jitsusama/pr-workflow-critique-output
skills/pr-workflow-critique-output/SKILL.md
Output contract for round-3 critique reviewer subagents in pr-workflow. The JSON shape of critique entries, position vocabulary, rationale requirements, and the verify_output self-check protocol. Loaded into each critique reviewer subagent via --skill.
$ install --global
skillsauthnpx skillsauth add jitsusama/agentic-harness.pi pr-workflow-critique-outputInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 27, 2026, 7:31 AM117.9s1 file scanned
SKILL.md
- name:
- pr-workflow-critique-output
- description:
- >
Round-3 critique output
Reply with a single fenced JSON block. No prose outside the block.
Top-level shape
{ "critiques": [ <CritiqueEntry>, ... ] }
Each CritiqueEntry has:
findingId— the consolidated finding's id from the judge's round-2 output.position— one ofagree,disagree,qualifyoramplify.rationale— one to two sentences. Must contain non-whitespace prose: blank rationales fail verification.
What a good rationale says
The rationale should name evidence, not opinion:
- What did you find in the worktree that proves the finding?
- What did you find that disproves it?
- Does the finding merely repeat an existing thread
(e.g.
[T3])?
A vague "I agree" or "looks fine" rationale is unacceptable. Be specific.
Self-verify before ending
The subagent has access to the verify_output tool from
the pr-workflow-critique-verify extension. Before
finishing your run:
- Call
verify_outputwithoutputset to the object you intend to emit (pass the object itself, not a stringified copy). - The tool returns
ok: truewith the parsed entry count, orok: falsewith a list of{path, message, hint}errors. - If errors are reported, fix the offending fields and
call
verify_outputagain. - Only emit your final fenced JSON block (and end the
run) once the verifier returns
ok: true.
If the verifier keeps reporting the same error after three attempts, emit your best attempt and the parent will surface the warnings.
Related Skills
jitsusama/quest-format
development
VerifiedTrustedCommunity
Structure of a quest README and the documents that live under it: frontmatter shape, the four core and four optional body sections, emoji glyphs, ID format, alias notation, Cast bullets and Journey entries. Use when writing or editing a quest README, a plan, research, brief or report document under a quest. Pairs with quest-convention for choices like kind, promotion and reordering. Follow the prose-standard for voice.
5SKILL.mdUpdated Jun 4, 2026
jitsusama/quest-convention
tools
VerifiedTrustedCommunity
Operational conventions for the quest system: when to use a quest versus a subquest versus a sidequest, when to scaffold a plan or research document, how to reorder priorities, when to add optional sections, when to conclude versus retire, the resuscitate pattern. Use when driving the quest tool, deciding kind, promoting or parking work, or organising a project as quests. Pairs with quest-format for the on-disk shape.
5SKILL.mdUpdated Jun 4, 2026
jitsusama/markdown-standard
development
VerifiedTrustedCommunity
Markdown structure rules: Title Case headings with their exceptions, the line-width target and its legitimate exceptions, reference-style links, fenced code blocks with language tags, tables and lists. Use when writing or editing any markdown file (README, AGENTS, docs, plans, skill files), or when adding a heading, link, table or code block. Owns markdown structure; pairs with prose-standard, which owns voice, grammar, spelling and punctuation.
5SKILL.mdUpdated Jun 4, 2026
jitsusama/convention-recurrence-sensor-guide
tools
VerifiedTrustedCommunity
How to measure whether convention corrections keep recurring in the pi session logs, by category and by week. Use to record a baseline before the convention gates take effect and to re-run afterwards to confirm the recurring categories bend down. Pairs with the convention gates (pr-guardian, issue-guardian, commit-guardian, slack-integration) and the convention-context extension.
5SKILL.mdUpdated Jun 4, 2026