jitsusama/pr-workflow-stack-judge-output
skills/pr-workflow-stack-judge-output/SKILL.md
Output contract for stack-wide judge subagents in pr-workflow. The JSON shape with per-PR and cross-PR findings, attribution fields, optional self-signal, membership rules, and the verify_output self-check protocol. Loaded into each stack-judge subagent via --skill.
$ install --global
skillsauthnpx skillsauth add jitsusama/agentic-harness.pi pr-workflow-stack-judge-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, 7:33 AM193.7s1 file scanned
SKILL.md
- name:
- pr-workflow-stack-judge-output
- description:
- >
Stack-judge output
Reply with a single fenced JSON block. No prose outside the block.
Top-level shape
{
"selfSignal": { ... }, // optional
"perPr": {
"<prNumber>": [ <Finding>, ... ],
...
},
"crossPr": [ <CrossFinding>, ... ]
}
perPr
- Keys are PR numbers encoded as strings (e.g.
"101","205"). They must match the pattern/^[1-9][0-9]*$/. - Include every PR in the stack as a key, using an
empty array
[]when that PR has no findings. - Each consolidated finding carries the round-2 core
shape:
location,label,subject,discussion, plus the optionaldecorations,severity,confidence,threadRelationfields. - Add optional
raisedBy(round-1 reviewer ids) andsourceFindingIds(round-1 finding ids) to record attribution. Omit both when the finding is judge synthesis.
crossPr
True cross-PR consolidated findings only. Each carries:
- The core finding fields.
homePrNumber— the PR where this finding should post.spans— non-empty array of PR numbers the finding refers to.- Optional
raisedByandsourceFindingIdsas above.
Membership rule
A finding under PR #101 must stay under perPr["101"]
unless it truly spans multiple PRs, in which case it
belongs in crossPr. Don't promote a per-PR finding to
cross-PR just because more than one reviewer surfaced it.
Synthesize, do not concatenate
Similar findings from multiple reviewers become one
consolidated finding with raisedBy and
sourceFindingIds. Don't list every reviewer's wording
separately.
Self-signal
Optional. When present, selfSignal.rationale must
contain non-whitespace prose: a concrete explanation of
your confidence. Blank rationales fail verification.
Self-verify before ending
The subagent has access to the verify_output tool from
the pr-workflow-stack-judge-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 item 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