soul-audit
Re-run or deepen the agent's identity interview. Drives the SHARED bootstrap answer bank (state/interview.json) via gbrain bootstrap interview --set/--show/--confirm, then re-renders the identity files with gbrain bootstrap render --only --force. One answer store, two surfaces: first-boot bootstrap and this re-run skill write the same bank, so an updated answer flows into SOUL.md, USER.md, ACCESSPOLICY.md, and HEARTBEAT.md without hand-editing rendered files. Every answer is the user's own words — never invented.
- Installs
- 253
- Last 24h
- +10
- Trending rank
- #8653
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/garrytan/gbrain --skill soul-audit- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads soul-audit automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Soul Audit — Agent Identity Builder (re-run / deepen surface)
Update the agent's identity through an interactive interview, any time after
bootstrap. This skill does NOT generate files from scratch and does NOT write
identity prose itself: it records the user's answers into the shared answer
bank, then lets the bootstrap render engine produce the files. That keeps one
source of truth — state/interview.json — no matter which surface (first-boot
bootstrap, this skill, a future re-audit) collected the answers.
IMPORTANT: Content comes from the USER'S OWN ANSWERS, recorded verbatim. NEVER invent, embellish, or default an identity answer. The render gate structurally refuses until required answers exist and were read back and confirmed by the human.
Contract
This skill guarantees:
- Answers land in the shared bank via
gbrain bootstrap interview --set KEY "value"(verbatim, one key per answer;--skip KEYrecords an explicit decline). - The read-back ritual runs before any render:
--showthe full answer set, mirror it to the user, then--confirm <hash>with the hash--statusprinted. Confirming a set the user never saw fails by design. - Files re-render through the ONE render path:
gbrain bootstrap render --only SOUL.md --force(repeat per file).--forcebacks the old file up under.gbrain-bootstrap-backups/<ts>/first — nothing is clobbered without a recoverable copy. - Each phase is independent and re-runnable; updating one answer and re-rendering one file is a complete, valid run.
The command loop
gbrain bootstrap interview --show # what the bank holds now (start here)
gbrain bootstrap interview --set KEY "..." # record one updated answer, verbatim
gbrain bootstrap interview --skip KEY # explicit decline for an optional key
gbrain bootstrap interview --status # gate + read-back hash
gbrain bootstrap interview --confirm <hash> # after reading answers back to the user
gbrain bootstrap render --only SOUL.md --force
Render targets: SOUL.md, USER.md, ACCESS_POLICY.md, HEARTBEAT.md,
AGENTS.md (re-render whichever files the changed keys feed). In an OpenClaw
workspace the HEARTBEAT.md target writes SCHEDULES.md, because OpenClaw
2026.10.6+ removes a workspace HEARTBEAT.md; render detects the workspace,
or pass --host openclaw.
Phases (each independent, each re-runnable)
Phase 1: Identity Interview
Ask: "What is this agent to you? Research partner? Executive assistant? Thinking
partner? All of the above?"
Keys: AGENT_NAME, AGENT_PURPOSE, SOUL_RELATIONSHIP. Renders: SOUL.md.
Phase 2: Vibe Calibration
Show 3-4 communication style examples:
- Formal: "I've prepared a comprehensive analysis of the situation..."
- Direct: "Here's what's happening. Three things matter."
- Technical: "The root cause is in the connection pooling. Here's the fix."
- Casual: "Yeah so basically the thing is broken because X. Easy fix."
Ask which feels right; also ask for a reply that made them wince and why.
Keys:
VOICE_REGISTER,SOUL_WINCE,SOUL_MODE_DEFAULT. Renders: SOUL.md.
Phase 3: Mission Mapping
Ask: "What are your top 3-5 goals? What are you trying to accomplish?"
Keys: AGENT_TOP_JOBS, SOUL_GOOD_OUTPUT, SOUL_WORLDVIEW. Renders: SOUL.md,
AGENTS.md.
Phase 4: User Profile
Ask: "Tell me about yourself. What do you do? What are you working on? Who are
the key people in your world?"
Keys: PRINCIPAL_NAME, PRINCIPAL_CONTEXT, PRINCIPAL_TIMEZONE. Renders:
USER.md.
Phase 5: Boundaries
Ask: "Who should have access to your brain? Are there people who should see some
but not all? Anyone to keep out entirely?"
Key: ACCESS_TIERS (and review the standing-disclosure sections). Renders:
ACCESS_POLICY.md.
Phase 6: Operational Cadence
Ask: "How often should the agent check in? Morning briefing? End of day summary?
What recurring jobs do you want?"
Keys: HEARTBEAT_CADENCE, QUIET_HOURS. Renders: HEARTBEAT.md (SCHEDULES.md on
OpenClaw). Jobs ship
disabled — enable one at a time after a manual dry run (the ritual is in the
rendered file).
Run gbrain bootstrap interview --init first if the bank does not exist yet
(a workspace that never ran bootstrap); it prints the full question list.
Output Format
Report exactly what changed: which keys were updated, which files re-rendered, and where the backups landed. Example: "Soul audit: updated VOICE_REGISTER + SOUL_WINCE, re-rendered SOUL.md (backup in .gbrain-bootstrap-backups/...). Re-run any phase anytime."
When it fails
Follow the agent operator protocol for any gbrain error code, exit code, [AGENT] block or notice block. Specific to this skill:
gbrain bootstrap interview --confirm <hash>fails: the hash must come from a read-back the user actually saw. Re-rungbrain bootstrap interview --status, read the answers back, and confirm only with the user's agreement.- Rendering refuses because required answers are missing: ask the user for them; never fill identity answers yourself.
Anti-Patterns
- Writing identity prose yourself instead of recording the user's words into the bank (the render engine is the only author of these files)
- Hand-editing SOUL.md/USER.md directly — the next render overwrites it; edit the ANSWER, then re-render
- Confirming a read-back hash for answers the user never saw
- Making the audit mandatory or asking all 6 phases in one go (overwhelming; each is independent — momentum beats completeness)
- Shipping pre-filled identity content (privacy violation)
- Not offering to re-run individual phases
FAQ
What does the soul-audit skill do?
Re-run or deepen the agent's identity interview. Drives the SHARED bootstrap answer bank (state/interview.json) via gbrain bootstrap interview --set/--show/--confirm, then re-renders the identity files with gbrain bootstrap render --only --force. One answer store, two surfaces: first-boot bootstrap and this re-run skill write the same bank, so an updated answer flows into SOUL.md, USER.md, ACCESSPOLICY.md, and HEARTBEAT.md without hand-editing rendered files. Every answer is the user's own words — never invented.
How do I install soul-audit?
Run npx skills add https://github.com/garrytan/gbrain --skill soul-audit in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/soul-audit/ (personal) or .claude/skills/soul-audit/ (project).
Which AI agents can use soul-audit?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is soul-audit safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains soul-audit?
It is published by garrytan in garrytan/gbrain. It has 253 recorded installs.
More from garrytan/gbrain
brain-ops
garrytan/gbrain
Brain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking. Read this before any brain interaction.
query
garrytan/gbrain
Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain.
maintain
garrytan/gbrain
Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.
idea-ingest
garrytan/gbrain
Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, credit the author (people page only when they pass the notability gate), and cross-link. Use when the user shares a link or says "read this", "save this", "think about this".
enrich
garrytan/gbrain
Enrich brain pages with tiered enrichment protocol. Creates and updates person/company pages with compiled truth, timeline, and cross-links. Use when a new entity is mentioned or an existing page needs updating.
meeting-ingestion
garrytan/gbrain
Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge. One unified pipeline: normalize the source into a standard transcript record, split multi-meeting recordings, resolve speakers by evidence, create the page, pass every surprising claim through the consistency check (transcript + brain + plausibility), enrich every entity, then run the verification checklist — substance AND sequence. A meeting is NOT fully ingested until the enrich skill has processed every entity AND the verification checklist passes, including the sequence verify (PASS or explicit user waive).
Popular security skills
azure-compliance
microsoft/azure-skills
Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized reprooutputs/ files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
seo-audit
coreyhaines31/marketingskills
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," "indexing issues," "stuck on page 2," "striking distance keywords," "title tag rewrite," "low CTR," "local SEO," "Google Business Profile," or "map pack." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema. For AI search optimization, see ai-seo.
firebase-security-rules-auditor
firebase/agent-skills
Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks. Use when auditing/reviewing rules, running red-team rule assessments, or scoring against auditor checklists. Don't use for Firebase CLI (login, deploy), Auth, Crashlytics, Remote Config, or database queries.
audit
pbakaus/impeccable
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
competitors
coreyhaines31/marketingskills
When the user wants to create competitor comparison or alternative pages for SEO and buyer-facing use. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'competitor teardown,' 'audit our competitor pages,' 'are our comparison pages out of date,' or 'competitive asset audit.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For auditing existing claims (not researching competitors from scratch, which is competitor-profiling; not technical SEO on these pages, which is seo-audit), use the asset audit here. For internal battle cards and sales-specific competitor docs, see sales-enablement.