.	.claude/skills/grill-with-docs/SKILL.md .claude/skills/grill-with-docs/CONTEXT-FORMAT.md .claude/skills/grill-with-docs/ADR-FORMAT.md
Add the to-issues skill to break plans or PRDs into actionable vertical-slice issues for the project issue tracker.	Define SKILL metadata and high-level description for converting plans/specs into issues. Describe step-by-step process for gathering context, optionally exploring the codebase, drafting tracer-bullet vertical slices, iterating with the user, and publishing issues. Provide a reusable issue body template including sections for parent reference, what to build, acceptance criteria, and blockers.	.claude/skills/to-issues/SKILL.md
Add the to-prd skill to synthesize a PRD from existing conversation and codebase context and publish it as an issue.	Define SKILL metadata and description for generating PRDs from current context without further user interviewing. Document a process for exploring the repo, identifying seams, confirming them with the user, and then authoring and publishing a PRD with a ready-for-agent label. Embed a detailed PRD template covering problem statement, solution, extensive user stories, implementation decisions, testing decisions, out-of-scope items, and further notes.	.claude/skills/to-prd/SKILL.md

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've found 2 issues

Prompt for AI Agents

Please address the comments from this code review:

## Individual Comments

### Comment 1
<location path=".claude/skills/grill-with-docs/ADR-FORMAT.md" line_range="44" />
<code_context>
+- **Boundary and scope decisions.** "Customer data is owned by the Customer context; other contexts reference it by ID only." The explicit no-s are as valuable as the yes-s.
</code_context>
<issue_to_address>
**issue (typo):** Fix the pluralization of "no-s" and "yes-s".

This sentence reads awkwardly; consider "The explicit nos are as valuable as the yeses" for clearer, more conventional wording.

```suggestion
- **Boundary and scope decisions.** "Customer data is owned by the Customer context; other contexts reference it by ID only." The explicit nos are as valuable as the yeses.
```
</issue_to_address>

### Comment 2
<location path=".claude/skills/to-prd/SKILL.md" line_range="6-15" />
<code_context>
+This skill takes the current conversation context and codebase understanding and produces a PRD. Do NOT interview the user — just synthesize what you already know.
</code_context>
<issue_to_address>
**issue:** Resolve the inconsistency between "do NOT interview the user" and later instructions to check with the user.

Step 2 later says "Check with the user that these seams match their expectations," which contradicts the instruction not to interview the user. Please clarify what level of user interaction is allowed for this skill and update the wording so these instructions are consistent.
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}