Agent Persona Exploration - 2026-11-04
I maintainer di solito rispondono entro 1 giorno
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 2/5
- Tempo stimato
- 1-3 ore
- Idoneità per principianti
- 72/100
- Tipo di issue
- Documentazione
- Chiarezza
- Specificata chiaramente
- Stato di attività
- Attiva
- Stack tecnologico
- github, github-actions
- Ambito
- devtools, documentation
Direzione di ricerca
Leggi .github/aw/create-agentic-workflow-trigger-details.md e aggiorna l’esempio di audit di conformità descritto nell’issue: modifica il relativo permesso e aggiungi l’impostazione di rete. Poi esamina .github/aw/report.md e .github/aw/create-agentic-workflow.md per individuare le due raccomandazioni aggiuntive. Il lavoro è completato quando gli esempi e le indicazioni rispettano le regole di privilegio minimo e coerenza specificate nell’issue.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Persona Overview
- Agent:
agentic-workflows(via thepersona-evaluatorClaude Code sub-agent) - Personas This Run: Program Manager, Designer, Legal / Compliance (one-time baseline)
- Scenarios Tested: 4 (PM-1, DS-1, LC-1, LC-2). All 4 invocations succeeded.
- Average Quality Score: 4.3/5.0
Key Findings
- The trigger was right in every case. The scheduled scenarios used a fuzzy weekly schedule plus
workflow_dispatch. The PR scenarios usedpull_requestwithpaths:filters. DS-1 also addededited, so the review re-runs when the author adds a design link. - Permissions stayed read-only in all 4. Every write went through safe outputs. LC-2 even rejected the
issues: writeshown in the guide's own compliance-audit example. - Network scoping is inconsistent. DS-1 used
network.allowed: []. PM-1 and LC-2 usednetwork: defaults, even though they only read repository files and GitHub data.create-agentic-workflow.md§5 prescribesallowed: []for exactly the LC-2 case. - Every response stated its assumptions. Each one named an ambiguity, such as what "overdue dependency" means, where the policy file lives, or where the design link is expected, and gave a fallback.
- The prose and the frontmatter sketch sometimes disagree. In PM-1 the prose says to comment on an existing issue, but
add-commentisn't configured. In LC-1 the prose lists more lockfile paths than the sketch. In LC-2 the prose saysgh-proxy, but the sketch doesn't set that mode.
Top Patterns
- Triggers: fuzzy
schedule+workflow_dispatch(2 of 4);pull_request+paths:(2 of 4) - Tools:
githubin all 4 (withgh-proxyin 2).bashrestricted to read-only commands in 2 of 4. No web or browser tools were suggested. - Safe outputs:
create-issuewithclose-older-issuesfor the scheduled reports.add-commentwithhide-older-comments, plus anadd-labelsallowlist, for PR reviews.noopwas always defined. - Security: least-privilege
readpermissions in all 4.pull_requestis preferred overpull_request_target. LC-1 explicitly said to treat package metadata as untrusted data.
View Scores by Scenario
| ID | Persona | Trigger | Tools | Security | Prompt | Complete | Avg |
|---|---|---|---|---|---|---|---|
| PM-1 | Program Manager | 5 | 4 | 3 | 4 | 4 | 4.0 |
| DS-1 | Designer | 5 | 5 | 5 | 5 | 4 | 4.8 |
| LC-1 | Legal / Compliance | 5 | 4 | 4 | 5 | 4 | 4.4 |
| LC-2 | Legal / Compliance | 5 | 4 | 3 | 4 | 4 | 4.0 |
View High Quality Responses (Top 2)
-
DS-1, design token review (4.8):
- Uses the
editedtrigger type so the review re-runs when a link is added. - Sets
network.allowed: [], and checks design links only for presence and format, without fetching them. - Applies concrete WCAG 2.2 contrast thresholds (4.5:1 and 3:1).
- Lists the components affected by renamed tokens.
- Restricts labels with
add-labelsallowed:. - Posts one rolling comment, using
hide-older-comments.
- Uses the
-
LC-1, SPDX license gate (4.4):
- Sorts licenses into allowed, disallowed and uncertain.
NOASSERTION, custom licenses and uncovered OR/AND/WITH expressions go to human review. - Has an explicit "never guess a license" rule.
- Keeps the workflow advisory (no blocking review) and offers
create-check-runas an option for a hard gate.
- Sorts licenses into allowed, disallowed and uncertain.
View Areas for Improvement (Top 3)
-
Network defaults on audits that only read the repository (PM-1, LC-2):
- Both used
network: defaultseven thoughworkflow-constraints.md:48andcreate-agentic-workflow.md:211say to useallowed: []. - Likely cause: the scheduled compliance-audit example in
create-agentic-workflow-trigger-details.md(around lines 109–124) has nonetwork:block and grantsissues: write.
- Both used
-
Ecosystems not inferred from the repository (LC-1): LC-1 enabled six ecosystems (
node,python,go,rust,java,ruby) up front. The §5 guidance says to infer them from the manifests. -
Prose and sketch drift:
- PM-1's dedup plan says to comment on an existing issue, but there is no
add-commentsafe output. Its weekly dedup key also overlaps withclose-older-issues. - LC-2 uses a monthly dedup key on a weekly schedule.
- LC-1's bash allowlist uses
"git diff:*", which differs from the documented"cmd *"and bare-command forms.
- PM-1's dedup plan says to comment on an existing issue, but there is no
Recommendations
- Fix the compliance-audit example in
.github/aw/create-agentic-workflow-trigger-details.md. Changeissues: writetoissues: readand addnetwork: { allowed: [] }. The agent appears to copy this sample, and today it contradictscreate-agentic-workflow.md§5 and the strict-mode rules. - Add a scheduled-report network rule to
.github/aw/report.md. State that digests and audits that only read GitHub throughgh-proxyshould usenetwork.allowed: [], notdefaults. PM-1 shows the gap for non-compliance digests. - Add a consistency check to the ad hoc evaluation checklist in
.github/aw/create-agentic-workflow.md. Every action the prompt describes (for example "comment on the existing issue") needs a matching configured safe output. The dedup-key granularity should match the schedule cadence. Ecosystems should be inferred from the manifests that actually exist.
References:
Generated by 🎭 Agent Persona Explorer · claude · routed: opus55 high · ~128 AIC · ⌖ ~2 AIC · ⊞ 6.6K · ◷
- Lingua principale
- Go
- Stelle
- 5.6k
- Fork
- 615
- Merge medio
- 5h 19m
- PR unite (30g)
- 798
Preparare l'ambiente
Avvia il container di sviluppo del progetto nel browser, con il tuo account GitHub.
- Include un Dockerfile o un file Docker Compose
- Nessun modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di github/gh-aw
-
automated-analysis code-quality cookie enhancement report safe-outputs testing workflows
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
I maintainer di solito rispondono entro 1 giorno
-
ai-inspected community model-routing
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
I maintainer di solito rispondono entro 1 giorno
-
ai-inspected community model-routing
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
I maintainer di solito rispondono entro 1 giorno
-
automation cli-tools testing
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
I maintainer di solito rispondono entro 1 giorno
-
cookie maintenance step-naming
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 74/100
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di github/gh-aw
Issue simili
-
needs-triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
I maintainer di solito rispondono entro 1 giorno
-
WriterSetTimes: the UTIME_NOW check fails when the kernel uses its coarse clockForse già presa @JakeChampion l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
JakeChampion/lang#14224 ·
I maintainer di solito rispondono entro 1 giorno
-
agent-butler-finding bug
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 88/100
jordansmall/spindrift#6391 ·
I maintainer di solito rispondono entro 1 giorno
-
common.Retry: data race on the shared response/err variables when the request context ends mid-attempt (v65.127.0, v65.128.0)Forse già presa @kmohit00 l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
oracle/oci-go-sdk#676 ·
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 65/100
SAP/crossplane-provider-btp#1175 ·
I maintainer di solito rispondono entro 1 giorno