Documentation updates can be technically accurate yet unnecessary,
duplicated, or poorly placed. Update research to justify an edit through
the reader's task and a specific documentation gap, write to integrate
it into the existing page, and review-changes to assess reader value,
placement, and flow.
Keep the guidance in the existing skills, without a required reporting
template. Each skill update has its own commit.
Markdown checks pass; Vale reports only pre-existing findings outside
the edited lines. Skill validation passes after excluding unchanged
Claude-specific metadata unsupported by the Codex validator.
Generated by Codex
## Summary
Removes files left over from earlier agent tooling that nothing
references anymore, and moves the `curate-whats-new` examples next to
the skill that uses them.
- Delete `tech_writer.yml` and `docs_engineer.yml`, unused docker-agent
configs, and the `.validation.log` ignore entry that only they wrote.
- Delete `.github/prompts/`, unreferenced Copilot prompt files that link
to a nonexistent style guide.
- Move `.github/agents/whats-new-examples/` to
`.agents/skills/curate-whats-new/examples/`.
`.github/agents/docs-scanner.yaml` and the `docker-agent-action`
workflows stay, since CI still uses them.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
## Summary
Agents can produce prose that passes style checks but still sounds
unnatural or takes effort to understand. Add guidance to AGENTS.md and a
required prose review with concrete examples to the write skill.
Broaden the skill to cover PR text, release notes, and other prose,
while keeping its branch and commit workflow specific to documentation
fixes.
Markdown formatting passes. Vale reports only existing findings in
unchanged text; the skill validator rejects the existing `hooks` field.
Generated by Codex
Several documented prose patterns were not enforced, and agents could overlook non-fatal Vale warnings.
Expand Docker's local Vale rules, remove obsolete rule links, and clarify scoped agent validation.
The scheduled curation workflow adds operational complexity to an editorial task that requires human review.
Remove the automation and tune the retained skill to report decisions directly without workflow-specific handoff files.
Co-Authored-By: Claude <noreply@anthropic.com>
## Summary
Fix the Sonnet 5 request failure by removing the deprecated temperature
setting. Make daily curation incremental: skip the model when there are
no unseen merges or expired highlights, review only unseen merge dates
when work exists, and retain a manual full-window recalibration option.
Generated by Codex
## Summary
Replace the static Featured topics section with a data-driven Whatʼs new
timeline. Show the five most important launches by default and let
readers expand the full curated 30-day archive.
Run a daily Claude Sonnet 5 curator over a rolling 30-day window, with
manual dispatch support, deterministic validation, and bot-managed pull
requests. Package the editorial workflow as the reusable
`curate-whats-new` repository skill so Docker Agent and other Agent
Skills-compatible clients can invoke the same process.
Preserve the human-reviewed July 13 through August 11, 2026 result and
flexible selection criteria as a regression example outside the skillʼs
runtime context.
@netlify /
[Homepage
preview](https://deploy-preview-25729--docsdocker.netlify.app/)
Generated by Codex
## Summary
Removes the unused Learnings/reflections section from the create-pr
skill (the self-learning loop it fed was never used), adds optional
guidance for Netlify deploy-preview entry paths and deep links on
focused PRs, and tightens the branch/remote handling (default-branch
guard, `git status --porcelain` clean-tree check, origin-vs-fork
fallback, and a `docs:` title-prefix note).
Generated by Claude Code
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The `PreToolUse:Bash` hook invoked `enforce-git-hygiene.sh` on every Bash tool call, even though the script only blocks `git add . / -A / --all`. Add `"if": "Bash(git add *)"` so the script only runs when the command actually contains `git add`.
Documentation PRs don't need test plans, but the system-level PR
template includes one. Add an explicit prohibition so the skill
instruction overrides the default.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The lint script was buried in the write skill's scripts directory, so
only agents that invoked that specific skill discovered it. Move it to
the repo-level scripts/ directory and reference it from AGENTS.md so
every agent session sees the recommended workflow.
- scripts/lint.sh: scoped markdownlint + vale on changed files
- AGENTS.md Commands and Verification loop now point here
- write skill SKILL.md updated to use the new path
- post-edit.sh stays in the skill (it's a PostToolUse hook tied to that
skill's lifecycle)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Hey @dvdksn 👋
I ran your skills through `tessl skill review` at work and found some targeted improvements for `create-lab-guide`. Here's the full before/after:
| Skill | Before | After | Change |
|-------|--------|-------|--------|
| create-lab-guide | 69% | 90% | +21% |
| check-pr | 99% | — | — |
| fix-issue | 99% | — | — |
| research | 97% | — | — |
| triage-issue | 96% | — | — |
| write | 93% | — | — |
| agent-readiness-audit | 93% | — | — |
| testcontainers-guides-migrator | 90% | — | — |
| create-pr | 90% | — | — |
| review-changes | 86% | — | — |
| migrate-content-ia | 79% | — | — |
## Description
Improves the `create-lab-guide` skill's description and content structure. The skill had the lowest baseline score (69%) across the repo's 11 skills, with the most room to grow — so it made sense to focus here.
<details>
<summary>Changes made</summary>
- **Rewrote frontmatter description** with explicit "Use when..." clause and five natural trigger terms (`create a lab guide`, `write a Labspace page`, `add a Docker lab tutorial`, `migrate a lab to docs`, `document a hands-on lab`)
- **Fixed duplicate "Step 2" heading** — renumbered to a proper 5-step sequence (Clone → Extract → Write → Style → Validate)
- **Added validation step (Step 5)** with explicit gate: frontmatter field checks, prettier formatting, lint/vale pass, and manual review before commit
- **Compressed style rules** from a verbose bullet list into a scannable two-column table
- **Replaced prose file listing** with a structured table mapping files to their purpose
- **Preserved all Labspace domain expertise**: `labspace.yaml`, `labspace-launch` shortcode, `dockersamples` org conventions, `model-download` parameter, `compose.override.yaml` model detection
</details>
I also stress-tested your `triage-issue` skill against a few real-world task evals and it held up really well on issue verdict decision trees with cross-referenced timeline checks. Kudos for that.
Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute.
Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me — [@yogesh-tessl](https://github.com/yogesh-tessl) — if you hit any snags.
## Related issues or tickets
N/A — proactive improvement based on skill evaluation.
## Reviews
- [ ] Technical review
- [ ] Editorial review
Thanks in advance 🙏
The issue triage and PR creation workflows did not require checking issue timeline cross-references for existing open PRs.
Added timeline checks to triage and create-pr instructions so agents skip duplicate PRs when an issue already has an associated fix.
Co-Authored-By: Codex <noreply@openai.com>
oreply@openai.com>
Several repo-managed skills hardcoded Claude Code in PR and issue comment footers.\n\nUpdate the skill guidance to require naming the active coding agent explicitly instead of hardcoding a specific tool name.
David Karlsson
Stefano Baghino
Yogesh Rao
Codex
Alexa Kristensen
Michael Irwin