Package Resync a Repo and Fleet Conformance Check as Skills - #679
Conversation
Phase 4 of the hub-docs-to-Skills conversion. resync-a-repo packages RESYNC.md section 3's apply order for a hub-context session driving a named repo's resync, with the carried-instruction-file-guard skill's distinctive-phrase probe made a mandatory, non-skippable step before any verbatim re-vendor of an instruction file. fleet-conformance-check is the new downstream-facing counterpart: run from inside a repo's own session with no hub checkout and no named target, it confirms the local Skills install is current, confirms AGENTS.md's pointer text matches the hub, self-applies what is safe, and escalates anything ambiguous to a hub-driven resync-a-repo run. RESYNC.md section 3 step 1 gains the mandatory probe requirement and the AGENTS.md skill-dependency pointer as one more verbatim-carried unit, sitting alongside the existing instruction-set-first step. AGENTS.md's Where the Rules Live table and pointer paragraph route to both new skills. .claude-plugin/fleet-skills/ rebuilt via build_dist.py. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
This PR continues the hub-docs-to-Skills conversion by adding two new fleet Skills (resync-a-repo and fleet-conformance-check) and updating the hub’s resync and routing docs so agents are directed to the right Skill-driven workflow.
Changes:
- Add
resync-a-repo(hub-context) andfleet-conformance-check(downstream-context) as Skills in both.agents/skills/(source) and.claude-plugin/fleet-skills/(generated dist). - Update
RESYNC.mdstep ordering guidance to make thecarried-instruction-file-guardprobe mandatory before verbatim instruction-file re-vendor, and to treat the AGENTS skill-pointer paragraph as part of the same “instruction set first” step. - Update
AGENTS.mdrouting to point conformance/resync scenarios to the new Skills.
Reviewed changes
Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| RESYNC.md | Expands resync step 1 guidance and mandates the probe before verbatim instruction-file re-vendor. |
| AGENTS.md | Updates “Where the Rules Live” routing and pointer paragraph to reference the new Skills. |
| .agents/skills/resync-a-repo/SKILL.md | Adds the source Skill definition for hub-driven resync procedure. |
| .agents/skills/fleet-conformance-check/SKILL.md | Adds the source Skill definition for in-repo conformance checking and safe self-fixes. |
| .claude-plugin/fleet-skills/skills/resync-a-repo/SKILL.md | Adds generated Claude Code Skill copy of resync-a-repo. |
| .claude-plugin/fleet-skills/skills/fleet-conformance-check/SKILL.md | Adds generated Claude Code Skill copy of fleet-conformance-check. |
| .claude-plugin/fleet-skills/.claude-plugin/plugin.json | Registers the two new Skills in the plugin manifest. |
| .claude-plugin/fleet-skills/.source-digest | Updates the dist source digest to reflect the rebuilt plugin output. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
The skill's description said it runs with no hub checkout required, while its own steps instruct fetching one to reach scripts/skills_install.py. Both are true at once: no *standing* checkout is needed to invoke the skill or name a target, but the check itself fetches one transiently to reach hub-hosted tooling, per Hub-Hosted Tooling. Reworded the skill's description and AGENTS.md's pointer paragraph to say both halves instead of only the first. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 8 out of 8 changed files in this pull request and generated no new comments.
Suppressed comments (1)
.agents/skills/resync-a-repo/SKILL.md:66
- This inline code span is broken across a newline (
... <owner>/<repo>thenrelease|operationalon the next line). CommonMark code spans cannot contain line breaks, so this will render inconsistently and makes the command easy to copy incorrectly.
Suggestion: keep the full command on one line (or switch to a fenced code block). Since this Skill is also emitted into .claude-plugin/fleet-skills/, update the source here and regenerate the dist output (and .source-digest).
5. **Settings, rulesets, and secrets.** Run `repo-config/configure.sh check <owner>/<repo>
release|operational` against the repo by name, then `apply` for what it reports, never from a
carried copy.
CommonMark code spans cannot contain a line break, so the repo-config/configure.sh command wrapped mid-span rendered inconsistently and was easy to copy incorrectly. Moved the wrap point outside the backticks and regenerated the dist copy. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
|
Answering round 2's suppressed finding: .agents/skills/resync-a-repo/SKILL.md:66 — "This inline code span is broken across a newline ( Fixed in 43fb9da: moved the wrap point outside the backticks so |
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 8 out of 8 changed files in this pull request and generated no new comments.
Suppressed comments (1)
.agents/skills/resync-a-repo/SKILL.md:34
spec/audit.pytakes registry repo names (therepos[].namevalues likeUtilities), but this skill uses the placeholder<repo>here while also using<owner>/<repo>elsewhere. That makes it ambiguous whether the argument is a local checkout path, anowner/reposlug, or the registry repo name.
Please rename the placeholder to something unambiguous (e.g. <RepoName>) and ideally note it maps to the registry name field.
Read RESYNC.md section 0. A repo with no instruction set at all, or a partial one, is not this
skill's job, it is STANDUP.md sections 1A and 2 instead, since an absent carried file is a
baseline that never arrived rather than drift to converge. Run `spec/audit.py <repo>` and read
whether the findings are letters (absent) or drift (present but stale) before doing anything else.
The finding kind names the procedure the repo is owed.
<repo> was used for spec/audit.py's registry-name argument, while <owner>/<repo> named an unrelated owner/repo slug a few lines later, so a reader could not tell whether the argument was a checkout path, a slug, or the registry name. Renamed to <RepoName>, matching the tool's own --help metavar, and named it as the registry name field explicitly. Regenerated the dist copy. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
|
Answering round 3's suppressed finding: .agents/skills/resync-a-repo/SKILL.md:34 — " Fixed in 0a01dfe: renamed the placeholder to (The other suppressed finding this round, on the same file at line 66, is the inline-code-span break already answered above, fixed in 43fb9da.) |
Phase 5 of the hub-docs-to-Skills conversion (Phase 0/1 shipped in #676, Phase 2 in #677, Phase 3 in #678, Phase 4 in #679). ## What this adds - `dotnet-codestyle` (appliesTo csharp), `python-codestyle` (appliesTo python), and `shell-codestyle` (appliesTo *, since a shell script can appear in any repo), extracted from CODESTYLE.md's .NET, Python, and Shell sections respectively: build/analyzer requirements, language and naming conventions, logging and testing conventions, the Python build-versus-lint-only profile split and toolchain, and the shell `set -Eeuo pipefail` / pipefail-early-reader / shellcheck rules. - This is the first phase gating a skill by `appliesTo` rather than fleet-wide `*`, expressed through each skill's own trigger wording (file extensions and project shape) rather than a mechanical field, since SKILL.md frontmatter carries no such field. ## What changed in existing files - CODESTYLE.md's .NET, Python, and Shell sections shrink to pointers, per this project's standing decision that a skill becomes the sole canonical content for its topic once one exists. No spec file or test references any subheading inside these three sections, so each collapses fully rather than keeping empty subheadings. Six now-orphaned link reference definitions (MD053) are removed with them. - CODESTYLE.md's and AGENTS.md's own descriptions of the file's structure are corrected to mention the pre-existing Shell section, which neither previously named. - `.claude-plugin/fleet-skills/` regenerated via `scripts/build_dist.py` to carry the three new skills alongside the six from Phases 1-4. ## Dropped - `docker-codestyle` (Phase 5b): a content-discovery pass found no dedicated Docker style section in CODESTYLE.md, only scattered linter-invocation mentions in OPERATIONS.md and release mechanics in GOVERNANCE.md, neither of which is Docker coding style. Not authored, per the plan's own don't-invent-content instruction. ## Verification performed - `scripts/prose_lint.py`, CRLF byte-integrity (all touched/new files 100% CRLF), `editorconfig-checker` (docker), `markdownlint-cli2` (docker, 72 files, 0 issues), `spec/validate.py`, `scripts/test_prose_lint.py` (223 tests), `scripts/test_build_dist.py` (19 tests), and `scripts/test_skills_install.py` all clean. - `scripts/build_dist.py --check` confirms the generated plugin is current relative to `.agents/skills/`. - Grepped `scripts/test_*.py` and `spec/*.json` for any coupling to the trimmed CODESTYLE.md subheadings before trimming: none found. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
…Python CI Gates (#718) Thirty-one squashes, `56f4d7d..d54862a`. 115 files, +20436/-5298. **Merge with a merge commit, never a squash, and never with `--delete-branch`.** This pull request's head is `develop` itself. ## What lands **Fleet Skills.** The `.agents/skills/` source tree, the generated `.claude-plugin/` distribution, `scripts/build_dist.py` with its `--check` gate, and `scripts/skills_install.py` with its host stamp (#676). Packaged as skills on top of the scaffold: PR review conduct and Copilot instructions upkeep (#677), comment and doc style (#678), resync-a-repo and fleet-conformance-check (#679), the per-language codestyles (#680), git commit conventions and operational vs release workflow (#681), stand up a repo (#683), and repo-worktree (#717). Coverage gaps closed in three passes (#690, #691, #692) plus the P4 sentence-length opt-in (#697). **Host setup.** The Windows host-setup tooling and its PowerShell gate (#674), the Windows bootstrap loader (#682), Docker install and upgrade on Linux and Windows with a version floor (#701, #705), a `uv` floor in `spec/host-tools.json` (#698), self-healing of a shadowing `uv`, `jq`, or `git-restore-mtime` copy (#689), node's real winget package id (#696), and a README for the Linux host-setup nuances (#710). **Python and CI.** Python tooling in CI with the script tests moved to `scripts/tests` (#704), `ruff format` adopted and gated (#709), and the PSScriptAnalyzer claim conditioned on repos that carry `.ps1` files (#686). **Conduct rules.** Triage-order and scope guardrails in pr-review-conduct (#684), `pr_review.py wait` requesting a review rather than only polling for one (#685), a tech-agnostic signed-commit verification (#708), execution rather than analogy to verify platform-specific code (#715), and a unique worktree for every task (#717). **Docs.** The fleet map and gap register with peer messaging declared (#687), mermaid flow diagrams in the kept-authority docs (#702), and the map pointed at the shipped diagrams and current tooling (#703). ## Issues this promotion closes Each landed on `develop` on its own pull request. The keyword fires only on a merge into `main`, so it sits here rather than on the feature pull requests. Closes #700 Closes #707 Closes #711 Closes #712 Closes #714 Closes #688 #699 stays open on purpose: #717 shipped the layout convention and the skill, and the physical migration of existing checkouts is still tracked there. ## Review record Every squash closed its own Copilot loop on its own pull request before merging to `develop`. This promotion carries no new content of its own, so its review is the merged tree as a whole. ## Consequence worth stating The `GOVERNANCE.md` and `AGENTS.md` sections these squashes changed become the canonical the moment this reaches `main`, and every carrying repository reads as drifted from that point until it resyncs. That is the ordinary consequence of a canonical moving rather than a defect. The Skills installer added here is also how a machine picks the new skills up, so a session that keeps restating a rule already packaged as a skill is the signal to run it.
Phase 4 of the hub-docs-to-Skills conversion (see #676, #677, #678 for Phases 0-3).
What this adds
resync-a-repo(hub-only): packagesRESYNC.mdsection 3's apply order for a hub-context session driving a named repo's resync. Thecarried-instruction-file-guardskill's distinctive-phrase probe is now a mandatory, non-skippable step before any verbatim re-vendor of an instruction file, the direct structural fix for the AGENTS.md-overwrite bug class rather than a rewording of existing advisory language.fleet-conformance-check(fleet-wide,appliesTo: "*", new content): the downstream-facing counterpart. Runs from inside a repo's own session with no hub checkout and no named target other than the repo itself. Confirms the local Skills install is current, confirmsAGENTS.md's pointer text matches the hub, self-applies what is safe (re-running the installer), and escalates anything ambiguous (a genuine local addition, a settings/workflow drift) to a hub-drivenresync-a-reporun rather than touching it.Supporting changes
RESYNC.mdsection 3 step 1 gains the mandatory probe requirement and theAGENTS.mdskill-dependency pointer as one more verbatim-carried unit in the same step.AGENTS.md's "Where the Rules Live" table and pointer paragraph route to both new skills..claude-plugin/fleet-skills/rebuilt viabuild_dist.py(now 6 skills).Verification
python3 -m unittest discover -s scripts -p "test_*.py": 628 tests, all pass.python3 scripts/prose_lint.pyon all touched files: clean.python3 spec/validate.py: clean.docker run ... mstruebing/editorconfig-checker:latest: clean.🤖 Generated with Claude Code