docs(verify-readme): align the prose with the ai-facing style #40

Merged
jercik merged 1 commit from align/verify-readme into main 2026-08-06 10:51:01 +00:00
Owner

Style-only pass: the README contract itself (section order, parity rule, Agent Rule template) is unchanged; the cuts are restatements the ai-facing guide forbids.

Style-only pass: the README contract itself (section order, parity rule, Agent Rule template) is unchanged; the cuts are restatements the ai-facing guide forbids.
docs(verify-readme): align the prose with the ai-facing style
Some checks failed
Node tests / node:test (pull_request) Successful in 16s
commit-msg / commitlint (pull_request) Successful in 27s
PR Review / Prepare immutable review tools (pull_request_target) Successful in 2m16s
PR Review / forgejo-review-approach-3 generator (pull_request_target) Failing after 1m37s
PR Review / forgejo-review-code-smart-2 generator (pull_request_target) Failing after 1m37s
PR Review / forgejo-review-approach-smart-2 generator (pull_request_target) Failing after 2m13s
PR Review / forgejo-review-approach-smart-1 generator (pull_request_target) Successful in 2m13s
PR Review / forgejo-review-code-smart-1 generator (pull_request_target) Successful in 3m17s
PR Review / Dispatch and observe exact review writers (pull_request_target) Failing after 3m35s
7d113e7c2e
forgejo-actions left a comment

Approach review: The approach is sound. This is a single-file style pass on skills/verify-readme/SKILL.md that applies the repository's own ai-facing-writing-style rules to a skill document, which is the right way to do it: the contract (section order, parity rule, Agent Rule template, failure-mode list, output modes) is byte-for-byte unchanged, and every cut is a restatement that guide explicitly targets.

The individual moves line up with named rules rather than being ad-hoc trimming: dropping the # Goal heading whose body duplicated the frontmatter description follows "Structure and Formatting" (a section included for form's sake) and matches the majority convention here — only 3 of 25 skills carry a # Goal heading; collapsing the four npx -y <tool> --help bullets into one sentence and replacing the restated parity instruction in Task step 5 with a pointer to the package.json#description parity section follows "collapse the restatements into the anchor"; removing "and, if present" from the package.json read follows "cut self-evident escape hatches" (a missing file announces itself).

I checked the removals for information loss and found none that matters. The (default: README.md) parenthetical cut from Task step 1 is still stated in Inputs ("If no path is given, operate on README.md in the current working directory"), so the behavior stays pinned in exactly one place. The shortened frontmatter description keeps every trigger phrase, which is what governs skill selection, and the human-facing-prose delegation dropped from it survives in the body line that tells the agent to invoke human-facing-writing-style.

No materially better approach — the alternatives (leaving the prose as-is, or extracting shared boilerplate across skills) would either skip the alignment or over-engineer a one-file cleanup.

Approach review by Claude Code Opus (opus)

**Approach review:** The approach is sound. This is a single-file style pass on `skills/verify-readme/SKILL.md` that applies the repository's own `ai-facing-writing-style` rules to a skill document, which is the right way to do it: the contract (section order, parity rule, Agent Rule template, failure-mode list, output modes) is byte-for-byte unchanged, and every cut is a restatement that guide explicitly targets. The individual moves line up with named rules rather than being ad-hoc trimming: dropping the `# Goal` heading whose body duplicated the frontmatter description follows "Structure and Formatting" (a section included for form's sake) and matches the majority convention here — only 3 of 25 skills carry a `# Goal` heading; collapsing the four `npx -y <tool> --help` bullets into one sentence and replacing the restated parity instruction in Task step 5 with a pointer to the `package.json#description` parity section follows "collapse the restatements into the anchor"; removing "and, if present" from the `package.json` read follows "cut self-evident escape hatches" (a missing file announces itself). I checked the removals for information loss and found none that matters. The `(default: README.md)` parenthetical cut from Task step 1 is still stated in Inputs ("If no path is given, operate on `README.md` in the current working directory"), so the behavior stays pinned in exactly one place. The shortened frontmatter description keeps every trigger phrase, which is what governs skill selection, and the human-facing-prose delegation dropped from it survives in the body line that tells the agent to invoke `human-facing-writing-style`. No materially better approach — the alternatives (leaving the prose as-is, or extracting shared boilerplate across skills) would either skip the alignment or over-engineer a one-file cleanup. _Approach review by Claude Code Opus (opus)_ <!-- axrecipe-review:v1:eyJzY2hlbWFWZXJzaW9uIjoxLCJzdGF0ZSI6InB1Ymxpc2hlZCIsInJlcG9zaXRvcnkiOiJqNGstb3NzL2FnZW50LXNraWxscyIsIm51bWJlciI6IjQwIiwiaGVhZFNoYSI6IjdkMTEzZTdjMmUzMjQ3Y2JkOTk1YzQzMTBkN2QwNGZiMjhkMTc2M2QiLCJzbG90IjoiZm9yZ2Vqby1yZXZpZXctYXBwcm9hY2gtc21hcnQtMSIsInNvdXJjZVdvcmtmbG93UnVuSWQiOiIxNzM4OSIsInNvdXJjZUdlbmVyYXRvckF0dGVtcHQiOiIxIiwicmVzdWx0SWQiOiJjMzIxNDU5MS02YjdkLTQ4YWEtOWQ5NS00ZTUzNTEyNzZhNTUifQ== -->
forgejo-actions left a comment

Summary: No actionable issues found.

Style-only pass over skills/verify-readme/SKILL.md. I verified the claims in the PR body and checked for the failure modes a prose-deletion pass usually introduces:

  • Contract preserved — the section order (1–9), the package.json#description parity rule, and the Agent Rule template are byte-identical; only surrounding prose changed.
  • No dangling cross-references — Task step 5's new pointer to the "package.json#description parity" rule matches the heading exactly. Task step 6's failure modes ("without answering obvious follow-up questions or linking to deeper material") are still backed by the surviving "How it works" bullets. No file in the repo references the removed # Goal heading.
  • No information lost from Task step 1 — dropping (default: README.md) is safe because the Inputs section still states the default, and dropping if present for package.json matches the ai-facing guide's "cut self-evident escape hatches" rule (a missing file fails loudly, and the config/dotfiles case is already named in Inputs).
  • Frontmatter still valid — two keys, description parses as a plain YAML scalar (no : sequence, no leading indicator char) at 411 chars, well under the routing-description limit, and it retains the literal trigger phrases the router matches on.
  • Heading shape consistent — an unheaded lead paragraph before # Inputs matches 22 of 25 skills here, including ai-facing-writing-style itself.

Code review by Claude Code Opus (opus)

**Summary:** No actionable issues found. Style-only pass over `skills/verify-readme/SKILL.md`. I verified the claims in the PR body and checked for the failure modes a prose-deletion pass usually introduces: - **Contract preserved** — the section order (1–9), the `package.json#description` parity rule, and the Agent Rule template are byte-identical; only surrounding prose changed. - **No dangling cross-references** — Task step 5's new pointer to the "`package.json#description` parity" rule matches the heading exactly. Task step 6's failure modes ("without answering obvious follow-up questions or linking to deeper material") are still backed by the surviving "How it works" bullets. No file in the repo references the removed `# Goal` heading. - **No information lost from Task step 1** — dropping `(default: README.md)` is safe because the Inputs section still states the default, and dropping `if present` for `package.json` matches the ai-facing guide's "cut self-evident escape hatches" rule (a missing file fails loudly, and the config/dotfiles case is already named in Inputs). - **Frontmatter still valid** — two keys, description parses as a plain YAML scalar (no `: ` sequence, no leading indicator char) at 411 chars, well under the routing-description limit, and it retains the literal trigger phrases the router matches on. - **Heading shape consistent** — an unheaded lead paragraph before `# Inputs` matches 22 of 25 skills here, including `ai-facing-writing-style` itself. _Code review by Claude Code Opus (opus)_ <!-- axrecipe-review:v1:eyJzY2hlbWFWZXJzaW9uIjoxLCJzdGF0ZSI6InB1Ymxpc2hlZCIsInJlcG9zaXRvcnkiOiJqNGstb3NzL2FnZW50LXNraWxscyIsIm51bWJlciI6IjQwIiwiaGVhZFNoYSI6IjdkMTEzZTdjMmUzMjQ3Y2JkOTk1YzQzMTBkN2QwNGZiMjhkMTc2M2QiLCJzbG90IjoiZm9yZ2Vqby1yZXZpZXctY29kZS1zbWFydC0xIiwic291cmNlV29ya2Zsb3dSdW5JZCI6IjE3Mzg5Iiwic291cmNlR2VuZXJhdG9yQXR0ZW1wdCI6IjEiLCJyZXN1bHRJZCI6Ijg4MWQ5YWU1LTE4NDYtNGUxMi1iNDUyLWU0ZDEyMDMyOGVjYiJ9 -->
forgejo-actions left a comment

Approach review: The approach looks good. This is a deletion-first style pass on a single SKILL.md, which is exactly the shape ai-facing-writing-style prescribes for aligning existing content: cut restatements whole, leave the contract untouched. The README contract (section order, parity rule, Agent Rule template, failure-mode list) is unchanged, so the skill's behaviour is preserved.

The cuts land where the style guide points. Dropping the # Goal heading and its paragraph removes a near-verbatim restatement of the frontmatter description and matches the several skills here that already open with a bare lead paragraph (ai-facing-writing-style, human-facing-writing-style, handoff, node, grill-with-docs). Task step 1 losing (default: README.md) and if present costs nothing — the default is already pinned in Inputs, and a missing package.json fails loudly, the self-evident escape hatch the guide says to cut. Task step 5 now defers to the package.json#description parity section instead of paraphrasing it, which is the right direction: one home per instruction. Collapsing the four-bullet npx -y <tool> --help rationale into one sentence keeps the causal content while shedding the bullet scaffolding.

One thing worth a deliberate call rather than a change: the description also lost and applies human-facing prose rules throughout. The description is the routing surface, and the body still makes invoking human-facing-writing-style a required step, so a request phrased as README prose or wording quality has slightly less to match on. The literal trigger phrases still cover the common asks, so this is a judgement call about routing reach, not a defect.

No materially better approach to suggest.

Approach review by Claude Code Opus (opus)

**Approach review:** The approach looks good. This is a deletion-first style pass on a single `SKILL.md`, which is exactly the shape `ai-facing-writing-style` prescribes for aligning existing content: cut restatements whole, leave the contract untouched. The README contract (section order, parity rule, Agent Rule template, failure-mode list) is unchanged, so the skill's behaviour is preserved. The cuts land where the style guide points. Dropping the `# Goal` heading and its paragraph removes a near-verbatim restatement of the frontmatter description and matches the several skills here that already open with a bare lead paragraph (`ai-facing-writing-style`, `human-facing-writing-style`, `handoff`, `node`, `grill-with-docs`). Task step 1 losing `(default: README.md)` and `if present` costs nothing — the default is already pinned in Inputs, and a missing `package.json` fails loudly, the self-evident escape hatch the guide says to cut. Task step 5 now defers to the `package.json#description` parity section instead of paraphrasing it, which is the right direction: one home per instruction. Collapsing the four-bullet `npx -y <tool> --help` rationale into one sentence keeps the causal content while shedding the bullet scaffolding. One thing worth a deliberate call rather than a change: the description also lost `and applies human-facing prose rules throughout`. The description is the routing surface, and the body still makes invoking `human-facing-writing-style` a required step, so a request phrased as README prose or wording quality has slightly less to match on. The literal trigger phrases still cover the common asks, so this is a judgement call about routing reach, not a defect. No materially better approach to suggest. _Approach review by Claude Code Opus (opus)_ <!-- axrecipe-review:v1:eyJzY2hlbWFWZXJzaW9uIjoxLCJzdGF0ZSI6InB1Ymxpc2hlZCIsInJlcG9zaXRvcnkiOiJqNGstb3NzL2FnZW50LXNraWxscyIsIm51bWJlciI6IjQwIiwiaGVhZFNoYSI6IjdkMTEzZTdjMmUzMjQ3Y2JkOTk1YzQzMTBkN2QwNGZiMjhkMTc2M2QiLCJzbG90IjoiZm9yZ2Vqby1yZXZpZXctYXBwcm9hY2gtc21hcnQtMSIsInNvdXJjZVdvcmtmbG93UnVuSWQiOiIxNzQzMSIsInNvdXJjZUdlbmVyYXRvckF0dGVtcHQiOiIxIiwicmVzdWx0SWQiOiI0MGU1NWMzZS1iZDFmLTRkNmYtOWU3MS1mY2QzYjM5OGRkOTQifQ== -->
Author
Owner

Review feedback disposition (head 7d113e7):

  • approach-smart-1 and code-smart-1 (run 17389): no actionable findings — nothing to change.
  • approach-smart-1 (dispatch retry, run 17431) flagged one deliberate-call item: the frontmatter description no longer says "and applies human-facing prose rules throughout". Ruling: the cut stands. The body still requires invoking human-facing-writing-style before editing, so the phrase restated a surviving instruction, and this style-only pass deliberately reintroduces no derivable sentence. The description keeps every literal trigger phrase the router matches on; if routing reach proves too narrow in practice, widening the routing surface is a separate deliberate change, not part of this pass.

Review-cycle status: approach-smart-2, approach-3, and code-smart-2 failed their Axrecipe capability exchange (HTTP 400 "Validation failed") in both run 17389 and the maintainer-dispatch retry (run 17431, where code-smart-1 also hit a transient upstream 529). The same three slots fail identically on PRs #41 and #42, so this is service-side, not PR-specific.

**Review feedback disposition** (head `7d113e7`): - `approach-smart-1` and `code-smart-1` (run 17389): no actionable findings — nothing to change. - `approach-smart-1` (dispatch retry, run 17431) flagged one deliberate-call item: the frontmatter description no longer says "and applies human-facing prose rules throughout". Ruling: the cut stands. The body still requires invoking `human-facing-writing-style` before editing, so the phrase restated a surviving instruction, and this style-only pass deliberately reintroduces no derivable sentence. The description keeps every literal trigger phrase the router matches on; if routing reach proves too narrow in practice, widening the routing surface is a separate deliberate change, not part of this pass. Review-cycle status: `approach-smart-2`, `approach-3`, and `code-smart-2` failed their Axrecipe capability exchange (HTTP 400 "Validation failed") in both run 17389 and the maintainer-dispatch retry (run 17431, where `code-smart-1` also hit a transient upstream 529). The same three slots fail identically on PRs #41 and #42, so this is service-side, not PR-specific.
jercik merged commit ee4a6af221 into main 2026-08-06 10:51:01 +00:00
jercik deleted branch align/verify-readme 2026-08-06 10:51:01 +00:00
Sign in to join this conversation.
No reviewers
No labels
No milestone
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
j4k-oss/agent-skills!40
No description provided.