Applies the two review suggestions on #624: the label was left with nothing
under it once the phrases moved to When to Use, and the Not-for line (from
nucliweb's review, originally in #492) marks where interview-me and
spec-driven-development take over.
Co-authored-by: Joan León <nucliweb@users.noreply.github.com>
docs/agents.md and two persona files said /review and /test wrap the
code-reviewer and test-engineer personas. They invoke a skill in the main
session and spawn nothing (#681). The review commands also still asked for
Critical/Important/Suggestion while the skill and persona use
Critical/Required/Optional/Nit, and /ship named the old labels.
Three fenced blocks were labelled bash but hold JavaScript: the Frontend
and Backend measurement examples in performance-optimization (web-vitals
imports, console.time) and the measurement block in the performance
checklist, which mixed npx commands with web-vitals code in one shell
fence. An agent reading a bash block can try to run it in a shell, and
`#` is not a JavaScript comment. Relabel the two skill blocks as
javascript with // comments, and split the checklist block into a bash
fence for the npx commands and a javascript fence for the code. Content
is unchanged line for line.
The Codex manifest's longDescription still said 24 workflows; the pack
has had 25 skills since constraint-driven-development landed. Say 25.
Found by scanning every fenced block in the repo by declared language;
these were the only mislabels.
- Node 24, the version CI pins, not Node 20+.
- Drop "in the order the workflow runs it": the checks are spread across
jobs and run in a different order. Group them by what they cover.
- Drop "this is the full set": name the two jobs that need the Claude
Code CLI (claude plugin validate, and the marketplace install) and say
when to run them.
- Restore the rule that editing skills/using-agent-skills/SKILL.md
requires the session-start hook test, since the script embeds the file.
- List the three hook test commands; `bash hooks/*-test.sh` runs only the
first match and passes the others as arguments.
- Remove the "new validator ships with a test file and a CI step" line;
it is policy, not a doc sync, and goes in its own PR.
docs/developer-onboarding.md promises that everything CI runs can be run
locally, then lists three validators, the eval runner and one hook test.
CI runs six validators, seven unit-test files and three hook suites on
three operating systems, so a contributor following the doc can fail
several steps they never ran. The Tier 1 row in evals/README.md names
two validators where there are five, and Tier 2 omits the rank-1 floor.
List every workflow command in the onboarding block in workflow order,
note the PowerShell glob caveat, state the cross-platform leg, name the
workflow file as the source of truth, and align Path 3 and the pre-PR
checklist. Update both tier rows in evals/README.md. CLAUDE.md's stale
line is left for later because #548 edits that file.
Every command in the new block was run from this branch and passes, and
every command in the workflow appears in the block.
Preserve the parser's null-or-object contract while reporting blank
evidence separately from malformed grader output. Keep rejected
responses on the raw-only persistence path.
Add CLI regressions for both verdicts, whitespace variants, malformed
grading, valid output, and stale scored-artifact cleanup.
Reject trim-empty evidence for both passing and failing verdicts and
ask the grader to explain observed or missing behavior. Keep invalid
responses on the existing raw-only persistence path.
Add regression coverage for blank evidence, Unicode whitespace,
evidence preservation, and scored-artifact rejection.
Two open threads, one doc. #652 reads the Cursor guide as wrong because
this repository has no .cursor/ directory; the guide means the user's
project but never says so. #494 reports Cursor failing with "An
unexpected error occurred on our servers" when a skill is attached to a
prompt with /, after which every message in that chat fails; the
maintainer confirmed it is Cursor-side, named referencing the skill by
name as the workaround, and said the setup doc should carry a note.
Add one sentence after the intro saying every .cursor/ path is in the
reader's project and this repo ships none, linking to the install step.
Add a troubleshooting row for the attach error with the workaround and a
pointer to #494, which stays open as a known host issue. Add the
project-not-repo clause to the README's Cursor entry.
Closes#652. Refs #494.
#542 reports following docs/copilot-setup.md and finding no /spec, /plan,
/build or /test. The doc already says the wrappers are Claude Code
commands, but in the middle of a paragraph that a reader scanning for
install steps walks past; the reporter did. The maintainer's answer on
the issue was that the doc should make this explicit.
Add a callout right after the intro that names the commands, says they
are expected to be absent, and points to the skill-name mapping and the
optional aliases. Add a lead-in to the troubleshooting list that rules
out the expected case before the real diagnostics. Add one sentence to
the README's Copilot entry so the expectation is set before the doc is
opened.
Closes#542
Keep operational facts and caveats intact when editing documentation. Reference a pinned Zero Slop workflow only as an optional review aid, and add an execution fixture for the preservation checks.
Pi implements the Agent Skills standard natively and discovers skills from
~/.agents/skills/ and .agents/skills/ with no plugin or config file, so its
package manager installs the pack directly from git.
Follows the Adding a Host Guide bar (CONTRIBUTING.md): one line, host name
and install command only.
Refs #355, #365
The fx setup guide (#507) was closed under the new host-guide bar, which
gives hosts no maintainer has run one line in docs/other-hosts.md. Add
that line with the corrected install command from the guide: copy the
skills into .fx/skills/, fx's native project root, discovered from 0.0.5
on. No affiliation with fx or Vercel Labs.
Refs #504, #507
